Merge release 2.4.3

2012-11-02 17:45:58 +04:00
parent 66b90d19a6 6484732509
commit 4d059e9e5b
126 changed files with 61518 additions and 51142 deletions
--- a/modules/calib3d/perf/perf_pnp.cpp
+++ b/modules/calib3d/perf/perf_pnp.cpp
@@ -55,7 +55,7 @@ PERF_TEST_P(PointsNum_Algo, solvePnP,
    }

    SANITY_CHECK(rvec, 1e-6);
-    SANITY_CHECK(tvec, 1e-6);
+    SANITY_CHECK(tvec, 1e-3);
 }

 PERF_TEST(PointsNum_Algo, solveP3P)
--- a/modules/calib3d/perf/perf_precomp.hpp
+++ b/modules/calib3d/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/calib3d/test/test_cameracalibration_artificial.cpp
+++ b/modules/calib3d/test/test_cameracalibration_artificial.cpp
@@ -426,4 +426,4 @@ protected:
    }
 };

-TEST(Calib3d_CalibrateCamera_CPP, accuracy_on_artificial_data) { CV_CalibrateCameraArtificialTest test; test.safe_run(); }
+TEST(Calib3d_CalibrateCamera_CPP, DISABLED_accuracy_on_artificial_data) { CV_CalibrateCameraArtificialTest test; test.safe_run(); }
--- a/modules/calib3d/test/test_precomp.hpp
+++ b/modules/calib3d/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/contrib/doc/contrib.rst
+++ b/modules/contrib/doc/contrib.rst
@@ -10,3 +10,4 @@ The module contains some recently added functionality that has not been stabiliz
    stereo
    FaceRecognizer Documentation <facerec/index>
    Retina Documentation <retina/index>
+    openfabmap
--- a/modules/contrib/doc/openfabmap.rst
+++ b/modules/contrib/doc/openfabmap.rst
@@ -1,4 +1,4 @@
-openFABMAP
+OpenFABMAP
 ========================================

 .. highlight:: cpp
--- a/modules/contrib/test/test_precomp.hpp
+++ b/modules/contrib/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/core/doc/operations_on_arrays.rst
+++ b/modules/core/doc/operations_on_arrays.rst
@@ -13,17 +13,17 @@ Calculates an absolute value of each matrix element.
    :param m: matrix.
    :param e: matrix expression.

-``abs`` is a meta-function that is expanded to one of :ocv:func:`absdiff` forms:
+``abs`` is a meta-function that is expanded to one of :ocv:func:`absdiff` or :ocv:func:`convertScaleAbs` forms:

    * ``C = abs(A-B)``     is equivalent to ``absdiff(A, B, C)``

    * ``C = abs(A)``     is equivalent to ``absdiff(A, Scalar::all(0), C)``

-    * ``C = Mat_<Vec<uchar,n> >(abs(A*alpha + beta))``     is equivalent to :ocv:funcx:`convertScaleAbs` (A, C, alpha, beta)
+    * ``C = Mat_<Vec<uchar,n> >(abs(A*alpha + beta))``     is equivalent to  ``convertScaleAbs(A, C, alpha, beta)``

 The output matrix has the same size and the same type as the input one except for the last case, where ``C`` is ``depth=CV_8U`` .

-    .. seealso:: :ref:`MatrixExpressions`, :ocv:func:`absdiff`
+    .. seealso:: :ref:`MatrixExpressions`, :ocv:func:`absdiff`, :ocv:func:`convertScaleAbs`


 absdiff
--- a/modules/core/include/opencv2/core/internal.hpp
+++ b/modules/core/include/opencv2/core/internal.hpp
@@ -59,16 +59,7 @@
 #  endif
 #endif

-#if defined WIN32 || defined WINCE
-#  ifndef _WIN32_WINNT         // This is needed for the declaration of TryEnterCriticalSection in winbase.h with Visual Studio 2005 (and older?)
-#    define _WIN32_WINNT 0x0400  // http://msdn.microsoft.com/en-us/library/ms686857(VS.85).aspx
-#  endif
-#  include <windows.h>
-#  undef small
-#  undef min
-#  undef max
-#  undef abs
-#else
+#if !defined WIN32 && !defined WINCE
 #  include <pthread.h>
 #endif

--- a/modules/core/include/opencv2/core/operations.hpp
+++ b/modules/core/include/opencv2/core/operations.hpp
@@ -56,7 +56,13 @@
  #define CV_XADD(addr,delta) _InterlockedExchangeAdd(const_cast<void*>(reinterpret_cast<volatile void*>(addr)), delta)
 #elif defined __GNUC__

-  #if __GNUC__*10 + __GNUC_MINOR__ >= 42
+  #if defined __clang__ && __clang_major__ >= 3
+    #ifdef __ATOMIC_SEQ_CST
+        #define CV_XADD(addr, delta) __c11_atomic_fetch_add((_Atomic(int)*)(addr), (delta), __ATOMIC_SEQ_CST)
+    #else
+        #define CV_XADD(addr, delta) __atomic_fetch_add((_Atomic(int)*)(addr), (delta), 5)
+    #endif
+  #elif __GNUC__*10 + __GNUC_MINOR__ >= 42

    #if !defined WIN32 && (defined __i486__ || defined __i586__ || \
        defined __i686__ || defined __MMX__ || defined __SSE__  || defined __ppc__)
@@ -2460,18 +2466,10 @@ dot(const Vector<_Tp>& v1, const Vector<_Tp>& v2)
    assert(v1.size() == v2.size());

    _Tw s = 0;
-    if( n > 0 )
-    {
-        const _Tp *ptr1 = &v1[0], *ptr2 = &v2[0];
-     #if CV_ENABLE_UNROLLED
-        const size_t n2 = (n > 4) ? n : 4;
-        for(; i <= n2 - 4; i += 4 )
-            s += (_Tw)ptr1[i]*ptr2[i] + (_Tw)ptr1[i+1]*ptr2[i+1] +
-                (_Tw)ptr1[i+2]*ptr2[i+2] + (_Tw)ptr1[i+3]*ptr2[i+3];
-    #endif
-        for( ; i < n; i++ )
-            s += (_Tw)ptr1[i]*ptr2[i];
-    }
+    const _Tp *ptr1 = &v1[0], *ptr2 = &v2[0];
+    for( ; i < n; i++ )
+        s += (_Tw)ptr1[i]*ptr2[i];
+
    return s;
 }

--- a/modules/core/perf/perf_addWeighted.cpp
+++ b/modules/core/perf/perf_addWeighted.cpp
@@ -25,12 +25,12 @@ PERF_TEST_P(Size_MatType, addWeighted, TYPICAL_MATS_ADWEIGHTED)

    if (CV_MAT_DEPTH(type) == CV_32S)
    {
-        //see ticket 1529: absdiff can be without saturation on 32S
-        src1 /= 8;
-        src2 /= 8;
+        // there might be not enough precision for integers
+        src1 /= 2048;
+        src2 /= 2048;
    }

    TEST_CYCLE() cv::addWeighted( src1, alpha, src2, beta, gamma, dst, dst.type() );

-    SANITY_CHECK(dst);
+    SANITY_CHECK(dst, 1);
 }
--- a/modules/core/perf/perf_precomp.hpp
+++ b/modules/core/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/core/src/algorithm.cpp
+++ b/modules/core/src/algorithm.cpp
@@ -430,7 +430,10 @@ void AlgorithmInfo::write(const Algorithm* algo, FileStorage& fs) const
            nestedAlgo->write(fs);
        }
        else
-            CV_Error( CV_StsUnsupportedFormat, "unknown/unsupported parameter type");
+        {
+            string msg = format("unknown/unsupported type of '%s' parameter == %d", pname.c_str(), p.type);
+            CV_Error( CV_StsUnsupportedFormat, msg.c_str());
+        }
    }
 }

@@ -486,7 +489,10 @@ void AlgorithmInfo::read(Algorithm* algo, const FileNode& fn) const
            info->set(algo, pname.c_str(), p.type, &nestedAlgo, true);
        }
        else
-            CV_Error( CV_StsUnsupportedFormat, "unknown/unsupported parameter type");
+        {
+            string msg = format("unknown/unsupported type of '%s' parameter == %d", pname.c_str(), p.type);
+            CV_Error( CV_StsUnsupportedFormat, msg.c_str());
+        }
    }
 }

@@ -777,7 +783,10 @@ void AlgorithmInfo::get(const Algorithm* algo, const char* parameter, int argTyp
            *(Ptr<Algorithm>*)((uchar*)algo + p->offset);
    }
    else
-        CV_Error(CV_StsBadArg, "Unknown/unsupported parameter type");
+    {
+        string message = getErrorMessageForWrongArgumentInGetter(algo->name(), parameter, p->type, argType);
+        CV_Error(CV_StsBadArg, message);
+    }
 }


--- a/modules/core/src/parallel.cpp
+++ b/modules/core/src/parallel.cpp
@@ -42,6 +42,14 @@

 #include "precomp.hpp"

+#if defined WIN32 || defined WINCE
+    #include <windows.h>
+    #undef small
+    #undef min
+    #undef max
+    #undef abs
+#endif
+
 #if defined __linux__ || defined __APPLE__
    #include <unistd.h>
    #include <stdio.h>
--- a/modules/core/src/rand.cpp
+++ b/modules/core/src/rand.cpp
@@ -48,8 +48,16 @@

 #include "precomp.hpp"

+#if defined WIN32 || defined WINCE
+    #include <windows.h>
+    #undef small
+    #undef min
+    #undef max
+    #undef abs
+#endif
+
 #if defined __SSE2__ || (defined _M_IX86_FP && 2 == _M_IX86_FP)
-#include "emmintrin.h"
+    #include "emmintrin.h"
 #endif

 namespace cv
--- a/modules/core/src/system.cpp
+++ b/modules/core/src/system.cpp
@@ -43,6 +43,14 @@
 #include "precomp.hpp"

 #if defined WIN32 || defined _WIN32 || defined WINCE
+#ifndef _WIN32_WINNT           // This is needed for the declaration of TryEnterCriticalSection in winbase.h with Visual Studio 2005 (and older?)
+  #define _WIN32_WINNT 0x0400  // http://msdn.microsoft.com/en-us/library/ms686857(VS.85).aspx
+#endif
+#include <windows.h>
+#undef small
+#undef min
+#undef max
+#undef abs
 #include <tchar.h>
 #if defined _MSC_VER
  #if _MSC_VER >= 1400
--- a/modules/core/test/test_precomp.hpp
+++ b/modules/core/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/features2d/perf/perf_fast.cpp
+++ b/modules/features2d/perf/perf_fast.cpp
@@ -30,10 +30,14 @@ PERF_TEST_P(fast, detect, testing::Combine(

    declare.in(frame);

-    FastFeatureDetector fd(20, true, type);
+    Ptr<FeatureDetector> fd = Algorithm::create<FeatureDetector>("Feature2D.FAST");
+    ASSERT_FALSE( fd == 0 );
+    fd->set("threshold", 20);
+    fd->set("nonmaxSuppression", true);
+    fd->set("type", type);
    vector<KeyPoint> points;

-    TEST_CYCLE() fd.detect(frame, points);
+    TEST_CYCLE() fd->detect(frame, points);

    SANITY_CHECK_KEYPOINTS(points);
 }
--- a/modules/features2d/perf/perf_orb.cpp
+++ b/modules/features2d/perf/perf_orb.cpp
@@ -22,7 +22,7 @@ PERF_TEST_P(orb, detect, testing::Values(ORB_IMAGES))

    Mat mask;
    declare.in(frame);
-    ORB detector(1500, 1.3f, 5);
+    ORB detector(1500, 1.3f, 1);
    vector<KeyPoint> points;

    TEST_CYCLE() detector(frame, mask, points);
@@ -42,7 +42,7 @@ PERF_TEST_P(orb, extract, testing::Values(ORB_IMAGES))
    Mat mask;
    declare.in(frame);

-    ORB detector(1500, 1.3f, 5);
+    ORB detector(1500, 1.3f, 1);
    vector<KeyPoint> points;
    detector(frame, mask, points);
    sort(points.begin(), points.end(), comparators::KeypointGreater());
@@ -64,7 +64,7 @@ PERF_TEST_P(orb, full, testing::Values(ORB_IMAGES))

    Mat mask;
    declare.in(frame);
-    ORB detector(1500, 1.3f, 5);
+    ORB detector(1500, 1.3f, 1);

    vector<KeyPoint> points;
    Mat descriptors;
--- a/modules/features2d/perf/perf_precomp.hpp
+++ b/modules/features2d/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/features2d/src/fast.cpp
+++ b/modules/features2d/src/fast.cpp
@@ -259,6 +259,10 @@ void FAST(InputArray _img, std::vector<KeyPoint>& keypoints, int threshold, bool
      FAST_t<12>(_img, keypoints, threshold, nonmax_suppression);
      break;
    case FastFeatureDetector::TYPE_9_16:
+#ifdef HAVE_TEGRA_OPTIMIZATION
+      if(tegra::FAST(_img, keypoints, threshold, nonmax_suppression))
+        break;
+#endif
      FAST_t<16>(_img, keypoints, threshold, nonmax_suppression);
      break;
  }
--- a/modules/features2d/src/precomp.hpp
+++ b/modules/features2d/src/precomp.hpp
@@ -52,4 +52,8 @@
 #include "opencv2/imgproc/imgproc_c.h"
 #include "opencv2/core/internal.hpp"

+#ifdef HAVE_TEGRA_OPTIMIZATION
+#include "opencv2/features2d/features2d_tegra.hpp"
+#endif
+
 #endif
--- a/modules/features2d/test/test_precomp.hpp
+++ b/modules/features2d/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/gpu/doc/image_processing.rst
+++ b/modules/gpu/doc/image_processing.rst
@@ -886,7 +886,7 @@ gpu::FastNonLocalMeansDenoising
 The class implements fast approximate Non Local Means Denoising algorithm.

 gpu::FastNonLocalMeansDenoising::simpleMethod()
-------------------------------------
+-----------------------------------------------
 Perform image denoising using Non-local Means Denoising algorithm http://www.ipol.im/pub/algo/bcm_non_local_means_denoising with several computational optimizations. Noise expected to be a gaussian white noise

 .. ocv:function:: void gpu::FastNonLocalMeansDenoising::simpleMethod(const GpuMat& src, GpuMat& dst, float h, int search_window = 21, int block_size = 7, Stream& s = Stream::Null())
@@ -910,7 +910,7 @@ This function expected to be applied to grayscale images. For colored images loo
    :ocv:func:`fastNlMeansDenoising`

 gpu::FastNonLocalMeansDenoising::labMethod()
-------------------------------------
+--------------------------------------------
 Modification of ``FastNonLocalMeansDenoising::simpleMethod`` for color images

 .. ocv:function:: void gpu::FastNonLocalMeansDenoising::labMethod(const GpuMat& src, GpuMat& dst, float h_luminance, float h_color, int search_window = 21, int block_size = 7, Stream& s = Stream::Null())
--- a/modules/gpu/perf/perf_precomp.hpp
+++ b/modules/gpu/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/gpu/src/precomp.hpp
+++ b/modules/gpu/src/precomp.hpp
@@ -73,6 +73,14 @@
 #include "opencv2/core/internal.hpp"
 #include "opencv2/video/video.hpp"

+#if defined WIN32 || defined WINCE
+    #include <windows.h>
+    #undef small
+    #undef min
+    #undef max
+    #undef abs
+#endif
+
 #define OPENCV_GPU_UNUSED(x) (void)x

 #ifdef HAVE_CUDA
--- a/modules/gpu/test/test_labeling.cpp
+++ b/modules/gpu/test/test_labeling.cpp
@@ -135,7 +135,7 @@ namespace {

            int outliers = 0;
            for (int j = 0; j < image.rows; ++j)
-                for (int i = 0; i < image.cols; ++i)
+                for (int i = 0; i < image.cols - 1; ++i)
                {
                    if ( (_labels.at<int>(j,i) == gpu.at<int>(j,i + 1)) && (diff.at<int>(j, i) != diff.at<int>(j,i + 1)))
                    {
--- a/modules/gpu/test/test_precomp.hpp
+++ b/modules/gpu/test/test_precomp.hpp
@@ -41,7 +41,10 @@

 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/highgui/doc/reading_and_writing_images_and_video.rst
+++ b/modules/highgui/doc/reading_and_writing_images_and_video.rst
@@ -75,11 +75,11 @@ Loads an image from a file.

    :param flags: Flags specifying the color type of a loaded image:

-        * 1 -
-        * CV_LOAD_IMAGE_ANYDEPTH -
-        CV_LOAD_IMAGE_COLOR
-        CV_LOAD_IMAGE_GRAYSCALE
+        * CV_LOAD_IMAGE_ANYDEPTH - If set, return 16-bit/32-bit image when the input has the corresponding depth, otherwise convert it to 8-bit.

+        * CV_LOAD_IMAGE_COLOR - If set, always convert image to the color one
+
+        * CV_LOAD_IMAGE_GRAYSCALE - If set, always convert image to the grayscale one

        * **>0**  Return a 3-channel color image.
            .. note:: In the current implementation the alpha channel, if any, is stripped from the output image. Use negative value if you need the alpha channel.
--- a/modules/highgui/perf/perf_input.cpp
+++ b/modules/highgui/perf/perf_input.cpp
@@ -6,6 +6,8 @@ using namespace perf;
 using std::tr1::make_tuple;
 using std::tr1::get;

+#ifndef ANDROID
+
 typedef perf::TestBaseWithParam<String> VideoCapture_Reading;

 PERF_TEST_P(VideoCapture_Reading, ReadFile, testing::Values( "highgui/video/big_buck_bunny.avi",
@@ -23,3 +25,5 @@ PERF_TEST_P(VideoCapture_Reading, ReadFile, testing::Values( "highgui/video/big_
  bool dummy = cap.isOpened();
  SANITY_CHECK(dummy);
 }
+
+#endif //ANDROID
--- a/modules/highgui/perf/perf_output.cpp
+++ b/modules/highgui/perf/perf_output.cpp
@@ -6,6 +6,8 @@ using namespace perf;
 using std::tr1::make_tuple;
 using std::tr1::get;

+#ifndef ANDROID
+
 typedef std::tr1::tuple<String, bool> VideoWriter_Writing_t;
 typedef perf::TestBaseWithParam<VideoWriter_Writing_t> VideoWriter_Writing;

@@ -28,3 +30,5 @@ PERF_TEST_P(VideoWriter_Writing, WriteFrame,
  bool dummy = writer.isOpened();
  SANITY_CHECK(dummy);
 }
+
+#endif //ANDROID
--- a/modules/highgui/perf/perf_precomp.hpp
+++ b/modules/highgui/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/highgui/src/precomp.hpp
+++ b/modules/highgui/src/precomp.hpp
@@ -49,11 +49,6 @@
 #include "opencv2/imgproc/imgproc_c.h"
 #include "opencv2/core/internal.hpp"

-#if defined WIN32 || defined _WIN32
-//required windows.h has to be included by the opencv2/core/internal.hpp
-void  FillBitmapInfo( BITMAPINFO* bmi, int width, int height, int bpp, int origin );
-#endif
-
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
@@ -61,6 +56,14 @@ void  FillBitmapInfo( BITMAPINFO* bmi, int width, int height, int bpp, int origi
 #include <ctype.h>
 #include <assert.h>

+#if defined WIN32 || defined WINCE
+    #include <windows.h>
+    #undef small
+    #undef min
+    #undef max
+    #undef abs
+#endif
+
 #ifdef HAVE_TEGRA_OPTIMIZATION
 #include "opencv2/highgui/highgui_tegra.hpp"
 #endif
--- a/modules/highgui/src/window_w32.cpp
+++ b/modules/highgui/src/window_w32.cpp
@@ -106,7 +106,7 @@ static const char* trackbar_text =

 #endif

-void FillBitmapInfo( BITMAPINFO* bmi, int width, int height, int bpp, int origin )
+static void FillBitmapInfo( BITMAPINFO* bmi, int width, int height, int bpp, int origin )
 {
    assert( bmi && width >= 0 && height >= 0 && (bpp == 8 || bpp == 24 || bpp == 32));

--- a/modules/highgui/test/test_precomp.hpp
+++ b/modules/highgui/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/highgui/test/test_video_io.cpp
+++ b/modules/highgui/test/test_video_io.cpp
@@ -143,7 +143,7 @@ void CV_HighGuiTest::ImageTest(const string& dir)
 #ifdef HAVE_JASPER
        "jp2",
 #endif
-#if defined HAVE_OPENEXR && !defined __APPLE__
+#if 0 /*defined HAVE_OPENEXR && !defined __APPLE__*/
        "exr",
 #endif
        "bmp",
--- a/modules/imgproc/perf/perf_precomp.hpp
+++ b/modules/imgproc/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/imgproc/perf/perf_warp.cpp
+++ b/modules/imgproc/perf/perf_warp.cpp
@@ -43,7 +43,7 @@ PERF_TEST_P( TestWarpAffine, WarpAffine,

    TEST_CYCLE() warpAffine( src, dst, warpMat, sz, interType, borderMode, Scalar::all(150) );

-    SANITY_CHECK(dst);
+    SANITY_CHECK(dst, 1);

 }

@@ -78,7 +78,7 @@ PERF_TEST_P( TestWarpPerspective, WarpPerspective,

    TEST_CYCLE() warpPerspective( src, dst, warpMat, sz, interType, borderMode, Scalar::all(150) );

-    SANITY_CHECK(dst);
+    SANITY_CHECK(dst, 1);
 }

 PERF_TEST_P( TestWarpPerspectiveNear_t, WarpPerspectiveNear,
@@ -119,7 +119,7 @@ PERF_TEST_P( TestWarpPerspectiveNear_t, WarpPerspectiveNear,

    resize(src, src, size);

-    int shift = src.cols*0.04;
+    int shift = static_cast<int>(src.cols*0.04);
    Mat srcVertices = (Mat_<Vec2f>(1, 4) << Vec2f(0, 0),
                                            Vec2f(static_cast<float>(size.width-1), 0),
                                            Vec2f(static_cast<float>(size.width-1), static_cast<float>(size.height-1)),
@@ -139,7 +139,7 @@ PERF_TEST_P( TestWarpPerspectiveNear_t, WarpPerspectiveNear,
        warpPerspective( src, dst, warpMat, size, interType, borderMode, Scalar::all(150) );
    }

-    SANITY_CHECK(dst);
+    SANITY_CHECK(dst, 1);
 }

 PERF_TEST_P( TestRemap, remap,
--- a/modules/imgproc/test/test_precomp.hpp
+++ b/modules/imgproc/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/java/android_test/src/org/opencv/test/features2d/BruteForceDescriptorMatcherTest.java
+++ b/modules/java/android_test/src/org/opencv/test/features2d/BruteForceDescriptorMatcherTest.java
@@ -84,11 +84,11 @@ public class BruteForceDescriptorMatcherTest extends OpenCVTestCase {
        matSize = 100;

        truth = new DMatch[] {
-                new DMatch(0, 0, 0, 1.049694f),
-                new DMatch(1, 0, 0, 1.066820f),
-                new DMatch(2, 1, 0, 0.494587f),
-                new DMatch(3, 0, 0, 1.141826f),
-                new DMatch(4, 0, 0, 1.084099f)
+                new DMatch(0, 0, 0, 1.0496940f),
+                new DMatch(1, 0, 0, 1.0984558f),
+                new DMatch(2, 1, 0, 0.4945875f),
+                new DMatch(3, 1, 0, 0.48435235f),
+                new DMatch(4, 0, 0, 1.0836693f)
                };

        super.setUp();
@@ -206,6 +206,7 @@ public class BruteForceDescriptorMatcherTest extends OpenCVTestCase {
        matcher.add(Arrays.asList(train));

        matcher.match(query, matches);
+
        assertArrayDMatchEquals(truth, matches.toArray(), EPS);
    }

--- a/modules/java/android_test/src/org/opencv/test/features2d/BruteForceL1DescriptorMatcherTest.java
+++ b/modules/java/android_test/src/org/opencv/test/features2d/BruteForceL1DescriptorMatcherTest.java
@@ -84,11 +84,11 @@ public class BruteForceL1DescriptorMatcherTest extends OpenCVTestCase {
        matSize = 100;

        truth = new DMatch[] {
-                new DMatch(0, 1, 0, 6.9202332f),
-                new DMatch(1, 0, 0, 6.0567350f),
-                new DMatch(2, 1, 0, 2.6798587f),
-                new DMatch(3, 0, 0, 5.8991642f),
-                new DMatch(4, 0, 0, 6.1321812f)
+                new DMatch(0, 1, 0, 6.9202340f),
+                new DMatch(1, 1, 0, 6.1675916f),
+                new DMatch(2, 1, 0, 2.6798590f),
+                new DMatch(3, 1, 0, 2.6545324f),
+                new DMatch(4, 0, 0, 6.1294870f)
                };
        super.setUp();
    }
@@ -183,6 +183,7 @@ public class BruteForceL1DescriptorMatcherTest extends OpenCVTestCase {
        matcher.add(Arrays.asList(train));

        matcher.match(query, matches);
+
        assertArrayDMatchEquals(truth, matches.toArray(), EPS);
    }

--- a/modules/java/android_test/src/org/opencv/test/features2d/BruteForceSL2DescriptorMatcherTest.java
+++ b/modules/java/android_test/src/org/opencv/test/features2d/BruteForceSL2DescriptorMatcherTest.java
@@ -89,11 +89,11 @@ public class BruteForceSL2DescriptorMatcherTest extends OpenCVTestCase {
        matSize = 100;

        truth = new DMatch[] {
-                new DMatch(0, 0, 0, 1.1018578f),
-                new DMatch(1, 0, 0, 1.1381058f),
+                new DMatch(0, 0, 0, 1.1018573f),
+                new DMatch(1, 0, 0, 1.2066052f),
                new DMatch(2, 1, 0, 0.2446168f),
-                new DMatch(3, 0, 0, 1.3037685f),
-                new DMatch(4, 0, 0, 1.1752719f)
+                new DMatch(3, 1, 0, 0.23459719f),
+                new DMatch(4, 0, 0, 1.174339f)
                };

        super.setUp();
@@ -189,9 +189,10 @@ public class BruteForceSL2DescriptorMatcherTest extends OpenCVTestCase {
        matcher.add(Arrays.asList(train));

        matcher.match(query, matches);
-OpenCVTestRunner.Log(matches);
-OpenCVTestRunner.Log(matches);
-OpenCVTestRunner.Log(matches);
+        OpenCVTestRunner.Log(matches);
+        OpenCVTestRunner.Log(matches);
+        OpenCVTestRunner.Log(matches);
+
        assertArrayDMatchEquals(truth, matches.toArray(), EPS);
    }

--- a/modules/java/android_test/src/org/opencv/test/features2d/FASTFeatureDetectorTest.java
+++ b/modules/java/android_test/src/org/opencv/test/features2d/FASTFeatureDetectorTest.java
@@ -128,7 +128,9 @@ public class FASTFeatureDetectorTest extends OpenCVTestCase {
        detector.write(filename);

        String truth = "<?xml version=\"1.0\"?>\n<opencv_storage>\n<name>Feature2D.FAST</name>\n<nonmaxSuppression>1</nonmaxSuppression>\n<threshold>10</threshold>\n</opencv_storage>\n";
-        assertEquals(truth, readFile(filename));
+        String data = readFile(filename);
+
+        assertEquals(truth, data);
    }

    public void testWriteYml() {
@@ -137,7 +139,8 @@ public class FASTFeatureDetectorTest extends OpenCVTestCase {
        detector.write(filename);

        String truth = "%YAML:1.0\nname: \"Feature2D.FAST\"\nnonmaxSuppression: 1\nthreshold: 10\n";
-        assertEquals(truth, readFile(filename));
-    }
+        String data = readFile(filename);

+        assertEquals(truth, data);
+    }
 }
--- a/modules/java/android_test/src/org/opencv/test/features2d/FlannBasedDescriptorMatcherTest.java
+++ b/modules/java/android_test/src/org/opencv/test/features2d/FlannBasedDescriptorMatcherTest.java
@@ -159,10 +159,10 @@ public class FlannBasedDescriptorMatcherTest extends OpenCVTestCase {

        truth = new DMatch[] {
                new DMatch(0, 0, 0, 1.049694f),
-                new DMatch(1, 0, 0, 1.066820f),
-                new DMatch(2, 1, 0, 0.494587f),
-                new DMatch(3, 0, 0, 1.141826f),
-                new DMatch(4, 0, 0, 1.084099f)
+                new DMatch(1, 0, 0, 1.0984558f),
+                new DMatch(2, 1, 0, 0.4945875f),
+                new DMatch(3, 1, 0, 0.48435235f),
+                new DMatch(4, 0, 0, 1.0836693f)
                };

        super.setUp();
--- a/modules/java/android_test/src/org/opencv/test/features2d/SIFTDescriptorExtractorTest.java
+++ b/modules/java/android_test/src/org/opencv/test/features2d/SIFTDescriptorExtractorTest.java
@@ -34,11 +34,14 @@ public class SIFTDescriptorExtractorTest extends OpenCVTestCase {
        truth = new Mat(1, 128, CvType.CV_32FC1) {
            {
                put(0, 0,
-                        0, 0, 0, 0, 0, 0, 0, 0, 16, 12, 17, 28, 26, 0, 0, 2, 23, 14, 12, 9, 6, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-                        14, 88, 23, 17, 24, 29, 0, 117, 54, 117, 116, 117, 22, 29, 27, 117, 59, 76, 19, 30, 2, 9, 26, 2, 7, 6, 0, 0,
-                        0, 0, 0, 0, 8, 50, 16, 30, 58, 89, 0, 117, 49, 95, 75, 117, 112, 117, 93, 81, 86, 117, 5, 5, 39, 117, 71, 20,
-                        20, 12, 0, 0, 1, 20, 19, 0, 0, 0, 2, 14, 4, 1, 0, 69, 0, 0, 14, 90, 31, 35, 56, 25, 0, 0, 0, 0, 2, 12, 16, 0,
-                        0, 0, 0, 0, 0, 2, 1);
+                          0, 0, 0, 1, 3, 0, 0, 0, 15, 23, 22, 20, 24, 2, 0, 0, 7, 8, 2, 0,
+                          0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 27, 16, 13, 2, 0, 0, 117,
+                          86, 79, 68, 117, 42, 5, 5, 79, 60, 117, 25, 9, 2, 28, 19, 11, 13,
+                          20, 2, 0, 0, 5, 8, 0, 0, 76, 58, 34, 31, 97, 16, 95, 49, 117, 92,
+                          117, 112, 117, 76, 117, 54, 117, 25, 29, 22, 117, 117, 16, 11, 14,
+                          1, 0, 0, 22, 26, 0, 0, 0, 0, 1, 4, 15, 2, 47, 8, 0, 0, 82, 56, 31,
+                          17, 81, 12, 0, 0, 26, 23, 18, 23, 0, 0, 0, 0, 0, 0, 0, 0
+                   );
            }
        };

@@ -76,18 +79,7 @@ public class SIFTDescriptorExtractorTest extends OpenCVTestCase {
    }

    public void testRead() {
-        MatOfKeyPoint keypoints =new MatOfKeyPoint(keypoint);
-        Mat img = getTestImg();
-        Mat descriptors = new Mat();
-
-        String filename = OpenCVTestRunner.getTempFileName("yml");
-        writeFile(filename,
-                "%YAML:1.0\nmagnification: 3.\nisNormalize: 1\nrecalculateAngles: 1\nnOctaves: 6\nnOctaveLayers: 4\nfirstOctave: -1\nangleMode: 0\n");
-
-        extractor.read(filename);
-
-        extractor.compute(img, keypoints, descriptors);
-        assertMatNotEqual(truth, descriptors, EPS);
+        fail("Not yet implemented");
    }

    public void testWrite() {
--- a/modules/java/android_test/src/org/opencv/test/features2d/SURFDescriptorExtractorTest.java
+++ b/modules/java/android_test/src/org/opencv/test/features2d/SURFDescriptorExtractorTest.java
@@ -47,19 +47,20 @@ public class SURFDescriptorExtractorTest extends OpenCVTestCase {
        Mat truth = new Mat(1, 128, CvType.CV_32FC1) {
            {
                put(0, 0,
-                        -0.0041138371, 0.0041138371, 0, 0, 0, 0, 0.0014427509, 0.0014427509, -0.0081971241, 0.034624498, 0.032569118,
-                        0.032569118, -0.007222258, 0.0076424959, 0.0033254174, 0.0033254174, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-                        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -0.10815519, 0.38033518, 0.24314292, 0.24314292, -0.068393648, 0.068393648,
-                        0.039715949, 0.039715949, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -8.7263528e-05, 8.7263528e-05, -6.0081031e-05,
-                        6.0081031e-05, -0.00012158759, 0.00012158759, 0.0033254174, 0.0033254174, -0.007222258, 0.0076424964,
-                        0.0081971241, 0.034624498, -0.032569118, 0.032569118, -0.077379324, 0.27552885, 0.14366581, 0.31175563,
-                        -0.013609707, 0.24329227, -0.091054246, 0.17476201, 0.022970313, 0.022970313, -0.035123408, 0.035771687,
-                        0.1907353, 0.3838968, -0.31571922, 0.31571922, 0.0092833797, 0.0092833797, -0.012892088, 0.012957365,
-                        0.029558292, 0.073337689, -0.043703932, 0.043703932, 0.0014427509, 0.0014427509, 0, 0, 0.0041138371,
-                        0.0041138371, 0, 0, -0.02955829, 0.073337704, 0.043703932, 0.043703932, -0.012892087, 0.012957364,
-                        0.0092833797,0.0092833797, 6.0081031e-05, 6.0081031e-05, 0.00012158759, 0.00012158759, -8.7263528e-05,
-                        8.7263528e-05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
-                        );
+                          0, 0, 0, 0, 0, 0, 0, 0, 0.045382127, 0.075976953, -0.031969212, 0.035002094, 0.012224297,
+                          0.012286193, -0.0088025155, 0.0088025155, 0.00017225844, 0.00017225844, 0, 0, 8.2743405e-05,
+                          8.2743405e-05, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 8.2743405e-05, 8.2743405e-05, -0.00017225844,
+                          0.00017225844, 0, 0, 0.31723264, 0.42715758, -0.19872268, 0.23621935, 0.033304065, 0.033918764,
+                          -0.021780485, 0.021780485, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -0.0088025145,
+                          0.0088025145, 0.012224296, 0.012286192, -0.045382123, 0.075976953, 0.031969212, 0.035002094,
+                          0.10047197, 0.21463872, -0.0012294546, 0.18176091, -0.075555265, 0.35627601, 0.01270232,
+                          0.20058797, -0.037658721, 0.037658721, 0.064850949, 0.064850949, -0.27688536, 0.44229308,
+                          0.14888979, 0.14888979, -0.0031531656, 0.0031531656, 0.0068481555, 0.0072466261, -0.034193151,
+                          0.040314503, 0.01108359, 0.023398584, -0.00071876607, 0.00071876607, -0.0031819802,
+                          0.0031819802, 0, 0, -0.0013680183, 0.0013680183, 0.034193147, 0.040314503, -0.01108359,
+                          0.023398584, 0.006848156, 0.0072466265, -0.0031531656, 0.0031531656, 0, 0, 0, 0, 0, 0, 0, 0,
+                         -0.0013680183, 0.0013680183, 0, 0, 0.00071876607, 0.00071876607, 0.0031819802, 0.0031819802
+                    );
            }
        };

--- a/modules/java/generator/src/java/android+AsyncServiceHelper.java
+++ b/modules/java/generator/src/java/android+AsyncServiceHelper.java
@@ -41,7 +41,7 @@ class AsyncServiceHelper
    }

    protected static final String TAG = "OpenCVManager/Helper";
-    protected static final int MINIMUM_ENGINE_VERSION = 1;
+    protected static final int MINIMUM_ENGINE_VERSION = 2;
    protected OpenCVEngineInterface mEngineService;
    protected LoaderCallbackInterface mUserAppCallback;
    protected String mOpenCVersion;
--- a/modules/java/generator/src/java/android+BaseLoaderCallback.java
+++ b/modules/java/generator/src/java/android+BaseLoaderCallback.java
@@ -52,7 +52,7 @@ public abstract class BaseLoaderCallback implements LoaderCallbackInterface {
                Log.d(TAG, "OpenCV Manager Service is uncompatible with this app!");
                AlertDialog IncomatibilityMessage = new AlertDialog.Builder(mAppContext).create();
                IncomatibilityMessage.setTitle("OpenCV Manager");
-                IncomatibilityMessage.setMessage("OpenCV Manager service is incompatible with this app. Update it!");
+                IncomatibilityMessage.setMessage("OpenCV Manager service is incompatible with this app. Try to update it via Google Play.");
                IncomatibilityMessage.setCancelable(false); // This blocks the 'BACK' button
                IncomatibilityMessage.setButton(AlertDialog.BUTTON_POSITIVE, "OK", new OnClickListener() {
                    public void onClick(DialogInterface dialog, int which) {
@@ -60,7 +60,7 @@ public abstract class BaseLoaderCallback implements LoaderCallbackInterface {
                    }
                });
                IncomatibilityMessage.show();
-            }
+            } break;
            /** Other status, i.e. INIT_FAILED. **/
            default:
            {
@@ -113,7 +113,7 @@ public abstract class BaseLoaderCallback implements LoaderCallbackInterface {
            {
                AlertDialog WaitMessage = new AlertDialog.Builder(mAppContext).create();
                WaitMessage.setTitle("OpenCV is not ready");
-                WaitMessage.setMessage("Installation is in progeress. Wait or exit?");
+                WaitMessage.setMessage("Installation is in progress. Wait or exit?");
                WaitMessage.setCancelable(false); // This blocks the 'BACK' button
                WaitMessage.setButton(AlertDialog.BUTTON_POSITIVE, "Wait", new OnClickListener() {
                    public void onClick(DialogInterface dialog, int which) {
--- a/modules/java/generator/src/java/android+CameraBridgeViewBase.java
+++ b/modules/java/generator/src/java/android+CameraBridgeViewBase.java
@@ -23,10 +23,10 @@ import android.view.SurfaceView;
 * The main responsibility of it - is to control when camera can be enabled, process the frame,
 * call external listener to make any adjustments to the frame and then draw the resulting
 * frame to the screen.
- * The clients shall implement CvCameraViewListener
- * TODO: add method to control the format in which the frames will be delivered to CvCameraViewListener
+ * The clients shall implement CvCameraViewListener.
 */
 public abstract class CameraBridgeViewBase extends SurfaceView implements SurfaceHolder.Callback {
+//TODO: add method to control the format in which the frames will be delivered to CvCameraViewListener

    private static final int MAX_UNSPECIFIED = -1;

--- a/modules/java/generator/src/java/android+JavaCameraView.java
+++ b/modules/java/generator/src/java/android+JavaCameraView.java
@@ -1,6 +1,5 @@
 package org.opencv.android;

-import java.io.IOException;
 import java.util.List;

 import android.annotation.TargetApi;
@@ -21,7 +20,7 @@ import org.opencv.highgui.Highgui;
 import org.opencv.imgproc.Imgproc;

 /**
- * This class is an implementation of the Bridge View between OpenCv and JAVA Camera.
+ * This class is an implementation of the Bridge View between OpenCV and Java Camera.
 * This class relays on the functionality available in base class and only implements
 * required functions:
 * connectCamera - opens Java camera and sets the PreviewCallback to be delivered.
@@ -36,7 +35,8 @@ public class JavaCameraView extends CameraBridgeViewBase implements PreviewCallb

    private Mat mBaseMat;
    private byte mBuffer[];
-
+    private Mat[] mFrameChain;
+    private int mChainIdx = 0;
    private Thread mThread;
    private boolean mStopThread;

@@ -65,6 +65,7 @@ public class JavaCameraView extends CameraBridgeViewBase implements PreviewCallb
    @TargetApi(11)
    protected boolean initializeCamera(int width, int height) {
        Log.d(TAG, "Initialize java camera");
+        boolean result = true;
        synchronized (this) {
            mCamera = null;

@@ -99,59 +100,76 @@ public class JavaCameraView extends CameraBridgeViewBase implements PreviewCallb
                Log.d(TAG, "getSupportedPreviewSizes()");
                List<android.hardware.Camera.Size> sizes = params.getSupportedPreviewSizes();

-                /* Select the size that fits surface considering maximum size allowed */
-                Size frameSize = calculateCameraFrameSize(sizes, new JavaCameraSizeAccessor(), width, height);
+                if (sizes != null) {
+                    /* Select the size that fits surface considering maximum size allowed */
+                    Size frameSize = calculateCameraFrameSize(sizes, new JavaCameraSizeAccessor(), width, height);

-                params.setPreviewFormat(ImageFormat.NV21);
-                Log.d(TAG, "Set preview size to " + Integer.valueOf((int)frameSize.width) + "x" + Integer.valueOf((int)frameSize.height));
-                params.setPreviewSize((int)frameSize.width, (int)frameSize.height);
+                    params.setPreviewFormat(ImageFormat.NV21);
+                    Log.d(TAG, "Set preview size to " + Integer.valueOf((int)frameSize.width) + "x" + Integer.valueOf((int)frameSize.height));
+                    params.setPreviewSize((int)frameSize.width, (int)frameSize.height);

-                List<String> FocusModes = params.getSupportedFocusModes();
-                if (FocusModes.contains(Camera.Parameters.FOCUS_MODE_CONTINUOUS_VIDEO))
-                {
-                    params.setFocusMode(Camera.Parameters.FOCUS_MODE_CONTINUOUS_VIDEO);
+                    List<String> FocusModes = params.getSupportedFocusModes();
+                    if (FocusModes.contains(Camera.Parameters.FOCUS_MODE_CONTINUOUS_VIDEO))
+                    {
+                        params.setFocusMode(Camera.Parameters.FOCUS_MODE_CONTINUOUS_VIDEO);
+                    }
+
+                    mCamera.setParameters(params);
+                    params = mCamera.getParameters();
+
+                    mFrameWidth = params.getPreviewSize().width;
+                    mFrameHeight = params.getPreviewSize().height;
+
+                    int size = mFrameWidth * mFrameHeight;
+                    size  = size * ImageFormat.getBitsPerPixel(params.getPreviewFormat()) / 8;
+                    mBuffer = new byte[size];
+
+                    mCamera.addCallbackBuffer(mBuffer);
+                    mCamera.setPreviewCallbackWithBuffer(this);
+
+                    mBaseMat = new Mat(mFrameHeight + (mFrameHeight/2), mFrameWidth, CvType.CV_8UC1);
+
+                    mFrameChain = new Mat[2];
+                    mFrameChain[0] = new Mat();
+                    mFrameChain[1] = new Mat();
+
+                    AllocateCache();
+
+                    if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.HONEYCOMB) {
+                        mSurfaceTexture = new SurfaceTexture(MAGIC_TEXTURE_ID);
+                        getHolder().setType(SurfaceHolder.SURFACE_TYPE_PUSH_BUFFERS);
+                        mCamera.setPreviewTexture(mSurfaceTexture);
+                    } else
+                       mCamera.setPreviewDisplay(null);
+
+                    /* Finally we are ready to start the preview */
+                    Log.d(TAG, "startPreview");
+                    mCamera.startPreview();
                }
-
-                mCamera.setParameters(params);
-                params = mCamera.getParameters();
-
-                mFrameWidth = params.getPreviewSize().width;
-                mFrameHeight = params.getPreviewSize().height;
-
-                int size = mFrameWidth * mFrameHeight;
-                size  = size * ImageFormat.getBitsPerPixel(params.getPreviewFormat()) / 8;
-                mBuffer = new byte[size];
-
-                mCamera.addCallbackBuffer(mBuffer);
-                mCamera.setPreviewCallbackWithBuffer(this);
-
-                mBaseMat = new Mat(mFrameHeight + (mFrameHeight/2), mFrameWidth, CvType.CV_8UC1);
-
-                AllocateCache();
-
-                if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.HONEYCOMB) {
-                    mSurfaceTexture = new SurfaceTexture(MAGIC_TEXTURE_ID);
-                    getHolder().setType(SurfaceHolder.SURFACE_TYPE_PUSH_BUFFERS);
-                    mCamera.setPreviewTexture(mSurfaceTexture);
-                } else
-                   mCamera.setPreviewDisplay(null);
-            } catch (IOException e) {
+                else
+                    result = false;
+            } catch (Exception e) {
+                result = false;
                e.printStackTrace();
            }
-
-            /* Finally we are ready to start the preview */
-            Log.d(TAG, "startPreview");
-            mCamera.startPreview();
        }

-        return true;
+        return result;
    }

    protected void releaseCamera() {
        synchronized (this) {
-            mCamera.stopPreview();
-            mCamera.release();
+            if (mCamera != null) {
+                mCamera.stopPreview();
+                mCamera.release();
+            }
            mCamera = null;
+            if (mBaseMat != null)
+                mBaseMat.release();
+            if (mFrameChain != null) {
+                mFrameChain[0].release();
+                mFrameChain[1].release();
+            }
        }
    }

@@ -187,7 +205,8 @@ public class JavaCameraView extends CameraBridgeViewBase implements PreviewCallb
                this.notify();
            }
            Log.d(TAG, "Wating for thread");
-            mThread.join();
+            if (mThread != null)
+                mThread.join();
        } catch (InterruptedException e) {
            e.printStackTrace();
        } finally {
@@ -224,19 +243,19 @@ public class JavaCameraView extends CameraBridgeViewBase implements PreviewCallb
                }

                if (!mStopThread) {
-                    Mat frameMat = new Mat();
                    switch (mPreviewFormat) {
                        case Highgui.CV_CAP_ANDROID_COLOR_FRAME_RGBA:
-                            Imgproc.cvtColor(mBaseMat, frameMat, Imgproc.COLOR_YUV2RGBA_NV21, 4);
+                            Imgproc.cvtColor(mBaseMat, mFrameChain[mChainIdx], Imgproc.COLOR_YUV2RGBA_NV21, 4);
                        break;
                        case Highgui.CV_CAP_ANDROID_GREY_FRAME:
-                            frameMat = mBaseMat.submat(0, mFrameHeight, 0, mFrameWidth);
+                            mFrameChain[mChainIdx] = mBaseMat.submat(0, mFrameHeight, 0, mFrameWidth);
                        break;
                        default:
                            Log.e(TAG, "Invalid frame format! Only RGBA and Gray Scale are supported!");
                    };
-                    deliverAndDrawFrame(frameMat);
-                    frameMat.release();
+                    if (!mFrameChain[mChainIdx].empty())
+                        deliverAndDrawFrame(mFrameChain[mChainIdx]);
+                    mChainIdx = 1 - mChainIdx;
                }
            } while (!mStopThread);
            Log.d(TAG, "Finish processing thread");
--- a/modules/legacy/test/test_precomp.hpp
+++ b/modules/legacy/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/ml/doc/statistical_models.rst
+++ b/modules/ml/doc/statistical_models.rst
@@ -156,7 +156,7 @@ CvStatModel::predict
 --------------------
 Predicts the response for a sample.

-.. ocv:function:: float CvStatModel::predict( const Mat& sample[, <prediction_params>] ) const
+.. ocv:function:: float CvStatModel::predict( const Mat& sample, <prediction_params> ) const

 The method is used to predict the response for a new sample. In case of a classification, the method returns the class label. In case of a regression, the method returns the output function value. The input sample must have as many components as the ``train_data`` passed to ``train`` contains. If the ``var_idx`` parameter is passed to ``train``, it is remembered and then is used to extract only the necessary components from the input sample in the method ``predict``.

--- a/modules/ml/test/test_precomp.hpp
+++ b/modules/ml/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/nonfree/perf/perf_precomp.hpp
+++ b/modules/nonfree/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/nonfree/test/test_precomp.hpp
+++ b/modules/nonfree/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/objdetect/perf/perf_cascadeclassifier.cpp
+++ b/modules/objdetect/perf/perf_cascadeclassifier.cpp
@@ -12,13 +12,10 @@ typedef perf::TestBaseWithParam<ImageName_MinSize_t> ImageName_MinSize;

 PERF_TEST_P(ImageName_MinSize, CascadeClassifierLBPFrontalFace,
            testing::Combine(testing::Values( std::string("cv/shared/lena.png"),
-                                              std::string("cv/shared/1_itseez-0000247.png"),
                                              std::string("cv/shared/1_itseez-0000289.png"),
                                              std::string("cv/shared/1_itseez-0000492.png"),
                                              std::string("cv/shared/1_itseez-0000573.png"),
-                                              std::string("cv/shared/1_itseez-0000803.png"),
                                              std::string("cv/shared/1_itseez-0000892.png"),
-                                              std::string("cv/shared/1_itseez-0000984.png"),
                                              std::string("cv/shared/1_itseez-0001238.png"),
                                              std::string("cv/shared/1_itseez-0001438.png"),
                                              std::string("cv/shared/1_itseez-0002524.png")),
@@ -53,5 +50,5 @@ PERF_TEST_P(ImageName_MinSize, CascadeClassifierLBPFrontalFace,
    }

    std::sort(faces.begin(), faces.end(), comparators::RectLess());
-    SANITY_CHECK(faces);
+    SANITY_CHECK(faces, 3.001 * faces.size());
 }
--- a/modules/objdetect/perf/perf_precomp.hpp
+++ b/modules/objdetect/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/objdetect/src/haar.cpp
+++ b/modules/objdetect/src/haar.cpp
@@ -728,8 +728,14 @@ double icvEvalHidHaarClassifierAVX( CvHidHaarClassifier* classifier,

        sum = _mm256_add_ps(sum,_mm256_load_ps(tmp));

-        __m256 left  = _mm256_set_ps(nodes[7]->left, nodes[6]->left, nodes[5]->left, nodes[4]->left, nodes[3]->left, nodes[2]->left, nodes[1]->left, nodes[0]->left );
-        __m256 right = _mm256_set_ps(nodes[7]->right,nodes[6]->right,nodes[5]->right,nodes[4]->right,nodes[3]->right,nodes[2]->right,nodes[1]->right,nodes[0]->right);
+        __m256 left  = _mm256_set_ps(static_cast<float>(nodes[7]->left), static_cast<float>(nodes[6]->left),
+                                     static_cast<float>(nodes[5]->left), static_cast<float>(nodes[4]->left),
+                                     static_cast<float>(nodes[3]->left), static_cast<float>(nodes[2]->left),
+                                     static_cast<float>(nodes[1]->left), static_cast<float>(nodes[0]->left));
+        __m256 right = _mm256_set_ps(static_cast<float>(nodes[7]->right),static_cast<float>(nodes[6]->right),
+                                     static_cast<float>(nodes[5]->right),static_cast<float>(nodes[4]->right),
+                                     static_cast<float>(nodes[3]->right),static_cast<float>(nodes[2]->right),
+                                     static_cast<float>(nodes[1]->right),static_cast<float>(nodes[0]->right));

        _mm256_store_si256((__m256i*)idxV, _mm256_cvttps_epi32(_mm256_blendv_ps(right, left, _mm256_cmp_ps(sum, t, _CMP_LT_OQ))));

--- a/modules/objdetect/test/test_latentsvmdetector.cpp
+++ b/modules/objdetect/test/test_latentsvmdetector.cpp
@@ -307,5 +307,5 @@ void LatentSVMDetectorTest::run( int /* start_from */)
    ts->set_failed_test_info( cvtest::TS::OK);
 }

-TEST(Objdetect_LatentSVMDetector_c, regression) { CV_LatentSVMDetectorTest test; test.safe_run(); }
-TEST(Objdetect_LatentSVMDetector_cpp, regression) { LatentSVMDetectorTest test; test.safe_run(); }
+TEST(Objdetect_LatentSVMDetector_c, DISABLED_regression) { CV_LatentSVMDetectorTest test; test.safe_run(); }
+TEST(Objdetect_LatentSVMDetector_cpp, DISABLED_regression) { LatentSVMDetectorTest test; test.safe_run(); }
--- a/modules/objdetect/test/test_precomp.hpp
+++ b/modules/objdetect/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/ocl/doc/data_structures.rst
+++ b/modules/ocl/doc/data_structures.rst
@@ -0,0 +1,189 @@
+Data Structures
+=============================
+
+.. ocv:class:: oclMat
+
+OpenCV C++ 1-D or 2-D dense array class ::
+
+        class CV_EXPORTS oclMat
+        {
+        public:
+            //! default constructor
+            oclMat();
+            //! constructs oclMatrix of the specified size and type (_type is CV_8UC1, CV_64FC3, CV_32SC(12) etc.)
+            oclMat(int rows, int cols, int type);
+            oclMat(Size size, int type);
+            //! constucts oclMatrix and fills it with the specified value _s.
+            oclMat(int rows, int cols, int type, const Scalar &s);
+            oclMat(Size size, int type, const Scalar &s);
+            //! copy constructor
+            oclMat(const oclMat &m);
+
+            //! constructor for oclMatrix headers pointing to user-allocated data
+            oclMat(int rows, int cols, int type, void *data, size_t step = Mat::AUTO_STEP);
+            oclMat(Size size, int type, void *data, size_t step = Mat::AUTO_STEP);
+
+            //! creates a matrix header for a part of the bigger matrix
+            oclMat(const oclMat &m, const Range &rowRange, const Range &colRange);
+            oclMat(const oclMat &m, const Rect &roi);
+
+            //! builds oclMat from Mat. Perfom blocking upload to device.
+            explicit oclMat (const Mat &m);
+
+            //! destructor - calls release()
+            ~oclMat();
+
+            //! assignment operators
+            oclMat &operator = (const oclMat &m);
+            //! assignment operator. Perfom blocking upload to device.
+            oclMat &operator = (const Mat &m);
+
+
+            //! pefroms blocking upload data to oclMat.
+            void upload(const cv::Mat &m);
+
+
+            //! downloads data from device to host memory. Blocking calls.
+            operator Mat() const;
+            void download(cv::Mat &m) const;
+
+
+            //! returns a new oclMatrix header for the specified row
+            oclMat row(int y) const;
+            //! returns a new oclMatrix header for the specified column
+            oclMat col(int x) const;
+            //! ... for the specified row span
+            oclMat rowRange(int startrow, int endrow) const;
+            oclMat rowRange(const Range &r) const;
+            //! ... for the specified column span
+            oclMat colRange(int startcol, int endcol) const;
+            oclMat colRange(const Range &r) const;
+
+            //! returns deep copy of the oclMatrix, i.e. the data is copied
+            oclMat clone() const;
+            //! copies the oclMatrix content to "m".
+            // It calls m.create(this->size(), this->type()).
+            // It supports any data type
+            void copyTo( oclMat &m ) const;
+            //! copies those oclMatrix elements to "m" that are marked with non-zero mask elements.
+            //It supports 8UC1 8UC4 32SC1 32SC4 32FC1 32FC4
+            void copyTo( oclMat &m, const oclMat &mask ) const;
+            //! converts oclMatrix to another datatype with optional scalng. See cvConvertScale.
+            //It supports 8UC1 8UC4 32SC1 32SC4 32FC1 32FC4
+            void convertTo( oclMat &m, int rtype, double alpha = 1, double beta = 0 ) const;
+
+            void assignTo( oclMat &m, int type = -1 ) const;
+
+            //! sets every oclMatrix element to s
+            //It supports 8UC1 8UC4 32SC1 32SC4 32FC1 32FC4
+            oclMat &operator = (const Scalar &s);
+            //! sets some of the oclMatrix elements to s, according to the mask
+            //It supports 8UC1 8UC4 32SC1 32SC4 32FC1 32FC4
+            oclMat &setTo(const Scalar &s, const oclMat &mask = oclMat());
+            //! creates alternative oclMatrix header for the same data, with different
+            // number of channels and/or different number of rows. see cvReshape.
+            oclMat reshape(int cn, int rows = 0) const;
+
+            //! allocates new oclMatrix data unless the oclMatrix already has specified size and type.
+            // previous data is unreferenced if needed.
+            void create(int rows, int cols, int type);
+            void create(Size size, int type);
+            //! decreases reference counter;
+            // deallocate the data when reference counter reaches 0.
+            void release();
+
+            //! swaps with other smart pointer
+            void swap(oclMat &mat);
+
+            //! locates oclMatrix header within a parent oclMatrix. See below
+            void locateROI( Size &wholeSize, Point &ofs ) const;
+            //! moves/resizes the current oclMatrix ROI inside the parent oclMatrix.
+            oclMat &adjustROI( int dtop, int dbottom, int dleft, int dright );
+            //! extracts a rectangular sub-oclMatrix
+            // (this is a generalized form of row, rowRange etc.)
+            oclMat operator()( Range rowRange, Range colRange ) const;
+            oclMat operator()( const Rect &roi ) const;
+
+            //! returns true if the oclMatrix data is continuous
+            // (i.e. when there are no gaps between successive rows).
+            // similar to CV_IS_oclMat_CONT(cvoclMat->type)
+            bool isContinuous() const;
+            //! returns element size in bytes,
+            // similar to CV_ELEM_SIZE(cvMat->type)
+            size_t elemSize() const;
+            //! returns the size of element channel in bytes.
+            size_t elemSize1() const;
+            //! returns element type, similar to CV_MAT_TYPE(cvMat->type)
+            int type() const;
+            //! returns element type, i.e. 8UC3 returns 8UC4 because in ocl
+            //! 3 channels element actually use 4 channel space
+            int ocltype() const;
+            //! returns element type, similar to CV_MAT_DEPTH(cvMat->type)
+            int depth() const;
+            //! returns element type, similar to CV_MAT_CN(cvMat->type)
+            int channels() const;
+            //! returns element type, return 4 for 3 channels element,
+            //!becuase 3 channels element actually use 4 channel space
+            int oclchannels() const;
+            //! returns step/elemSize1()
+            size_t step1() const;
+            //! returns oclMatrix size:
+            // width == number of columns, height == number of rows
+            Size size() const;
+            //! returns true if oclMatrix data is NULL
+            bool empty() const;
+
+            //! returns pointer to y-th row
+            uchar *ptr(int y = 0);
+            const uchar *ptr(int y = 0) const;
+
+            //! template version of the above method
+            template<typename _Tp> _Tp *ptr(int y = 0);
+            template<typename _Tp> const _Tp *ptr(int y = 0) const;
+
+            //! matrix transposition
+            oclMat t() const;
+
+            /*! includes several bit-fields:
+              - the magic signature
+              - continuity flag
+              - depth
+              - number of channels
+              */
+            int flags;
+            //! the number of rows and columns
+            int rows, cols;
+            //! a distance between successive rows in bytes; includes the gap if any
+            size_t step;
+            //! pointer to the data(OCL memory object)
+            uchar *data;
+
+            //! pointer to the reference counter;
+            // when oclMatrix points to user-allocated data, the pointer is NULL
+            int *refcount;
+
+            //! helper fields used in locateROI and adjustROI
+            //datastart and dataend are not used in current version
+            uchar *datastart;
+            uchar *dataend;
+
+            //! OpenCL context associated with the oclMat object.
+            Context *clCxt;
+            //add offset for handle ROI, calculated in byte
+            int offset;
+            //add wholerows and wholecols for the whole matrix, datastart and dataend are no longer used
+            int wholerows;
+            int wholecols;
+        };
+
+Basically speaking, the oclMat is the mirror of Mat with the extension of ocl feature, the members have the same meaning and useage of Mat except following:
+
+datastart and dataend are replaced with wholerows and wholecols
+
+add clCxt for oclMat
+
+Only basic flags are supported in oclMat(i.e. depth number of channels)
+
+All the 3-channel matrix(i.e. RGB image) are represented by 4-channel matrix in oclMat. It means 3-channel image have 4-channel space with the last channel unused. We provide a transparent interface to handle the difference between OpenCV Mat and oclMat.
+
+For example: If a oclMat has 3 channels, channels() returns 3 and oclchannels() returns 4
--- a/modules/ocl/doc/feature_detection_and_description.rst
+++ b/modules/ocl/doc/feature_detection_and_description.rst
@@ -0,0 +1,502 @@
+Feature Detection And Description
+=================================
+
+.. highlight:: cpp
+
+ocl::Canny
+-------------------
+Finds edges in an image using the [Canny86]_ algorithm.
+
+.. ocv:function:: void ocl::Canny(const oclMat& image, oclMat& edges, double low_thresh, double high_thresh, int apperture_size = 3, bool L2gradient = false)
+
+.. ocv:function:: void ocl::Canny(const oclMat& image, CannyBuf& buf, oclMat& edges, double low_thresh, double high_thresh, int apperture_size = 3, bool L2gradient = false)
+
+.. ocv:function:: void ocl::Canny(const oclMat& dx, const oclMat& dy, oclMat& edges, double low_thresh, double high_thresh, bool L2gradient = false)
+
+.. ocv:function:: void ocl::Canny(const oclMat& dx, const oclMat& dy, CannyBuf& buf, oclMat& edges, double low_thresh, double high_thresh, bool L2gradient = false)
+
+    :param image: Single-channel 8-bit input image.
+
+    :param dx: First derivative of image in the vertical direction. Support only ``CV_32S`` type.
+
+    :param dy: First derivative of image in the horizontal direction. Support only ``CV_32S`` type.
+
+    :param edges: Output edge map. It has the same size and type as  ``image`` .
+
+    :param low_thresh: First threshold for the hysteresis procedure.
+
+    :param high_thresh: Second threshold for the hysteresis procedure.
+
+    :param apperture_size: Aperture size for the  :ocv:func:`Sobel`  operator.
+
+    :param L2gradient: Flag indicating whether a more accurate  :math:`L_2`  norm  :math:`=\sqrt{(dI/dx)^2 + (dI/dy)^2}`  should be used to compute the image gradient magnitude ( ``L2gradient=true`` ), or a faster default  :math:`L_1`  norm  :math:`=|dI/dx|+|dI/dy|`  is enough ( ``L2gradient=false`` ).
+
+    :param buf: Optional buffer to avoid extra memory allocations (for many calls with the same sizes).
+
+.. seealso:: :ocv:func:`Canny`
+
+
+ocl::BruteForceMatcher_OCL
+--------------------------
+.. ocv:class:: ocl::BruteForceMatcher_OCL_base
+
+Brute-force descriptor matcher. For each descriptor in the first set, this matcher finds the closest descriptor in the second set by trying each one. This descriptor matcher supports masking permissible matches between descriptor sets. ::
+
+    class BruteForceMatcher_OCL_base
+    {
+    public:
+            enum DistType {L1Dist = 0, L2Dist, HammingDist};
+
+        // Add descriptors to train descriptor collection.
+        void add(const std::vector<oclMat>& descCollection);
+
+        // Get train descriptors collection.
+        const std::vector<oclMat>& getTrainDescriptors() const;
+
+        // Clear train descriptors collection.
+        void clear();
+
+        // Return true if there are no train descriptors in collection.
+        bool empty() const;
+
+        // Return true if the matcher supports mask in match methods.
+        bool isMaskSupported() const;
+
+        void matchSingle(const oclMat& query, const oclMat& train,
+            oclMat& trainIdx, oclMat& distance,
+            const oclMat& mask = oclMat());
+
+        static void matchDownload(const oclMat& trainIdx,
+            const oclMat& distance, std::vector<DMatch>& matches);
+        static void matchConvert(const Mat& trainIdx,
+            const Mat& distance, std::vector<DMatch>& matches);
+
+        void match(const oclMat& query, const oclMat& train,
+            std::vector<DMatch>& matches, const oclMat& mask = oclMat());
+
+        void makeGpuCollection(oclMat& trainCollection, oclMat& maskCollection,
+            const vector<oclMat>& masks = std::vector<oclMat>());
+
+        void matchCollection(const oclMat& query, const oclMat& trainCollection,
+            oclMat& trainIdx, oclMat& imgIdx, oclMat& distance,
+            const oclMat& maskCollection);
+
+        static void matchDownload(const oclMat& trainIdx, oclMat& imgIdx,
+            const oclMat& distance, std::vector<DMatch>& matches);
+        static void matchConvert(const Mat& trainIdx, const Mat& imgIdx,
+            const Mat& distance, std::vector<DMatch>& matches);
+
+        void match(const oclMat& query, std::vector<DMatch>& matches,
+            const std::vector<oclMat>& masks = std::vector<oclMat>());
+
+        void knnMatchSingle(const oclMat& query, const oclMat& train,
+            oclMat& trainIdx, oclMat& distance, oclMat& allDist, int k,
+            const oclMat& mask = oclMat());
+
+        static void knnMatchDownload(const oclMat& trainIdx, const oclMat& distance,
+            std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
+        static void knnMatchConvert(const Mat& trainIdx, const Mat& distance,
+            std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
+
+        void knnMatch(const oclMat& query, const oclMat& train,
+            std::vector< std::vector<DMatch> >& matches, int k,
+            const oclMat& mask = oclMat(), bool compactResult = false);
+
+        void knnMatch2Collection(const oclMat& query, const oclMat& trainCollection,
+            oclMat& trainIdx, oclMat& imgIdx, oclMat& distance,
+            const oclMat& maskCollection = oclMat());
+
+        static void knnMatch2Download(const oclMat& trainIdx, const oclMat& imgIdx, const oclMat& distance,
+            std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
+        static void knnMatch2Convert(const Mat& trainIdx, const Mat& imgIdx, const Mat& distance,
+            std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
+
+        void knnMatch(const oclMat& query, std::vector< std::vector<DMatch> >& matches, int k,
+            const std::vector<oclMat>& masks = std::vector<oclMat>(),
+            bool compactResult = false);
+
+        void radiusMatchSingle(const oclMat& query, const oclMat& train,
+            oclMat& trainIdx, oclMat& distance, oclMat& nMatches, float maxDistance,
+            const oclMat& mask = oclMat());
+
+        static void radiusMatchDownload(const oclMat& trainIdx, const oclMat& distance, const oclMat& nMatches,
+            std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
+        static void radiusMatchConvert(const Mat& trainIdx, const Mat& distance, const Mat& nMatches,
+            std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
+
+        void radiusMatch(const oclMat& query, const oclMat& train,
+            std::vector< std::vector<DMatch> >& matches, float maxDistance,
+            const oclMat& mask = oclMat(), bool compactResult = false);
+
+        void radiusMatchCollection(const oclMat& query, oclMat& trainIdx, oclMat& imgIdx, oclMat& distance, oclMat& nMatches, float maxDistance,
+            const std::vector<oclMat>& masks = std::vector<oclMat>());
+
+        static void radiusMatchDownload(const oclMat& trainIdx, const oclMat& imgIdx, const oclMat& distance, const oclMat& nMatches,
+            std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
+        static void radiusMatchConvert(const Mat& trainIdx, const Mat& imgIdx, const Mat& distance, const Mat& nMatches,
+            std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
+
+        void radiusMatch(const oclMat& query, std::vector< std::vector<DMatch> >& matches, float maxDistance,
+            const std::vector<oclMat>& masks = std::vector<oclMat>(), bool compactResult = false);
+
+                DistType distType;
+
+    private:
+        std::vector<oclMat> trainDescCollection;
+    };
+
+
+The class ``BruteForceMatcher_OCL_base`` has an interface similar to the class :ocv:class:`DescriptorMatcher`. It has two groups of ``match`` methods: for matching descriptors of one image with another image or with an image set. Also, all functions have an alternative to save results either to the GPU memory or to the CPU memory. ``BruteForceMatcher_OCL_base`` supports only the ``L1<float>``, ``L2<float>``, and ``Hamming`` distance types.
+
+.. seealso:: :ocv:class:`DescriptorMatcher`, :ocv:class:`BruteForceMatcher`
+
+
+
+ocl::BruteForceMatcher_OCL_base::match
+--------------------------------------
+Finds the best match for each descriptor from a query set with train descriptors.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::match(const oclMat& query, const oclMat& train, std::vector<DMatch>& matches, const oclMat& mask = oclMat())
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::matchSingle(const oclMat& query, const oclMat& train, oclMat& trainIdx, oclMat& distance, const oclMat& mask = oclMat())
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::match(const oclMat& query, std::vector<DMatch>& matches, const std::vector<oclMat>& masks = std::vector<oclMat>())
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::matchCollection(const oclMat& query, const oclMat& trainCollection, oclMat& trainIdx, oclMat& imgIdx, oclMat& distance, const oclMat& masks)
+
+.. seealso:: :ocv:func:`DescriptorMatcher::match`
+
+
+
+ocl::BruteForceMatcher_OCL_base::makeGpuCollection
+--------------------------------------------------
+Performs a GPU collection of train descriptors and masks in a suitable format for the :ocv:func:`ocl::BruteForceMatcher_OCL_base::matchCollection` function.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::makeGpuCollection(oclMat& trainCollection, oclMat& maskCollection, const vector<oclMat>& masks = std::vector<oclMat>())
+
+
+
+ocl::BruteForceMatcher_OCL_base::matchDownload
+----------------------------------------------
+Downloads matrices obtained via :ocv:func:`ocl::BruteForceMatcher_OCL_base::matchSingle` or :ocv:func:`ocl::BruteForceMatcher_OCL_base::matchCollection` to vector with :ocv:class:`DMatch`.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::matchDownload(const oclMat& trainIdx, const oclMat& distance, std::vector<DMatch>&matches)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::matchDownload(const oclMat& trainIdx, oclMat& imgIdx, const oclMat& distance, std::vector<DMatch>&matches)
+
+
+
+ocl::BruteForceMatcher_OCL_base::matchConvert
+---------------------------------------------
+Converts matrices obtained via :ocv:func:`ocl::BruteForceMatcher_OCL_base::matchSingle` or :ocv:func:`ocl::BruteForceMatcher_OCL_base::matchCollection` to vector with :ocv:class:`DMatch`.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::matchConvert(const Mat& trainIdx, const Mat& distance, std::vector<DMatch>&matches)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::matchConvert(const Mat& trainIdx, const Mat& imgIdx, const Mat& distance, std::vector<DMatch>&matches)
+
+
+
+ocl::BruteForceMatcher_OCL_base::knnMatch
+-----------------------------------------
+Finds the ``k`` best matches for each descriptor from a query set with train descriptors.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::knnMatch(const oclMat& query, const oclMat& train, std::vector< std::vector<DMatch> >&matches, int k, const oclMat& mask = oclMat(), bool compactResult = false)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::knnMatchSingle(const oclMat& query, const oclMat& train, oclMat& trainIdx, oclMat& distance, oclMat& allDist, int k, const oclMat& mask = oclMat())
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::knnMatch(const oclMat& query, std::vector< std::vector<DMatch> >&matches, int k, const std::vector<oclMat>&masks = std::vector<oclMat>(), bool compactResult = false )
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::knnMatch2Collection(const oclMat& query, const oclMat& trainCollection, oclMat& trainIdx, oclMat& imgIdx, oclMat& distance, const oclMat& maskCollection = oclMat())
+
+    :param query: Query set of descriptors.
+
+    :param train: Training set of descriptors. It is not be added to train descriptors collection stored in the class object.
+
+    :param k: Number of the best matches per each query descriptor (or less if it is not possible).
+
+    :param mask: Mask specifying permissible matches between the input query and train matrices of descriptors.
+
+    :param compactResult: If ``compactResult`` is ``true`` , the ``matches`` vector does not contain matches for fully masked-out query descriptors.
+
+
+The function returns detected ``k`` (or less if not possible) matches in the increasing order by distance.
+
+The third variant of the method stores the results in GPU memory.
+
+.. seealso:: :ocv:func:`DescriptorMatcher::knnMatch`
+
+
+
+ocl::BruteForceMatcher_OCL_base::knnMatchDownload
+-------------------------------------------------
+Downloads matrices obtained via :ocv:func:`ocl::BruteForceMatcher_OCL_base::knnMatchSingle` or :ocv:func:`ocl::BruteForceMatcher_OCL_base::knnMatch2Collection` to vector with :ocv:class:`DMatch`.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::knnMatchDownload(const oclMat& trainIdx, const oclMat& distance, std::vector< std::vector<DMatch> >&matches, bool compactResult = false)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::knnMatch2Download(const oclMat& trainIdx, const oclMat& imgIdx, const oclMat& distance, std::vector< std::vector<DMatch> >& matches, bool compactResult = false)
+
+If ``compactResult`` is ``true`` , the ``matches`` vector does not contain matches for fully masked-out query descriptors.
+
+
+
+ocl::BruteForceMatcher_OCL_base::knnMatchConvert
+------------------------------------------------
+Converts matrices obtained via :ocv:func:`ocl::BruteForceMatcher_OCL_base::knnMatchSingle` or :ocv:func:`ocl::BruteForceMatcher_OCL_base::knnMatch2Collection` to CPU vector with :ocv:class:`DMatch`.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::knnMatchConvert(const Mat& trainIdx, const Mat& distance, std::vector< std::vector<DMatch> >&matches, bool compactResult = false)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::knnMatch2Convert(const Mat& trainIdx, const Mat& imgIdx, const Mat& distance, std::vector< std::vector<DMatch> >& matches, bool compactResult = false)
+
+If ``compactResult`` is ``true`` , the ``matches`` vector does not contain matches for fully masked-out query descriptors.
+
+
+
+ocl::BruteForceMatcher_OCL_base::radiusMatch
+--------------------------------------------
+For each query descriptor, finds the best matches with a distance less than a given threshold.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::radiusMatch(const oclMat& query, const oclMat& train, std::vector< std::vector<DMatch> >&matches, float maxDistance, const oclMat& mask = oclMat(), bool compactResult = false)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::radiusMatchSingle(const oclMat& query, const oclMat& train, oclMat& trainIdx, oclMat& distance, oclMat& nMatches, float maxDistance, const oclMat& mask = oclMat())
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::radiusMatch(const oclMat& query, std::vector< std::vector<DMatch> >&matches, float maxDistance, const std::vector<oclMat>& masks = std::vector<oclMat>(), bool compactResult = false)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::radiusMatchCollection(const oclMat& query, oclMat& trainIdx, oclMat& imgIdx, oclMat& distance, oclMat& nMatches, float maxDistance, const std::vector<oclMat>& masks = std::vector<oclMat>())
+
+    :param query: Query set of descriptors.
+
+    :param train: Training set of descriptors. It is not added to train descriptors collection stored in the class object.
+
+    :param maxDistance: Distance threshold.
+
+    :param mask: Mask specifying permissible matches between the input query and train matrices of descriptors.
+
+    :param compactResult: If ``compactResult`` is ``true`` , the ``matches`` vector does not contain matches for fully masked-out query descriptors.
+
+
+The function returns detected matches in the increasing order by distance.
+
+The methods work only on devices with the compute capability  :math:`>=` 1.1.
+
+The third variant of the method stores the results in GPU memory and does not store the points by the distance.
+
+.. seealso:: :ocv:func:`DescriptorMatcher::radiusMatch`
+
+
+
+ocl::BruteForceMatcher_OCL_base::radiusMatchDownload
+----------------------------------------------------
+Downloads matrices obtained via :ocv:func:`ocl::BruteForceMatcher_OCL_base::radiusMatchSingle` or :ocv:func:`ocl::BruteForceMatcher_OCL_base::radiusMatchCollection` to vector with :ocv:class:`DMatch`.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::radiusMatchDownload(const oclMat& trainIdx, const oclMat& distance, const oclMat& nMatches, std::vector< std::vector<DMatch> >&matches, bool compactResult = false)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::radiusMatchDownload(const oclMat& trainIdx, const oclMat& imgIdx, const oclMat& distance, const oclMat& nMatches, std::vector< std::vector<DMatch> >& matches, bool compactResult = false)
+
+If ``compactResult`` is ``true`` , the ``matches`` vector does not contain matches for fully masked-out query descriptors.
+
+
+
+
+ocl::BruteForceMatcher_OCL_base::radiusMatchConvert
+---------------------------------------------------
+Converts matrices obtained via :ocv:func:`ocl::BruteForceMatcher_OCL_base::radiusMatchSingle` or :ocv:func:`ocl::BruteForceMatcher_OCL_base::radiusMatchCollection` to vector with :ocv:class:`DMatch`.
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::radiusMatchConvert(const Mat& trainIdx, const Mat& distance, const Mat& nMatches, std::vector< std::vector<DMatch> >&matches, bool compactResult = false)
+
+.. ocv:function:: void ocl::BruteForceMatcher_OCL_base::radiusMatchConvert(const Mat& trainIdx, const Mat& imgIdx, const Mat& distance, const Mat& nMatches, std::vector< std::vector<DMatch> >& matches, bool compactResult = false)
+
+If ``compactResult`` is ``true`` , the ``matches`` vector does not contain matches for fully masked-out query descriptors.
+
+ocl::HOGDescriptor
+------------------
+
+.. ocv:class:: ocl::HOGDescriptor
+
+The class implements Histogram of Oriented Gradients ([Dalal2005]_) object detector. ::
+
+    struct CV_EXPORTS HOGDescriptor
+    {
+        enum { DEFAULT_WIN_SIGMA = -1 };
+        enum { DEFAULT_NLEVELS = 64 };
+        enum { DESCR_FORMAT_ROW_BY_ROW, DESCR_FORMAT_COL_BY_COL };
+
+        HOGDescriptor(Size win_size=Size(64, 128), Size block_size=Size(16, 16),
+                      Size block_stride=Size(8, 8), Size cell_size=Size(8, 8),
+                      int nbins=9, double win_sigma=DEFAULT_WIN_SIGMA,
+                      double threshold_L2hys=0.2, bool gamma_correction=true,
+                      int nlevels=DEFAULT_NLEVELS);
+
+        size_t getDescriptorSize() const;
+        size_t getBlockHistogramSize() const;
+
+        void setSVMDetector(const vector<float>& detector);
+
+        static vector<float> getDefaultPeopleDetector();
+        static vector<float> getPeopleDetector48x96();
+        static vector<float> getPeopleDetector64x128();
+
+        void detect(const oclMat& img, vector<Point>& found_locations,
+                    double hit_threshold=0, Size win_stride=Size(),
+                    Size padding=Size());
+
+        void detectMultiScale(const oclMat& img, vector<Rect>& found_locations,
+                              double hit_threshold=0, Size win_stride=Size(),
+                              Size padding=Size(), double scale0=1.05,
+                              int group_threshold=2);
+
+        void getDescriptors(const oclMat& img, Size win_stride,
+                            oclMat& descriptors,
+                            int descr_format=DESCR_FORMAT_COL_BY_COL);
+
+        Size win_size;
+        Size block_size;
+        Size block_stride;
+        Size cell_size;
+        int nbins;
+        double win_sigma;
+        double threshold_L2hys;
+        bool gamma_correction;
+        int nlevels;
+
+    private:
+        // Hidden
+    }
+
+
+Interfaces of all methods are kept similar to the ``CPU HOG`` descriptor and detector analogues as much as possible.
+
+
+
+ocl::HOGDescriptor::HOGDescriptor
+-------------------------------------
+Creates the ``HOG`` descriptor and detector.
+
+.. ocv:function:: ocl::HOGDescriptor::HOGDescriptor(Size win_size=Size(64, 128), Size block_size=Size(16, 16), Size block_stride=Size(8, 8), Size cell_size=Size(8, 8), int nbins=9, double win_sigma=DEFAULT_WIN_SIGMA, double threshold_L2hys=0.2, bool gamma_correction=true, int nlevels=DEFAULT_NLEVELS)
+
+   :param win_size: Detection window size. Align to block size and block stride.
+
+   :param block_size: Block size in pixels. Align to cell size. Only (16,16) is supported for now.
+
+   :param block_stride: Block stride. It must be a multiple of cell size.
+
+   :param cell_size: Cell size. Only (8, 8) is supported for now.
+
+   :param nbins: Number of bins. Only 9 bins per cell are supported for now.
+
+   :param win_sigma: Gaussian smoothing window parameter.
+
+   :param threshold_L2hys: L2-Hys normalization method shrinkage.
+
+   :param gamma_correction: Flag to specify whether the gamma correction preprocessing is required or not.
+
+   :param nlevels: Maximum number of detection window increases.
+
+
+
+ocl::HOGDescriptor::getDescriptorSize
+-----------------------------------------
+Returns the number of coefficients required for the classification.
+
+.. ocv:function:: size_t ocl::HOGDescriptor::getDescriptorSize() const
+
+
+
+ocl::HOGDescriptor::getBlockHistogramSize
+---------------------------------------------
+Returns the block histogram size.
+
+.. ocv:function:: size_t ocl::HOGDescriptor::getBlockHistogramSize() const
+
+
+
+ocl::HOGDescriptor::setSVMDetector
+--------------------------------------
+Sets coefficients for the linear SVM classifier.
+
+.. ocv:function:: void ocl::HOGDescriptor::setSVMDetector(const vector<float>& detector)
+
+
+
+ocl::HOGDescriptor::getDefaultPeopleDetector
+------------------------------------------------
+Returns coefficients of the classifier trained for people detection (for default window size).
+
+.. ocv:function:: static vector<float> ocl::HOGDescriptor::getDefaultPeopleDetector()
+
+
+
+ocl::HOGDescriptor::getPeopleDetector48x96
+----------------------------------------------
+Returns coefficients of the classifier trained for people detection (for 48x96 windows).
+
+.. ocv:function:: static vector<float> ocl::HOGDescriptor::getPeopleDetector48x96()
+
+
+
+ocl::HOGDescriptor::getPeopleDetector64x128
+-----------------------------------------------
+Returns coefficients of the classifier trained for people detection (for 64x128 windows).
+
+.. ocv:function:: static vector<float> ocl::HOGDescriptor::getPeopleDetector64x128()
+
+
+
+ocl::HOGDescriptor::detect
+------------------------------
+Performs object detection without a multi-scale window.
+
+.. ocv:function:: void ocl::HOGDescriptor::detect(const oclMat& img, vector<Point>& found_locations, double hit_threshold=0, Size win_stride=Size(), Size padding=Size())
+
+   :param img: Source image.  ``CV_8UC1``  and  ``CV_8UC4`` types are supported for now.
+
+   :param found_locations: Left-top corner points of detected objects boundaries.
+
+   :param hit_threshold: Threshold for the distance between features and SVM classifying plane. Usually it is 0 and should be specfied in the detector coefficients (as the last free coefficient). But if the free coefficient is omitted (which is allowed), you can specify it manually here.
+
+   :param win_stride: Window stride. It must be a multiple of block stride.
+
+   :param padding: Mock parameter to keep the CPU interface compatibility. It must be (0,0).
+
+
+
+ocl::HOGDescriptor::detectMultiScale
+----------------------------------------
+Performs object detection with a multi-scale window.
+
+.. ocv:function:: void ocl::HOGDescriptor::detectMultiScale(const oclMat& img, vector<Rect>& found_locations, double hit_threshold=0, Size win_stride=Size(), Size padding=Size(), double scale0=1.05, int group_threshold=2)
+
+   :param img: Source image. See  :ocv:func:`ocl::HOGDescriptor::detect`  for type limitations.
+
+   :param found_locations: Detected objects boundaries.
+
+   :param hit_threshold: Threshold for the distance between features and SVM classifying plane. See  :ocv:func:`ocl::HOGDescriptor::detect`  for details.
+
+   :param win_stride: Window stride. It must be a multiple of block stride.
+
+   :param padding: Mock parameter to keep the CPU interface compatibility. It must be (0,0).
+
+   :param scale0: Coefficient of the detection window increase.
+
+   :param group_threshold: Coefficient to regulate the similarity threshold. When detected, some objects can be covered by many rectangles. 0 means not to perform grouping. See  :ocv:func:`groupRectangles` .
+
+
+
+ocl::HOGDescriptor::getDescriptors
+--------------------------------------
+Returns block descriptors computed for the whole image.
+
+.. ocv:function:: void ocl::HOGDescriptor::getDescriptors(const oclMat& img, Size win_stride, oclMat& descriptors, int descr_format=DESCR_FORMAT_COL_BY_COL)
+
+   :param img: Source image. See  :ocv:func:`ocl::HOGDescriptor::detect`  for type limitations.
+
+   :param win_stride: Window stride. It must be a multiple of block stride.
+
+   :param descriptors: 2D array of descriptors.
+
+   :param descr_format: Descriptor storage format:
+
+        * **DESCR_FORMAT_ROW_BY_ROW** - Row-major order.
+
+        * **DESCR_FORMAT_COL_BY_COL** - Column-major order.
+
+The function is mainly used to learn the classifier.
--- a/modules/ocl/doc/image_filtering.rst
+++ b/modules/ocl/doc/image_filtering.rst
@@ -0,0 +1,283 @@
+Image Filtering
+=============================
+
+.. highlight:: cpp
+
+ocl::Sobel
+------------------
+Returns void
+
+.. ocv:function:: void Sobel(const oclMat &src, oclMat &dst, int ddepth, int dx, int dy, int ksize = 3, double scale = 1, double delta = 0.0, int bordertype = BORDER_DEFAULT)
+
+    :param src: The source image
+
+    :param dst: The destination image; It will have the same size as src
+
+    :param ddepth: The destination image depth
+
+    :param dx: Order of the derivative x
+
+    :param dy: Order of the derivative y
+
+    :param ksize: Size of the extended Sobel kernel
+
+    :param scale: The optional scale factor for the computed derivative values(by default, no scaling is applied)
+
+    :param delta: The optional delta value, added to the results prior to storing them in dst
+
+    :param bordertype: Pixel extrapolation method.
+
+The function computes the first x- or y- spatial image derivative using Sobel operator. Surpport 8UC1 8UC4 32SC1 32SC4 32FC1 32FC4 data type.
+
+ocl::Scharr
+------------------
+Returns void
+
+.. ocv:function:: void Scharr(const oclMat &src, oclMat &dst, int ddepth, int dx, int dy, double scale = 1, double delta = 0.0, int bordertype = BORDER_DEFAULT)
+
+    :param src: The source image
+
+    :param dst: The destination image; It will have the same size as src
+
+    :param ddepth: The destination image depth
+
+    :param dx: Order of the derivative x
+
+    :param dy: Order of the derivative y
+
+    :param scale: The optional scale factor for the computed derivative values(by default, no scaling is applied)
+
+    :param delta: The optional delta value, added to the results prior to storing them in dst
+
+    :param bordertype: Pixel extrapolation method.
+
+The function computes the first x- or y- spatial image derivative using Scharr operator. Surpport 8UC1 8UC4 32SC1 32SC4 32FC1 32FC4 data type.
+
+ocl::GaussianBlur
+------------------
+Returns void
+
+.. ocv:function:: void GaussianBlur(const oclMat &src, oclMat &dst, Size ksize, double sigma1, double sigma2 = 0, int bordertype = BORDER_DEFAULT)
+
+    :param src: The source image
+
+    :param dst: The destination image; It will have the same size and the same type as src
+
+    :param ksize: The Gaussian kernel size; ksize.width and ksize.height can differ, but they both must be positive and odd. Or, they can be zero's, then they are computed from sigma
+
+    :param sigma1sigma2: The Gaussian kernel standard deviations in X and Y direction. If sigmaY is zero, it is set to be equal to sigmaX. If they are both zeros, they are computed from ksize.width and ksize.height. To fully control the result regardless of possible future modification of all this semantics, it is recommended to specify all of ksize, sigmaX and sigmaY
+
+    :param bordertype: Pixel extrapolation method.
+
+The function convolves the source image with the specified Gaussian kernel. In-place filtering is supported.  Surpport 8UC1 8UC4 32SC1 32SC4 32FC1 32FC4 data type.
+
+ocl::boxFilter
+------------------
+Returns void
+
+.. ocv:function:: void boxFilter(const oclMat &src, oclMat &dst, int ddepth, Size ksize, Point anchor = Point(-1, -1), int borderType = BORDER_DEFAULT)
+
+    :param src: The source image
+
+    :param dst: The destination image; It will have the same size and the same type as src
+
+    :param ddepth: The desired depth of the destination image
+
+    :param ksize: The smoothing kernel size. It must be positive and odd
+
+    :param anchor: The anchor point. The default value Point(-1,-1) means that the anchor is at the kernel center.
+
+    :param bordertype: Pixel extrapolation method.
+
+Smoothes image using box filter.Supports data type: CV_8UC1, CV_8UC4, CV_32FC1 and CV_32FC4.
+
+ocl::Laplacian
+------------------
+Returns void
+
+.. ocv:function:: void Laplacian(const oclMat &src, oclMat &dst, int ddepth, int ksize = 1, double scale = 1)
+
+    :param src: The source image
+
+    :param dst: The destination image; It will have the same size and the same type as src
+
+    :param ddepth: The desired depth of the destination image
+
+    :param ksize: The aperture size used to compute the second-derivative filters. It must be positive and odd
+
+    :param scale: The optional scale factor for the computed Laplacian values (by default, no scaling is applied
+
+The function calculates the Laplacian of the source image by adding up the second x and y derivatives calculated using the Sobel operator.
+
+ocl::convolve
+------------------
+Returns void
+
+.. ocv:function:: void convolve(const oclMat &image, const oclMat &temp1, oclMat &result)
+
+    :param image: The source image
+
+    :param temp1: Convolution kernel, a single-channel floating point matrix.
+
+    :param result: The destination image
+
+Convolves an image with the kernel. Supports only CV_32FC1 data types and do not support ROI.
+
+ocl::bilateralFilter
+--------------------
+Returns void
+
+.. ocv:function:: void bilateralFilter(const oclMat &src, oclMat &dst, int d, double sigmaColor, double sigmaSpave, int borderType=BORDER_DEFAULT)
+
+    :param src: The source image
+
+    :param dst: The destination image; will have the same size and the same type as src
+
+    :param d: The diameter of each pixel neighborhood, that is used during filtering. If it is non-positive, it's computed from sigmaSpace
+
+    :param sigmaColor: Filter sigma in the color space. Larger value of the parameter means that farther colors within the pixel neighborhood (see sigmaSpace) will be mixed together, resulting in larger areas of semi-equal color
+
+    :param sigmaSpave: Filter sigma in the coordinate space. Larger value of the parameter means that farther pixels will influence each other (as long as their colors are close enough; see sigmaColor). Then d>0, it specifies the neighborhood size regardless of sigmaSpace, otherwise d is proportional to sigmaSpace.
+
+    :param borderType: Pixel extrapolation method.
+
+Applies bilateral filter to the image. Supports 8UC1 8UC4 data types.
+
+ocl::copyMakeBorder
+--------------------
+Returns void
+
+.. ocv:function:: void copyMakeBorder(const oclMat &src, oclMat &dst, int top, int bottom, int left, int right, int boardtype, const Scalar &value = Scalar())
+
+    :param src: The source image
+
+    :param dst: The destination image; will have the same type as src and the size size(src.cols+left+right, src.rows+top+bottom)
+
+    :param topbottomleftright: Specify how much pixels in each direction from the source image rectangle one needs to extrapolate, e.g. top=1, bottom=1, left=1, right=1mean that 1 pixel-wide border needs to be built
+
+    :param bordertype: Pixel extrapolation method.
+
+    :param value: The border value if borderType==BORDER CONSTANT
+
+Forms a border around the image. Supports 8UC1 8UC4 32SC1 32SC4 32FC1 32FC4 data types.
+
+ocl::dilate
+------------------
+Returns void
+
+.. ocv:function:: void dilate( const oclMat &src, oclMat &dst, const Mat &kernel, Point anchor = Point(-1, -1), int iterations = 1, int borderType = BORDER_CONSTANT, const Scalar &borderValue = morphologyDefaultBorderValue())
+
+    :param src: The source image
+
+    :param dst: The destination image; It will have the same size and the same type as src
+
+    :param kernel: The structuring element used for dilation. If element=Mat(), a 3times 3 rectangular structuring element is used
+
+    :param anchor: Position of the anchor within the element. The default value (-1, -1) means that the anchor is at the element center, only default value is supported
+
+    :param iterations: The number of times dilation is applied
+
+    :param bordertype: Pixel extrapolation method.
+
+    :param value: The border value if borderType==BORDER CONSTANT
+
+The function dilates the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the maximum is taken. Supports 8UC1 8UC4 data types.
+
+ocl::erode
+------------------
+Returns void
+
+.. ocv:function:: void erode( const oclMat &src, oclMat &dst, const Mat &kernel, Point anchor = Point(-1, -1), int iterations = 1, int borderType = BORDER_CONSTANT, const Scalar &borderValue = morphologyDefaultBorderValue())
+
+    :param src: The source image
+
+    :param dst: The destination image; It will have the same size and the same type as src
+
+    :param kernel: The structuring element used for dilation. If element=Mat(), a 3times 3 rectangular structuring element is used
+
+    :param anchor: Position of the anchor within the element. The default value (-1, -1) means that the anchor is at the element center, only default value is supported
+
+    :param iterations: The number of times dilation is applied
+
+    :param bordertype: Pixel extrapolation method.
+
+    :param value: The border value if borderType==BORDER CONSTANT
+
+The function erodes the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the minimum is taken. Supports 8UC1 8UC4 data types.
+
+ocl::morphologyEx
+------------------
+Returns void
+
+.. ocv:function:: void morphologyEx( const oclMat &src, oclMat &dst, int op, const Mat &kernel, Point anchor = Point(-1, -1), int iterations = 1, int borderType = BORDER_CONSTANT, const Scalar &borderValue = morphologyDefaultBorderValue())
+
+    :param src: The source image
+
+    :param dst: The destination image; It will have the same size and the same type as src
+
+    :param op: Type of morphological operation, one of the following: ERODE DILTATE OPEN CLOSE GRADIENT TOPHAT BLACKHAT
+
+    :param kernel: The structuring element used for dilation. If element=Mat(), a 3times 3 rectangular structuring element is used
+
+    :param anchor: Position of the anchor within the element. The default value (-1, -1) means that the anchor is at the element center, only default value is supported
+
+    :param iterations: The number of times dilation is applied
+
+    :param bordertype: Pixel extrapolation method.
+
+    :param value: The border value if borderType==BORDER CONSTANT
+
+A wrapper for erode and dilate. Supports 8UC1 8UC4 data types.
+
+ocl::pyrDown
+-------------------
+Smoothes an image and downsamples it.
+
+.. ocv:function:: void ocl::pyrDown(const oclMat& src, oclMat& dst)
+
+    :param src: Source image.
+
+    :param dst: Destination image. Will have ``Size((src.cols+1)/2, (src.rows+1)/2)`` size and the same type as ``src`` .
+
+.. seealso:: :ocv:func:`pyrDown`
+
+
+
+ocl::pyrUp
+-------------------
+Upsamples an image and then smoothes it.
+
+.. ocv:function:: void ocl::pyrUp(const oclMat& src, oclMat& dst)
+
+    :param src: Source image.
+
+    :param dst: Destination image. Will have ``Size(src.cols*2, src.rows*2)`` size and the same type as ``src`` .
+
+.. seealso:: :ocv:func:`pyrUp`
+
+ocl::columnSum
+------------------
+Computes a vertical (column) sum.
+
+.. ocv:function:: void ocl::columnSum(const oclMat& src, oclMat& sum)
+
+    :param src: Source image. Only  ``CV_32FC1`` images are supported for now.
+
+    :param sum: Destination image of the  ``CV_32FC1`` type.
+
+
+ocl::blendLinear
+-------------------
+Performs linear blending of two images.
+
+.. ocv:function:: void ocl::blendLinear(const oclMat& img1, const oclMat& img2, const oclMat& weights1, const oclMat& weights2, oclMat& result)
+
+    :param img1: First image. Supports only ``CV_8U`` and ``CV_32F`` depth.
+
+    :param img2: Second image. Must have the same size and the same type as ``img1`` .
+
+    :param weights1: Weights for first image. Must have tha same size as ``img1`` . Supports only ``CV_32F`` type.
+
+    :param weights2: Weights for second image. Must have tha same size as ``img2`` . Supports only ``CV_32F`` type.
+
+    :param result: Destination image.
--- a/modules/ocl/doc/image_processing.rst
+++ b/modules/ocl/doc/image_processing.rst
@@ -0,0 +1,331 @@
+Image Processing
+=============================
+
+.. highlight:: cpp
+
+ocl::cornerHarris
+------------------
+Returns void
+
+.. ocv:function:: void cornerHarris(const oclMat &src, oclMat &dst, int blockSize, int ksize, double k, int bordertype = cv::BORDER_DEFAULT)
+
+    :param src: Source image. Only CV_8UC1 and CV_32FC1 images are supported now.
+
+    :param dst: Destination image containing cornerness values. It has the same size as src and CV_32FC1 type.
+
+    :param blockSize: Neighborhood size
+
+    :param ksize: Aperture parameter for the Sobel operator
+
+    :param k: Harris detector free parameter
+
+    :param bordertype: Pixel extrapolation method. Only BORDER_REFLECT101, BORDER_REFLECT, BORDER_CONSTANT and BORDER_REPLICATE are supported now.
+
+Calculate Harris corner.
+
+ocl::cornerMinEigenVal
+------------------------
+Returns void
+
+.. ocv:function:: void cornerMinEigenVal(const oclMat &src, oclMat &dst, int blockSize, int ksize, int bordertype = cv::BORDER_DEFAULT)
+
+    :param src: Source image. Only CV_8UC1 and CV_32FC1 images are supported now.
+
+    :param dst: Destination image containing cornerness values. It has the same size as src and CV_32FC1 type.
+
+    :param blockSize: Neighborhood size
+
+    :param ksize: Aperture parameter for the Sobel operator
+
+    :param bordertype: Pixel extrapolation method. Only BORDER_REFLECT101, BORDER_REFLECT, BORDER_CONSTANT and BORDER_REPLICATE are supported now.
+
+Calculate MinEigenVal.
+
+ocl::calcHist
+------------------
+Returns void
+
+.. ocv:function:: void calcHist(const oclMat &mat_src, oclMat &mat_hist)
+
+    :param src: Source arrays. They all should have the same depth, CV 8U, and the same size. Each of them can have an arbitrary number of channels.
+
+    :param dst: The output histogram, a dense or sparse dims-dimensional
+
+Calculates histogram of one or more arrays. Supports only 8UC1 data type.
+
+ocl::remap
+------------------
+Returns void
+
+.. ocv:function:: void remap(const oclMat &src, oclMat &dst, oclMat &map1, oclMat &map2, int interpolation, int bordertype, const Scalar &value = Scalar())
+
+    :param src: Source image. Only CV_8UC1 and CV_32FC1 images are supported now.
+
+    :param dst: Destination image containing cornerness values. It has the same size as src and CV_32FC1 type.
+
+    :param map1: The first map of either (x,y) points or just x values having the type CV_16SC2 , CV_32FC1 , or CV_32FC2 . See covertMaps() for details on converting a floating point representation to fixed-point for speed.
+
+    :param map2: The second map of y values having the type CV_32FC1 , or none (empty map if map1 is (x,y) points), respectively.
+
+    :param interpolation: The interpolation method
+
+    :param bordertype: Pixel extrapolation method. Only BORDER_CONSTANT are supported now.
+
+    :param value: The border value if borderType==BORDER CONSTANT
+
+The function remap transforms the source image using the specified map: dst (x ,y) = src (map1(x , y) , map2(x , y)) where values of pixels with non-integer coordinates are computed using one of available interpolation methods. map1 and map2 can be encoded as separate floating-point maps in map1 and map2 respectively, or interleaved floating-point maps of (x,y) in map1. Supports CV_8UC1, CV_8UC3, CV_8UC4, CV_32FC1 , CV_32FC3 and CV_32FC4 data types.
+
+ocl::resize
+------------------
+Returns void
+
+.. ocv:function:: void resize(const oclMat &src, oclMat &dst, Size dsize, double fx = 0, double fy = 0, int interpolation = INTER_LINEAR)
+
+    :param src: Source image.
+
+    :param dst: Destination image.
+
+    :param dsize: he destination image size. If it is zero, then it is computed as: dsize = Size(round(fx*src.cols), round(fy*src.rows)). Either dsize or both fx or fy must be non-zero.
+
+    :param fx: The scale factor along the horizontal axis. When 0, it is computed as (double)dsize.width/src.cols
+
+    :param fy: The scale factor along the vertical axis. When 0, it is computed as (double)dsize.height/src.rows
+
+    :param interpolation: The interpolation method: INTER NEAREST or INTER LINEAR
+
+Resizes an image. Supports CV_8UC1, CV_8UC3, CV_8UC4, CV_32FC1 , CV_32FC3 and CV_32FC4 data types.
+
+ocl::warpAffine
+------------------
+Returns void
+
+.. ocv:function:: void warpAffine(const oclMat &src, oclMat &dst, const Mat &M, Size dsize, int flags = INTER_LINEAR)
+
+    :param src: Source image.
+
+    :param dst: Destination image.
+
+    :param M: 2times 3 transformation matrix
+
+    :param dsize: Size of the destination image
+
+    :param flags: A combination of interpolation methods, see cv::resize, and the optional flag WARP INVERSE MAP that means that M is the inverse transformation (dst to $src)
+
+The function warpAffine transforms the source image using the specified matrix. Supports INTER_NEAREST, INTER_LINEAR, INTER_CUBIC types.
+
+ocl::warpPerspective
+---------------------
+Returns void
+
+.. ocv:function:: void warpPerspective(const oclMat &src, oclMat &dst, const Mat &M, Size dsize, int flags = INTER_LINEAR)
+
+    :param src: Source image.
+
+    :param dst: Destination image.
+
+    :param M: 2times 3 transformation matrix
+
+    :param dsize: Size of the destination image
+
+    :param flags: A combination of interpolation methods, see cv::resize, and the optional flag WARP INVERSE MAP that means that M is the inverse transformation (dst to $src)
+
+Applies a perspective transformation to an image. Supports INTER_NEAREST, INTER_LINEAR, INTER_CUBIC types.
+
+ocl::cvtColor
+------------------
+Returns void
+
+.. ocv:function:: void cvtColor(const oclMat &src, oclMat &dst, int code , int dcn = 0)
+
+    :param src: Source image.
+
+    :param dst: Destination image.
+
+    :param code:The color space conversion code
+
+    :param dcn: The number of channels in the destination image; if the parameter is 0, the number of the channels will be derived automatically from src and the code
+
+Converts image from one color space to another.For now, only RGB2GRAY is supportted. Supports.CV_8UC1,CV_8UC4,CV_32SC1,CV_32SC4,CV_32FC1,CV_32FC4
+
+ocl::threshold
+------------------
+Returns Threshold value
+
+.. ocv:function:: double threshold(const oclMat &src, oclMat &dst, double thresh, double maxVal, int type = THRESH_TRUNC)
+
+    :param src: The source array
+
+    :param dst: Destination array; will have the same size and the same type as src
+
+    :param thresh: Threshold value
+
+    :param maxVal: Maximum value to use with THRESH BINARY and THRESH BINARY INV thresholding types
+
+    :param type: Thresholding type
+
+The function applies fixed-level thresholding to a single-channel array. The function is typically used to get a bi-level (binary) image out of a grayscale image or for removing a noise, i.e. filtering out pixels with too small or too large values. There are several types of thresholding that the function supports that are determined by thresholdType. Supports only CV_32FC1 and CV_8UC1 data type.
+
+ocl::buildWarpPlaneMaps
+-----------------------
+Builds plane warping maps.
+
+.. ocv:function:: void ocl::buildWarpPlaneMaps(Size src_size, Rect dst_roi, const Mat& R, double f, double s, double dist, oclMat& map_x, oclMat& map_y)
+
+
+
+ocl::buildWarpCylindricalMaps
+-----------------------------
+Builds cylindrical warping maps.
+
+.. ocv:function:: void ocl::buildWarpCylindricalMaps(Size src_size, Rect dst_roi, const Mat& R, double f, double s, oclMat& map_x, oclMat& map_y)
+
+
+
+
+ocl::buildWarpSphericalMaps
+---------------------------
+Builds spherical warping maps.
+
+.. ocv:function:: void ocl::buildWarpSphericalMaps(Size src_size, Rect dst_roi, const Mat& R, double f, double s, oclMat& map_x, oclMat& map_y)
+
+
+ocl::buildWarpPerspectiveMaps
+-----------------------------
+Builds transformation maps for perspective transformation.
+
+.. ocv:function:: void buildWarpAffineMaps(const Mat& M, bool inverse, Size dsize, oclMat& xmap, oclMat& ymap)
+
+    :param M: *3x3*  transformation matrix.
+
+    :param inverse: Flag  specifying that  ``M`` is an inverse transformation ( ``dst=>src`` ).
+
+    :param dsize: Size of the destination image.
+
+    :param xmap: X values with  ``CV_32FC1`` type.
+
+    :param ymap: Y values with  ``CV_32FC1`` type.
+
+.. seealso:: :ocv:func:`ocl::warpPerspective` , :ocv:func:`ocl::remap`
+
+
+ocl::buildWarpAffineMaps
+------------------------
+Builds transformation maps for affine transformation.
+
+.. ocv:function:: void buildWarpAffineMaps(const Mat& M, bool inverse, Size dsize, oclMat& xmap, oclMat& ymap)
+
+    :param M: *2x3*  transformation matrix.
+
+    :param inverse: Flag  specifying that  ``M`` is an inverse transformation ( ``dst=>src`` ).
+
+    :param dsize: Size of the destination image.
+
+    :param xmap: X values with  ``CV_32FC1`` type.
+
+    :param ymap: Y values with  ``CV_32FC1`` type.
+
+.. seealso:: :ocv:func:`ocl::warpAffine` , :ocv:func:`ocl::remap`
+
+ocl::PyrLKOpticalFlow
+---------------------
+.. ocv:class:: ocl::PyrLKOpticalFlow
+
+Class used for calculating an optical flow. ::
+
+    class PyrLKOpticalFlow
+    {
+    public:
+        PyrLKOpticalFlow();
+
+        void sparse(const oclMat& prevImg, const oclMat& nextImg, const oclMat& prevPts, oclMat& nextPts,
+            oclMat& status, oclMat* err = 0);
+
+        void dense(const oclMat& prevImg, const oclMat& nextImg, oclMat& u, oclMat& v, oclMat* err = 0);
+
+        Size winSize;
+        int maxLevel;
+        int iters;
+        double derivLambda;
+        bool useInitialFlow;
+        float minEigThreshold;
+        bool getMinEigenVals;
+
+        void releaseMemory();
+    };
+
+The class can calculate an optical flow for a sparse feature set or dense optical flow using the iterative Lucas-Kanade method with pyramids.
+
+.. seealso:: :ocv:func:`calcOpticalFlowPyrLK`
+
+
+
+ocl::PyrLKOpticalFlow::sparse
+-----------------------------
+Calculate an optical flow for a sparse feature set.
+
+.. ocv:function:: void ocl::PyrLKOpticalFlow::sparse(const oclMat& prevImg, const oclMat& nextImg, const oclMat& prevPts, oclMat& nextPts, oclMat& status, oclMat* err = 0)
+
+    :param prevImg: First 8-bit input image (supports both grayscale and color images).
+
+    :param nextImg: Second input image of the same size and the same type as  ``prevImg`` .
+
+    :param prevPts: Vector of 2D points for which the flow needs to be found. It must be one row matrix with CV_32FC2 type.
+
+    :param nextPts: Output vector of 2D points (with single-precision floating-point coordinates) containing the calculated new positions of input features in the second image. When ``useInitialFlow`` is true, the vector must have the same size as in the input.
+
+    :param status: Output status vector (CV_8UC1 type). Each element of the vector is set to 1 if the flow for the corresponding features has been found. Otherwise, it is set to 0.
+
+    :param err: Output vector (CV_32FC1 type) that contains the difference between patches around the original and moved points or min eigen value if ``getMinEigenVals`` is checked. It can be NULL, if not needed.
+
+.. seealso:: :ocv:func:`calcOpticalFlowPyrLK`
+
+
+
+ocl::PyrLKOpticalFlow::dense
+-----------------------------
+Calculate dense optical flow.
+
+.. ocv:function:: void ocl::PyrLKOpticalFlow::dense(const oclMat& prevImg, const oclMat& nextImg, oclMat& u, oclMat& v, oclMat* err = 0)
+
+    :param prevImg: First 8-bit grayscale input image.
+
+    :param nextImg: Second input image of the same size and the same type as  ``prevImg`` .
+
+    :param u: Horizontal component of the optical flow of the same size as input images, 32-bit floating-point, single-channel
+
+    :param v: Vertical component of the optical flow of the same size as input images, 32-bit floating-point, single-channel
+
+    :param err: Output vector (CV_32FC1 type) that contains the difference between patches around the original and moved points or min eigen value if ``getMinEigenVals`` is checked. It can be NULL, if not needed.
+
+
+
+ocl::PyrLKOpticalFlow::releaseMemory
+------------------------------------
+Releases inner buffers memory.
+
+.. ocv:function:: void ocl::PyrLKOpticalFlow::releaseMemory()
+
+
+ocl::interpolateFrames
+----------------------
+Interpolate frames (images) using provided optical flow (displacement field).
+
+.. ocv:function:: void ocl::interpolateFrames(const oclMat& frame0, const oclMat& frame1, const oclMat& fu, const oclMat& fv, const oclMat& bu, const oclMat& bv, float pos, oclMat& newFrame, oclMat& buf)
+
+    :param frame0: First frame (32-bit floating point images, single channel).
+
+    :param frame1: Second frame. Must have the same type and size as ``frame0`` .
+
+    :param fu: Forward horizontal displacement.
+
+    :param fv: Forward vertical displacement.
+
+    :param bu: Backward horizontal displacement.
+
+    :param bv: Backward vertical displacement.
+
+    :param pos: New frame position.
+
+    :param newFrame: Output image.
+
+    :param buf: Temporary buffer, will have width x 6*height size, CV_32FC1 type and contain 6 oclMat: occlusion masks for first frame, occlusion masks for second, interpolated forward horizontal flow, interpolated forward vertical flow, interpolated backward horizontal flow, interpolated backward vertical flow.
--- a/modules/ocl/doc/introduction.rst
+++ b/modules/ocl/doc/introduction.rst
@@ -6,14 +6,39 @@ OpenCL Module Introduction
 General Information
 -------------------

-The OpenCV OCL module is a set of classes and functions to utilize OpenCL compatible device. It should support any device compatible with OpenCL 1.1. The module includes utility functions, low-level vision primitives, and a few high-level algorithms ready to be used in the end-user applications.
+The OpenCV OCL module is a set of classes and functions to utilize OpenCL compatible device. In theroy, it supports any OpenCL 1.1 compatible device, but we only test it on AMD's, Intel's and NVIDIA's GPU at this stage. The compatibility, correctness and performance on CPU is not guaranteed. The OpenCV OCL module includes utility functions, low-level vision primitives, and high-level algorithms. The utility functions and low-level primitives provide a powerful infrastructure for developing fast vision algorithms taking advangtage of OCL whereas the high-level functionality includes some state-of-the-art algorithms(such as surf detector, face detector) ready to be used by the application developers.

-The OpenCV OCL module is designed as a host-level API plus device-level kernels. The device-level kernels are converted to text string and are compiled at runtime, so it need OpenCL runtime support. To correctly run the OpenCV OCL module, make sure you have OpenCL runtime provided by your device vendor, which is device driver normally.
+The OpenCV OCL module is designed as a host-level API plus device-level kernels. The device-level kernels are collected as strings at OpenCV compile time and are compiled at runtime, so it need OpenCL runtime support. To correctly build the OpenCV OCL module, make sure you have OpenCL SDK provided your device vendor. To correctly run the OpenCV OCL module, make sure you have OpenCL runtime provided by your device vendor, which is device driver normally.

-The OpenCV OCL module is designed for ease of use and does not require any knowledge of OpenCL. Though, such a knowledge will certainly be useful to handle non-trivial cases or achieve the highest performance. It is helpful to understand the cost of various operations, what the module does, what the preferred data formats are, and so on. Since there is data transfer between OpenCL host and OpenCL device, for better performance it's recommended to copy data once to the OpenCL host memory (i.e. copy ``cv::Mat`` to ``cv::ocl::OclMat``), then call several ``cv::ocl`` functions and then copy the result back to CPU memory, rather than do forward and backward transfer for each OCL function.
+The OpenCV OCL module is designed for ease of use and does not require any knowledge of OpenCL. Though, such a knowledge will certainly be useful to handle non-trivial cases or achieve the highest performance. It is helpful to understand the cost of various operations, what the OCL does, what the preferred data formats are, and so on. Since there is data transfer between OpenCL host and OpenCL device, for better performance it's recommended to copy data once to the OpenCL host memory (i.e. copy ``cv::Mat`` to ``cv::ocl::OclMat``), then call several ``cv::ocl`` functions and then copy the result back to CPU memory, rather than do forward and backward transfer for each OCL function.

-To enable OCL support, configure OpenCV using CMake with the option ``WITH\_OPENCL=ON``. If the option is passed and if OpenCL SDK is installed (e.g. on MacOSX it's always the case), the full-featured OpenCV OCL module will be built. Otherwise, the module will not be built.
+To enable OCL support, configure OpenCV using CMake with WIHT\_OPENCL=ON. When the flag is set and if OpenCL SDK is installed, the full-featured OpenCV OCL module is built. Otherwise, the module may be not built. If you have AMD'S FFT and BLAS library, you can select it with WITH\_OPENCLAMDFFT=ON, WIHT\_OPENCLAMDBLAS=ON.

-Right now, the user should define the ``cv::ocl::Info`` class in the application and call ``cv::ocl::getDevice`` before any ``cv::ocl::<func>``. This operation initialize OpenCL runtime and set the first found device as computing device. If there is more than one device and you want to use non-default device, you should call ``cv::ocl::setDevice``.
+Right now, the user should define the cv::ocl::Info class in the application and call cv::ocl::getDevice before any cv::ocl::func. This operation initialize OpenCL runtime and set the first found device as computing device. If there are more than one device and you want to use undefault device, you can call cv::ocl::setDevice then.

-In the current version, all the threads share the same context and device so the multi-devices are not supported. This is to be fixed in future releases.
+In the current version, all the thread share the same context and device so the multi-devices are not supported. We will add this feature soon. If a function support 4-channel operator, it should support 3-channel operator as well, because All the 3-channel matrix(i.e. RGB image) are represented by 4-channel matrix in oclMat. It means 3-channel image have 4-channel space with the last channel unused. We provide a transparent interface to handle the difference between OpenCV Mat and oclMat.
+
+Developer Notes
+-------------------
+
+This section descripe the design details of ocl module for who are interested in the detail of this module or want to contribute this module. User who isn't interested the details, can safely ignore it.
+
+1. OpenCL version should be larger than 1.1 with FULL PROFILE.
+
+2. There's only one OpenCL context and commandqueue and generated as a singleton. So now it only support one device with single commandqueue.
+
+3. All the functions use 256 as its workgroup size if possible, so the max work group size of the device must larger than 256.
+
+4. If the device support double, we will use double in kernel if OpenCV cpu version use double, otherwise, we use float instead.
+
+5. The oclMat use buffer object, not image object.
+
+6. All the 3-channel matrix(i.e. RGB image) are represented by 4-channel matrix in oclMat. It means 3-channel image have 4-channel space with the last channel unused. We provide a transparent interface to handle the difference between OpenCV Mat and oclMat.
+
+7. All the matrix in oclMat is aligned in column(now the alignment factor is 32 byte). It means, if a matrix is n columns m rows with the element size x byte, we will assign ALIGNMENT(x*n) bytes for each column with the last ALIGNMENT(x*n) - x*n bytes unused, so there's small holes after each column if its size is not the multiply of ALIGN.
+
+8. Data transfer between Mat and oclMat. If the CPU matrix is aligned in column, we will use faster API to transfer between Mat and oclMat, otherwise, we will use clEnqueueRead/WriteBufferRect to transfer data to guarantee the alignment. 3-channel matrix is an exception, it's directly transferred to a temp buffer and then padded to 4-channel matrix(also aligned) when uploading and do the reverse operation when downloading.
+
+9. Data transfer between Mat and oclMat. ROI is a feature of OpenCV, which allow users process a sub rectangle of a matrix. When a CPU matrix which has ROI will be transfered to GPU, the whole matrix will be transfered and set ROI as CPU's. In a word, we always transfer the whole matrix despite whether it has ROI or not.
+
+10. All the kernel file should locate in ocl/src/kernels/ with the extension ".cl". ALL the kernel files are transformed to pure characters at compilation time in kernels.cpp, and the file name without extension is the name of the characters.
--- a/modules/ocl/doc/matrix_reductions.rst
+++ b/modules/ocl/doc/matrix_reductions.rst
@@ -0,0 +1,70 @@
+Matrix Reductions
+=============================
+
+.. highlight:: cpp
+
+ocl::countNonZero
+------------------
+Returns the number of non-zero elements in src
+
+.. ocv:function:: int countNonZero(const oclMat &src)
+
+    :param src: Single-channel array
+
+Counts non-zero array elements.
+
+ocl::minMax
+------------------
+Returns void
+
+.. ocv:function:: void minMax(const oclMat &src, double *minVal, double *maxVal = 0, const oclMat &mask = oclMat())
+
+    :param src: Single-channel array
+
+    :param minVal: Pointer to returned minimum value, should not be NULL
+
+    :param maxVal: Pointer to returned maximum value, should not be NULL
+
+    :param mask: The optional mask used to select a sub-array
+
+Finds global minimum and maximum in a whole array or sub-array. Supports all data types.
+
+ocl::minMaxLoc
+------------------
+Returns void
+
+.. ocv:function:: void minMaxLoc(const oclMat &src, double *minVal, double *maxVal = 0, Point *minLoc = 0, Point *maxLoc = 0,const oclMat &mask = oclMat())
+
+    :param src: Single-channel array
+
+    :param minVal: Pointer to returned minimum value, should not be NULL
+
+    :param maxVal: Pointer to returned maximum value, should not be NULL
+
+    :param minLoc: Pointer to returned minimum location (in 2D case), should not be NULL
+
+    :param maxLoc: Pointer to returned maximum location (in 2D case) should not be NULL
+
+    :param mask: The optional mask used to select a sub-array
+
+The functions minMaxLoc find minimum and maximum element values and their positions. The extremums are searched across the whole array, or, if mask is not an empty array, in the specified array region. The functions do not work with multi-channel arrays.
+
+ocl::Sum
+------------------
+Returns the sum of matrix elements for each channel
+
+.. ocv:function:: Scalar sum(const oclMat &m)
+
+    :param m: The Source image of all depth
+
+Counts the sum of matrix elements for each channel.
+
+ocl::sqrSum
+------------------
+Returns the squared sum of matrix elements for each channel
+
+.. ocv:function:: Scalar sqrSum(const oclMat &m)
+
+    :param m: The Source image of all depth
+
+Counts the squared sum of matrix elements for each channel.
--- a/modules/ocl/doc/object_detection.rst
+++ b/modules/ocl/doc/object_detection.rst
@@ -0,0 +1,188 @@
+Object Detection
+=============================
+
+.. highlight:: cpp
+
+ocl::oclCascadeClassifier
+-------------------------
+
+Cascade classifier class used for object detection. Supports HAAR cascade classifier  in the form of cross link ::
+
+    class CV_EXPORTS OclCascadeClassifier : public  cv::CascadeClassifier
+    {
+    public:
+          OclCascadeClassifier() {};
+          ~OclCascadeClassifier() {};
+           CvSeq *oclHaarDetectObjects(oclMat &gimg, CvMemStorage *storage,
+                                      double scaleFactor,int minNeighbors,
+                                      int flags, CvSize minSize = cvSize(0, 0),
+                                      CvSize maxSize = cvSize(0, 0));
+    };
+
+ocl::oclCascadeClassifier::oclHaarDetectObjects
+------------------------------------------------------
+Returns the detected objects by a list of rectangles
+
+.. ocv:function:: CvSeq *OclCascadeClassifier::oclHaarDetectObjects(oclMat &gimg, CvMemStorage *storage, double scaleFactor,int minNeighbors, int flags, CvSize minSize = cvSize(0, 0), CvSize maxSize = cvSize(0, 0))
+
+    :param image:  Matrix of type CV_8U containing an image where objects should be detected.
+
+    :param imageobjectsBuff: Buffer to store detected objects (rectangles). If it is empty, it is allocated with the defaultsize. If not empty, the function searches not more than N  objects, where N = sizeof(objectsBufers data)/sizeof(cv::Rect).
+
+    :param scaleFactor: Parameter specifying how much the image size is reduced at each image scale.
+
+    :param minNeighbors: Parameter specifying how many neighbors each candidate rectangle should have to retain it.
+
+    :param minSize: Minimum possible object size. Objects smaller than that are ignored.
+
+Detects objects of different sizes in the input image,only tested for face detection now. The function returns the number of detected objects.
+
+ocl::MatchTemplateBuf
+---------------------
+.. ocv:class:: ocl::MatchTemplateBuf
+
+Class providing memory buffers for :ocv:func:`ocl::matchTemplate` function, plus it allows to adjust some specific parameters. ::
+
+    struct CV_EXPORTS MatchTemplateBuf
+    {
+        Size user_block_size;
+        oclMat imagef, templf;
+        std::vector<oclMat> images;
+        std::vector<oclMat> image_sums;
+        std::vector<oclMat> image_sqsums;
+    };
+
+You can use field `user_block_size` to set specific block size for :ocv:func:`ocl::matchTemplate` function. If you leave its default value `Size(0,0)` then automatic estimation of block size will be used (which is optimized for speed). By varying `user_block_size` you can reduce memory requirements at the cost of speed.
+
+ocl::matchTemplate
+----------------------
+Computes a proximity map for a raster template and an image where the template is searched for.
+
+.. ocv:function:: void ocl::matchTemplate(const oclMat& image, const oclMat& templ, oclMat& result, int method)
+
+.. ocv:function:: void ocl::matchTemplate(const oclMat& image, const oclMat& templ, oclMat& result, int method, MatchTemplateBuf &buf)
+
+    :param image: Source image.  ``CV_32F`` and  ``CV_8U`` depth images (1..4 channels) are supported for now.
+
+    :param templ: Template image with the size and type the same as  ``image`` .
+
+    :param result: Map containing comparison results ( ``CV_32FC1`` ). If  ``image`` is  *W x H*  and ``templ`` is  *w x h*, then  ``result`` must be *W-w+1 x H-h+1*.
+
+    :param method: Specifies the way to compare the template with the image.
+
+    :param buf: Optional buffer to avoid extra memory allocations and to adjust some specific parameters. See :ocv:class:`ocl::MatchTemplateBuf`.
+
+    The following methods are supported for the ``CV_8U`` depth images for now:
+
+    * ``CV_TM_SQDIFF``
+    * ``CV_TM_SQDIFF_NORMED``
+    * ``CV_TM_CCORR``
+    * ``CV_TM_CCORR_NORMED``
+    * ``CV_TM_CCOEFF``
+    * ``CV_TM_CCOEFF_NORMED``
+
+    The following methods are supported for the ``CV_32F`` images for now:
+
+    * ``CV_TM_SQDIFF``
+    * ``CV_TM_CCORR``
+
+.. seealso:: :ocv:func:`matchTemplate`
+
+
+ocl::SURF_OCL
+-------------
+.. ocv:class:: ocl::SURF_OCL
+
+Class used for extracting Speeded Up Robust Features (SURF) from an image. ::
+
+    class SURF_OCL
+    {
+    public:
+        enum KeypointLayout
+        {
+            X_ROW = 0,
+            Y_ROW,
+            LAPLACIAN_ROW,
+            OCTAVE_ROW,
+            SIZE_ROW,
+            ANGLE_ROW,
+            HESSIAN_ROW,
+            ROWS_COUNT
+        };
+
+        //! the default constructor
+        SURF_OCL();
+        //! the full constructor taking all the necessary parameters
+        explicit SURF_OCL(double _hessianThreshold, int _nOctaves=4,
+             int _nOctaveLayers=2, bool _extended=false, float _keypointsRatio=0.01f, bool _upright = false);
+
+        //! returns the descriptor size in float's (64 or 128)
+        int descriptorSize() const;
+
+        //! upload host keypoints to device memory
+        void uploadKeypoints(const vector<KeyPoint>& keypoints,
+            oclMat& keypointsocl);
+        //! download keypoints from device to host memory
+        void downloadKeypoints(const oclMat& keypointsocl,
+            vector<KeyPoint>& keypoints);
+
+        //! download descriptors from device to host memory
+        void downloadDescriptors(const oclMat& descriptorsocl,
+            vector<float>& descriptors);
+
+        void operator()(const oclMat& img, const oclMat& mask,
+            oclMat& keypoints);
+
+        void operator()(const oclMat& img, const oclMat& mask,
+            oclMat& keypoints, oclMat& descriptors,
+            bool useProvidedKeypoints = false);
+
+        void operator()(const oclMat& img, const oclMat& mask,
+            std::vector<KeyPoint>& keypoints);
+
+        void operator()(const oclMat& img, const oclMat& mask,
+            std::vector<KeyPoint>& keypoints, oclMat& descriptors,
+            bool useProvidedKeypoints = false);
+
+        void operator()(const oclMat& img, const oclMat& mask,
+            std::vector<KeyPoint>& keypoints,
+            std::vector<float>& descriptors,
+            bool useProvidedKeypoints = false);
+
+        void releaseMemory();
+
+        // SURF parameters
+        double hessianThreshold;
+        int nOctaves;
+        int nOctaveLayers;
+        bool extended;
+        bool upright;
+
+        //! max keypoints = min(keypointsRatio * img.size().area(), 65535)
+        float keypointsRatio;
+
+        oclMat sum, mask1, maskSum, intBuffer;
+
+        oclMat det, trace;
+
+        oclMat maxPosBuffer;
+    };
+
+
+The class ``SURF_OCL`` implements Speeded Up Robust Features descriptor. There is a fast multi-scale Hessian keypoint detector that can be used to find the keypoints (which is the default option). But the descriptors can also be computed for the user-specified keypoints. Only 8-bit grayscale images are supported.
+
+The class ``SURF_OCL`` can store results in the GPU and CPU memory. It provides functions to convert results between CPU and GPU version ( ``uploadKeypoints``, ``downloadKeypoints``, ``downloadDescriptors`` ). The format of CPU results is the same as ``SURF`` results. GPU results are stored in ``oclMat``. The ``keypoints`` matrix is :math:`\texttt{nFeatures} \times 7` matrix with the ``CV_32FC1`` type.
+
+* ``keypoints.ptr<float>(X_ROW)[i]`` contains x coordinate of the i-th feature.
+* ``keypoints.ptr<float>(Y_ROW)[i]`` contains y coordinate of the i-th feature.
+* ``keypoints.ptr<float>(LAPLACIAN_ROW)[i]``  contains the laplacian sign of the i-th feature.
+* ``keypoints.ptr<float>(OCTAVE_ROW)[i]`` contains the octave of the i-th feature.
+* ``keypoints.ptr<float>(SIZE_ROW)[i]`` contains the size of the i-th feature.
+* ``keypoints.ptr<float>(ANGLE_ROW)[i]`` contain orientation of the i-th feature.
+* ``keypoints.ptr<float>(HESSIAN_ROW)[i]`` contains the response of the i-th feature.
+
+The ``descriptors`` matrix is :math:`\texttt{nFeatures} \times \texttt{descriptorSize}` matrix with the ``CV_32FC1`` type.
+
+The class ``SURF_OCL`` uses some buffers and provides access to it. All buffers can be safely released between function calls.
+
+.. seealso:: :ocv:class:`SURF`
--- a/modules/ocl/doc/ocl.rst
+++ b/modules/ocl/doc/ocl.rst
@@ -6,15 +6,13 @@ ocl. OpenCL-accelerated Computer Vision
    :maxdepth: 1

    introduction
-    structures_and_functions
-..    initalization_and_information
-..    data_structures
-..    operations_on_matrices
-..    per_element_operations
-..    image_processing
-..    matrix_reductions
-..    object_detection
-..    feature_detection_and_description
-..    image_filtering
+    structures_and_utility_functions
+    data_structures
+    operations_on_matrices
+    matrix_reductions
+    image_filtering
+    image_processing
+    object_detection
+    feature_detection_and_description
 ..    camera_calibration_and_3d_reconstruction
 ..    video
--- a/modules/ocl/doc/operations_on_matrices.rst
+++ b/modules/ocl/doc/operations_on_matrices.rst
@@ -0,0 +1,474 @@
+Operations on Matrics
+=============================
+
+.. highlight:: cpp
+
+ocl::convertTo
+------------------
+Returns void
+
+.. ocv:function:: void convertTo( oclMat &m, int rtype, double alpha = 1, double beta = 0 ) const
+
+    :param m: The destination matrix. If it does not have a proper size or type before the operation, it will be reallocated
+
+    :param rtype: The desired destination matrix type, or rather, the depth(since the number of channels will be the same with the source one). If rtype is negative, the destination matrix will have the same type as the source.
+
+    :param alpha: must be default now
+
+    :param beta: must be default now
+
+The method converts source pixel values to the target datatype. saturate cast is applied in the end to avoid possible overflows. Supports CV_8UC1, CV_8UC4, CV_32SC1, CV_32SC4, CV_32FC1, CV_32FC4.
+
+ocl::copyTo
+------------------
+Returns void
+
+.. ocv:function:: void copyTo( oclMat &m, const oclMat &mask ) const
+
+    :param m: The destination matrix. If it does not have a proper size or type before the operation, it will be reallocated
+
+    :param mask(optional): The operation mask. Its non-zero elements indicate, which matrix elements need to be copied
+
+Copies the matrix to another one. Supports CV_8UC1, CV_8UC4, CV_32SC1, CV_32SC4, CV_32FC1, CV_32FC4
+
+ocl::setTo
+------------------
+Returns oclMat
+
+.. ocv:function:: oclMat &setTo(const Scalar &s, const oclMat &mask = oclMat())
+
+    :param s: Assigned scalar, which is converted to the actual array type
+
+    :param mask: The operation mask of the same size as ``*this``
+
+Sets all or some of the array elements to the specified value. This is the advanced variant of Mat::operator=(const Scalar s) operator. Supports CV_8UC1, CV_8UC4, CV_32SC1, CV_32SC4, CV_32FC1, CV_32FC4.
+
+ocl::absdiff
+------------------
+Returns void
+
+.. ocv:function:: void absdiff(const oclMat &a, const oclMat &b, oclMat &c)
+
+.. ocv:function:: void absdiff(const oclMat &a, const Scalar& sc, oclMat &c)
+
+    :param a: The first input array
+
+    :param b: The second input array, must be the same size and same type as a
+
+    :param sc: Scalar, the second input parameter
+
+    :param c: The destination array, it will have the same size and same type as a
+
+Computes per-element absolute difference between two arrays or between array and a scalar. Supports all data types except CV_8S.
+
+ocl::add
+------------------
+Returns void
+
+.. ocv:function:: void add(const oclMat &src1, const oclMat &src2, oclMat &dst, const oclMat& mask=oclMat())
+
+.. ocv:function:: void add(const oclMat &src1, const Scalar &sc, oclMat &dst, const oclMat& mask=oclMat())
+
+    :param src1: The first input array
+
+    :param src2: The second input array, must be the same size and same type as src1
+
+    :param sc: Scalar, the second input parameter
+
+    :param dst: The destination array, it will have the same size and same type as src1
+
+    :param mask: he optional operation mask, 8-bit single channel array; specifies elements of the destination array to be changed
+
+Computes per-element additon between two arrays or between array and a scalar. Supports all data types except CV_8S.
+
+ocl::subtract
+------------------
+Returns void
+
+.. ocv:function:: void subtract(const oclMat &src1, const oclMat &src2, oclMat &dst, const oclMat& mask=oclMat())
+
+.. ocv:function:: void subtract(const oclMat &src1, const Scalar &sc, oclMat &dst, const oclMat& mask=oclMat())
+
+    :param src1: The first input array
+
+    :param src2: The second input array, must be the same size and same type as src1
+
+    :param sc: Scalar, the second input parameter
+
+    :param dst: The destination array, it will have the same size and same type as src1
+
+    :param mask: he optional operation mask, 8-bit single channel array; specifies elements of the destination array to be changed
+
+Computes per-element subtract between two arrays or between array and a scalar. Supports all data types except CV_8S.
+
+ocl::multiply
+------------------
+Returns void
+
+.. ocv:function:: void multiply(const oclMat &src1, const oclMat &src2, oclMat &dst, double scale = 1)
+
+    :param src1: The first input array
+
+    :param src2: The second input array, must be the same size and same type as src1
+
+    :param dst: The destination array, it will have the same size and same type as src1
+
+    :param scale: must be 1 now
+
+Computes per-element multiply between two arrays or between array and a scalar. Supports all data types except CV_8S.
+
+ocl::divide
+------------------
+Returns void
+
+.. ocv:function:: void divide(const oclMat &src1, const oclMat &src2, oclMat &dst, double scale = 1)
+
+    :param src1: The first input array
+
+    :param src2: The second input array, must be the same size and same type as src1
+
+    :param dst: The destination array, it will have the same size and same type as src1
+
+    :param scale: must be 1 now
+
+Computes per-element divide between two arrays or between array and a scalar. Supports all data types except CV_8S.
+
+ocl::bitwise_and
+------------------
+Returns void
+
+.. ocv:function:: void bitwise_and(const oclMat &src1, const oclMat &src2, oclMat &dst, const oclMat& mask=oclMat())
+
+.. ocv:function:: void bitwise_and(const oclMat &src1, const Scalar &sc, oclMat &dst, const oclMat& mask=oclMat())
+
+    :param src1: The first input array
+
+    :param src2: The second input array, must be the same size and same type as src1
+
+    :param sc: Scalar, the second input parameter
+
+    :param dst: The destination array, it will have the same size and same type as src1
+
+    :param mask: The optional operation mask, 8-bit single channel array; specifies elements of the destination array to be changed
+
+Computes per-element bitwise_and between two arrays or between array and a scalar. Supports all data types except CV_8S.
+
+ocl::bitwise_or
+------------------
+Returns void
+
+.. ocv:function:: void bitwise_or(const oclMat &src1, const oclMat &src2, oclMat &dst, const oclMat& mask=oclMat())
+
+.. ocv:function:: void bitwise_or(const oclMat &src1, const Scalar &sc, oclMat &dst, const oclMat& mask=oclMat())
+
+    :param src1: The first input array
+
+    :param src2: The second input array, must be the same size and same type as src1
+
+    :param sc: Scalar, the second input parameter
+
+    :param dst: The destination array, it will have the same size and same type as src1
+
+    :param mask: The optional operation mask, 8-bit single channel array; specifies elements of the destination array to be changed
+
+Computes per-element bitwise_or between two arrays or between array and a scalar. Supports all data types except CV_8S.
+
+ocl::bitwise_xor
+------------------
+Returns void
+
+.. ocv:function:: void bitwise_xor(const oclMat &src1, const oclMat &src2, oclMat &dst, const oclMat& mask=oclMat())
+
+.. ocv:function:: void bitwise_xor(const oclMat &src1, const Scalar &sc, oclMat &dst, const oclMat& mask=oclMat())
+
+    :param src1: The first input array
+
+    :param src2: The second input array, must be the same size and same type as src1
+
+    :param sc: Scalar, the second input parameter
+
+    :param dst: The destination array, it will have the same size and same type as src1
+
+    :param mask: The optional operation mask, 8-bit single channel array; specifies elements of the destination array to be changed
+
+Computes per-element bitwise_xor between two arrays or between array and a scalar. Supports all data types except CV_8S.
+
+ocl::bitwise_not
+------------------
+Returns void
+
+.. ocv:function:: void bitwise_not(const oclMat &src, oclMat &dst)
+
+    :param src: The input array
+
+    :param dst: The destination array, it will have the same size and same type as src1
+
+The functions bitwise not compute per-element bit-wise inversion of the source array:. Supports all data types except CV_8S.
+
+ocl::cartToPolar
+------------------
+Returns void
+
+.. ocv:function:: void cartToPolar(const oclMat &x, const oclMat &y, oclMat &magnitude, oclMat &angle, bool angleInDegrees = false)
+
+    :param x: The array of x-coordinates; must be single-precision or double-precision floating-point array
+
+    :param y: The array of y-coordinates; it must have the same size and same type as x
+
+    :param magnitude: The destination array of magnitudes of the same size and same type as x
+
+    :param angle: The destination array of angles of the same size and same type as x. The angles are measured in radians (0 to 2pi ) or in degrees (0 to 360 degrees).
+
+    :param angleInDegrees: The flag indicating whether the angles are measured in radians, which is default mode, or in degrees
+
+Calculates the magnitude and angle of 2d vectors. Supports only CV_32F and CV_64F data types.
+
+ocl::polarToCart
+------------------
+Returns void
+
+.. ocv:function:: void polarToCart(const oclMat &magnitude, const oclMat &angle, oclMat &x, oclMat &y, bool angleInDegrees = false)
+
+    :param magnitude: The source floating-point array of magnitudes of 2D vectors. It can be an empty matrix (=Mat()) - in this case the function assumes that all the magnitudes are =1. If it's not empty, it must have the same size and same type as angle
+
+    :param angle: The source floating-point array of angles of the 2D vectors
+
+    :param x: The destination array of x-coordinates of 2D vectors; will have the same size and the same type as angle
+
+    :param y: The destination array of y-coordinates of 2D vectors; will have the same size and the same type as angle
+
+    :param angleInDegrees: The flag indicating whether the angles are measured in radians, which is default mode, or in degrees
+
+The function polarToCart computes the cartesian coordinates of each 2D vector represented by the corresponding elements of magnitude and angle. Supports only CV_32F and CV_64F data types.
+
+ocl::compare
+------------------
+Returns void
+
+.. ocv:function:: void compare(const oclMat &a, const oclMat &b, oclMat &c, int cmpop)
+
+    :param a: The first source array
+
+    :param b: The second source array; must have the same size and same type as a
+
+    :param c: The destination array; will have the same size as a
+
+    :param cmpop: The flag specifying the relation between the elements to be checked
+
+Performs per-element comparison of two arrays or an array and scalar value. Supports all the 1 channel data types except CV_8S.
+
+ocl::exp
+------------------
+Returns void
+
+.. ocv:function:: void exp(const oclMat &a, oclMat &b)
+
+    :param a: The first source array
+
+    :param b: The dst array; must have the same size and same type as a
+
+The function exp calculates the exponent of every element of the input array. Supports only CV_32FC1 data type.
+
+ocl::log
+------------------
+Returns void
+
+.. ocv:function:: void log(const oclMat &a, oclMat &b)
+
+    :param a: The first source array
+
+    :param b: The dst array; must have the same size and same type as a
+
+The function log calculates the log of every element of the input array. Supports only CV_32FC1 data type.
+
+ocl::LUT
+------------------
+Returns void
+
+.. ocv:function:: void LUT(const oclMat &src, const oclMat &lut, oclMat &dst)
+
+    :param src: Source array of 8-bit elements
+
+    :param lut: Look-up table of 256 elements. In the case of multi-channel source array, the table should either have a single channel (in this case the same table is used for all channels) or the same number of channels as in the source array
+
+    :param dst: Destination array; will have the same size and the same number of channels as src, and the same depth as lut
+
+Performs a look-up table transform of an array. Supports only CV_8UC1 and CV_8UC4 data type.
+
+ocl::magnitude
+------------------
+Returns void
+
+.. ocv:function:: void magnitude(const oclMat &x, const oclMat &y, oclMat &magnitude)
+
+    :param x: The floating-point array of x-coordinates of the vectors
+
+    :param y: he floating-point array of y-coordinates of the vectors; must have the same size as x
+
+    :param magnitude: The destination array; will have the same size and same type as x
+
+The function magnitude calculates magnitude of 2D vectors formed from the corresponding elements of x and y arrays. Supports only CV_32F and CV_64F data type.
+
+ocl::flip
+------------------
+Returns void
+
+.. ocv:function:: void flip(const oclMat &src, oclMat &dst, int flipCode)
+
+    :param src: Source image.
+
+    :param dst: Destination image
+
+    :param flipCode: Specifies how to flip the array: 0 means flipping around the x-axis, positive (e.g., 1) means flipping around y-axis, and negative (e.g., -1) means flipping around both axes.
+
+The function flip flips the array in one of three different ways (row and column indices are 0-based). Supports all data types.
+
+ocl::meanStdDev
+------------------
+Returns void
+
+.. ocv:function:: void meanStdDev(const oclMat &mtx, Scalar &mean, Scalar &stddev)
+
+    :param mtx: Source image.
+
+    :param mean: The output parameter: computed mean value
+
+    :param stddev: The output parameter: computed standard deviation
+
+The functions meanStdDev compute the mean and the standard deviation M of array elements, independently for each channel, and return it via the output parameters. Supports all data types except CV_32F,CV_64F
+
+ocl::merge
+------------------
+Returns void
+
+.. ocv:function:: void merge(const vector<oclMat> &src, oclMat &dst)
+
+    :param src: The source array or vector of the single-channel matrices to be merged. All the matrices in src must have the same size and the same type
+
+    :param dst: The destination array; will have the same size and the same depth as src, the number of channels will match the number of source matrices
+
+Composes a multi-channel array from several single-channel arrays. Supports all data types.
+
+ocl::split
+------------------
+Returns void
+
+.. ocv:function:: void split(const oclMat &src, vector<oclMat> &dst)
+
+    :param src: The source multi-channel array
+
+    :param dst: The destination array or vector of arrays; The number of arrays must match src.channels(). The arrays themselves will be reallocated if needed
+
+The functions split split multi-channel array into separate single-channel arrays. Supports all data types.
+
+ocl::norm
+------------------
+Returns the calculated norm
+
+.. ocv:function:: double norm(const oclMat &src1, int normType = NORM_L2)
+
+.. ocv:function:: double norm(const oclMat &src1, const oclMat &src2, int normType = NORM_L2)
+
+    :param src1: The first source array
+
+    :param src2: The second source array of the same size and the same type as src1
+
+    :param normType: Type of the norm
+
+Calculates absolute array norm, absolute difference norm, or relative difference norm. Supports only CV_8UC1 data type.
+
+ocl::phase
+------------------
+Returns void
+
+.. ocv:function:: void phase(const oclMat &x, const oclMat &y, oclMat &angle, bool angleInDegrees = false)
+
+    :param x: The source floating-point array of x-coordinates of 2D vectors
+
+    :param y: The source array of y-coordinates of 2D vectors; must have the same size and the same type as x
+
+    :param angle: The destination array of vector angles; it will have the same size and same type as x
+
+    :param angleInDegrees: When it is true, the function will compute angle in degrees, otherwise they will be measured in radians
+
+The function phase computes the rotation angle of each 2D vector that is formed from the corresponding elements of x and y. Supports only CV_32FC1 and CV_64FC1 data type.
+
+ocl::pow
+------------------
+Returns void
+
+.. ocv:function:: void pow(const oclMat &x, double p, oclMat &y)
+
+    :param x: The source array
+
+    :param power: The exponent of power;The source floating-point array of angles of the 2D vectors
+
+    :param y: The destination array, should be the same type as the source
+
+The function pow raises every element of the input array to p. Supports only CV_32FC1 and CV_64FC1 data type.
+
+ocl::transpose
+------------------
+Returns void
+
+.. ocv:function:: void transpose(const oclMat &src, oclMat &dst)
+
+    :param src: The source array
+
+    :param dst: The destination array of the same type as src
+
+Transposes a matrix. Supports 8UC1, 8UC4, 8SC4, 16UC2, 16SC2, 32SC1 and 32FC1 data types.
+
+
+ocl::dft
+------------
+Performs a forward or inverse discrete Fourier transform (1D or 2D) of the floating point matrix.
+
+.. ocv:function:: void ocl::dft(const oclMat& src, oclMat& dst, Size dft_size, int flags=0)
+
+    :param src: Source matrix (real or complex).
+
+    :param dst: Destination matrix (real or complex).
+
+    :param dft_size: Size of original input, which is used for transformation from complex to real.
+
+    :param flags: Optional flags:
+
+        * **DFT_ROWS** transforms each individual row of the source matrix.
+
+        * **DFT_COMPLEX_OUTPUT** performs a forward transformation of 1D or 2D real array. The result, though being a complex array, has complex-conjugate symmetry (*CCS*, see the function description below for details). Such an array can be packed into a real array of the same size as input, which is the fastest option and which is what the function does by default. However, you may wish to get a full complex array (for simpler spectrum analysis, and so on). Pass the flag to enable the function to produce a full-size complex output array.
+
+        * **DFT_INVERSE** inverts DFT. Use for complex-complex cases (real-complex and complex-real cases are always forward and inverse, respectively).
+
+        * **DFT_REAL_OUTPUT** specifies the output as real. The source matrix is the result of real-complex transform, so the destination matrix must be real.
+
+Use to handle real matrices ( ``CV32FC1`` ) and complex matrices in the interleaved format ( ``CV32FC2`` ).
+
+The dft_size must be powers of 2, 3 and 5. Real to complex dft output is not the same with cpu version. real to complex and complex to real does not support DFT_ROWS
+
+.. seealso:: :ocv:func:`dft`
+
+ocl::gemm
+------------------
+Performs generalized matrix multiplication.
+
+.. ocv:function:: void gemm(const oclMat& src1, const oclMat& src2, double alpha, const oclMat& src3, double beta, oclMat& dst, int flags = 0)
+
+    :param src1: First multiplied input matrix that should be ``CV_32FC1`` type.
+
+    :param src2: Second multiplied input matrix of the same type as  ``src1`` .
+
+    :param alpha: Weight of the matrix product.
+
+    :param src3: Third optional delta matrix added to the matrix product. It should have the same type as  ``src1``  and  ``src2`` .
+
+    :param beta: Weight of  ``src3`` .
+
+    :param dst: Destination matrix. It has the proper size and the same type as input matrices.
+
+    :param flags: Operation flags:
+
+            * **GEMM_1_T** transpose  ``src1``
+            * **GEMM_2_T** transpose  ``src2``
+
+.. seealso:: :ocv:func:`gemm`
--- a/modules/ocl/doc/structures_and_functions.rst
+++ b/modules/ocl/doc/structures_and_functions.rst
@@ -1,23 +0,0 @@
-Data Structures and Functions
-=============================
-
-.. highlight:: cpp
-
-ocl::Info
---------
-.. ocv:class:: ocl::Info
-
-this class should be maintained by the user and be passed to getDevice
-
-ocl::getDevice
------------------
-Returns the list of devices
-
-.. ocv:function:: int ocl::getDevice( std::vector<Info> & oclinfo, int devicetype=CVCL_DEVICE_TYPE_GPU )
-
-    :param oclinfo: Output vector of ``ocl::Info`` structures
-
-    :param devicetype: One of ``CVCL_DEVICE_TYPE_GPU``, ``CVCL_DEVICE_TYPE_CPU`` or ``CVCL_DEVICE_TYPE_DEFAULT``.
-
-the function must be called before any other ``cv::ocl`` functions; it initializes ocl runtime.
-
--- a/modules/ocl/doc/structures_and_utility_functions.rst
+++ b/modules/ocl/doc/structures_and_utility_functions.rst
@@ -0,0 +1,58 @@
+Data Structures and Utility Functions
+========================================
+
+.. highlight:: cpp
+
+ocl::Info
+---------
+.. ocv:class:: ocl::Info
+
+this class should be maintained by the user and be passed to getDevice
+
+ocl::getDevice
+------------------
+Returns the list of devices
+
+.. ocv:function:: int ocl::getDevice( std::vector<Info> & oclinfo, int devicetype=CVCL_DEVICE_TYPE_GPU )
+
+    :param oclinfo: Output vector of ``ocl::Info`` structures
+
+    :param devicetype: One of ``CVCL_DEVICE_TYPE_GPU``, ``CVCL_DEVICE_TYPE_CPU`` or ``CVCL_DEVICE_TYPE_DEFAULT``.
+
+the function must be called before any other ``cv::ocl`` functions; it initializes ocl runtime.
+
+ocl::setDevice
+------------------
+Returns void
+
+.. ocv:function:: void ocl::setDevice( Info &oclinfo, int devnum = 0 )
+
+    :param oclinfo: Output vector of ``ocl::Info`` structures
+
+    :param devnum: the selected OpenCL device under this platform.
+
+ocl::setBinpath
+------------------
+Returns void
+
+.. ocv:function:: void setBinpath(const char *path)
+
+    :param path: the path of OpenCL kernel binaries
+
+If you call this function and set a valid path, the OCL module will save the compiled kernel to the address in the first time and reload the binary since that. It can save compilation time at the runtime.
+
+ocl::getoclContext
+------------------
+Returns the pointer to the opencl context
+
+.. ocv:function:: void *getoclContext()
+
+Thefunction are used to get opencl context so that opencv can interactive with other opencl program.
+
+ocl::getoclCommandQueue
+--------------------------
+Returns the pointer to the opencl command queue
+
+.. ocv:function:: void *getoclCommandQueue()
+
+Thefunction are used to get opencl command queue so that opencv can interactive with other opencl program.
--- a/modules/ocl/src/brute_force_matcher.cpp
+++ b/modules/ocl/src/brute_force_matcher.cpp
@@ -300,7 +300,7 @@ void matchUnrolledCached(const oclMat &query, const oclMat &train, float maxDist
        args.push_back( make_pair( sizeof(cl_int), (void *)&query.cols ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&train.rows ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&train.cols ));
-        args.push_back( make_pair( sizeof(cl_mem), (void *)&trainIdx.cols ));
+        args.push_back( make_pair( sizeof(cl_int), (void *)&trainIdx.cols ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&query.step ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&trainIdx.step ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&distType ));
@@ -338,7 +338,7 @@ void radius_match(const oclMat &query, const oclMat &train, float maxDistance, c
        args.push_back( make_pair( sizeof(cl_int), (void *)&query.cols ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&train.rows ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&train.cols ));
-        args.push_back( make_pair( sizeof(cl_mem), (void *)&trainIdx.cols ));
+        args.push_back( make_pair( sizeof(cl_int), (void *)&trainIdx.cols ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&query.step ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&trainIdx.step ));
        args.push_back( make_pair( sizeof(cl_int), (void *)&distType ));
--- a/modules/ocl/src/initialization.cpp
+++ b/modules/ocl/src/initialization.cpp
@@ -338,7 +338,8 @@ namespace cv
                                           EXT_LEN, (void *)extends_set, &extends_size));
            CV_Assert(extends_size < EXT_LEN);
            extends_set[EXT_LEN - 1] = 0;
-            //oclinfo.extra_options = NULL;
+            memset(oclinfo.impl->extra_options, 0, 512);
+            oclinfo.impl->double_support = 0;
            int fp64_khr = string(extends_set).find("cl_khr_fp64");

            if(fp64_khr >= 0 && fp64_khr < EXT_LEN)
--- a/modules/photo/perf/perf_precomp.hpp
+++ b/modules/photo/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/photo/test/test_precomp.hpp
+++ b/modules/photo/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/stitching/perf/perf_precomp.hpp
+++ b/modules/stitching/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_PERF_PRECOMP_HPP__
--- a/modules/stitching/test/test_precomp.hpp
+++ b/modules/stitching/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__
--- a/modules/ts/include/opencv2/ts/ts_perf.hpp
+++ b/modules/ts/include/opencv2/ts/ts_perf.hpp
@@ -478,7 +478,7 @@ CV_EXPORTS void PrintTo(const Size& sz, ::std::ostream* os);
 #define CV_PERF_TEST_MAIN(testsuitname, ...) \
 int main(int argc, char **argv)\
 {\
-    __VA_ARGS__;\
+    while (++argc >= (--argc,-1)) {__VA_ARGS__; break;} /*this ugly construction is needed for VS 2005*/\
    ::perf::Regression::Init(#testsuitname);\
    ::perf::TestBase::Init(argc, argv);\
    ::testing::InitGoogleTest(&argc, argv);\
--- a/modules/video/perf/perf_precomp.hpp
+++ b/modules/video/perf/perf_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_VIDEO_PRECOMP_HPP__
--- a/modules/video/test/test_precomp.hpp
+++ b/modules/video/test/test_precomp.hpp
@@ -1,6 +1,9 @@
 #ifdef __GNUC__
 #  pragma GCC diagnostic ignored "-Wmissing-declarations"
-#  pragma GCC diagnostic ignored "-Wmissing-prototypes" //OSX
+#  ifdef __clang__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
 #endif

 #ifndef __OPENCV_TEST_PRECOMP_HPP__