generic-library/opencv
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

fixed problems indicated with ? marks

Browse Source
This commit is contained in:
Vadim Pisarevsky
2011-05-05 13:31:54 +00:00
parent 3467c6f732
commit f39db3f15a
11 changed files with 154 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
modules/features2d/doc/feature_detection_and_description.rst
View File

@@ -27,7 +27,7 @@ MSER
----
.. c:type:: MSER
Maximally (or Most??) stable extremal region extractor ::
Maximally stable extremal region extractor ::
class MSER : public CvMSERParams
{
@@ -85,7 +85,7 @@ Class implementing the Star keypoint detector ::
};
The class implements a modified version of the CenSurE keypoint detector described in
Agrawal08??.
[Agrawal08].
.. index:: SIFT
@@ -210,10 +210,10 @@ Class for extracting Speeded Up Robust Features from an image ::
bool useProvidedKeypoints=false) const;
};
The class implements the Speeded Up Robust Features descriptor Bay06.
The class implements the Speeded Up Robust Features descriptor [Bay06].
There is a fast multi-scale Hessian keypoint detector that can be used to find keypoints
(which is the default option). But the descriptors can be also computed for the user-specified keypoints.
The function?? can be used for object tracking and localization, image stitching, and so on. See the ``find_obj.cpp`` demo in OpenCV samples directory.
The algorithm can be used for object tracking and localization, image stitching, and so on. See the ``find_obj.cpp`` demo in OpenCV samples directory.
.. index:: RandomizedTree
@@ -301,13 +301,19 @@ RandomizedTree::train
.. c:function:: void train(std::vector<BaseKeypoint> const& base_set, RNG& rng, PatchGenerator& make_patch, int depth, int views, size_t reduced_num_dim, int num_quant_bits)
{Vector of ``BaseKeypoint`` type. Contains keypoints from the image that are used for training}??
{Random numbers generator is used for training}??
{Patch generator is used for training}??
{Maximum tree depth}??
:param base_set: Vector of ``BaseKeypoint`` type. Contains keypoints from the image that are used for training
:param rng: Random numbers generator is used for training
:param make_patch: Patch generator is used for training
:param depth: Maximum tree depth
{Number of dimensions are used in compressed signature}??
{Number of bits are used for quantization}??
:param views: The number of random views of each keypoint neighborhood to generate
:param reduced_num_dim: Number of dimensions are used in compressed signature
:param num_quant_bits: Number of bits are used for quantization
.. index:: RandomizedTree::read
@@ -315,15 +321,15 @@ RandomizedTree::read
------------------------
.. c:function:: read(const char* file_name, int num_quant_bits)
Reads a pre-saved randomized tree from a file or stream. ?? is it applied to the 1st func only?
.. c:function:: read(std::istream &is, int num_quant_bits)
.. c:function:: read(std::istream \&is, int num_quant_bits)
Read a pre-saved randomized tree from a file or stream.
:param file_name: Name of the file that contains randomized tree data.
:param is: Input stream associated with the file that contains randomized tree data.
{Number of bits are used for quantization}??
:param num_quant_bits: Number of bits are used for quantization
.. index:: RandomizedTree::write
@@ -347,7 +353,7 @@ RandomizedTree::applyQuantization
Applies quantization to the current randomized tree.
{Number of bits are used for quantization}??
:param num_quant_bits: Number of bits are used for quantization
.. index:: RTreeNode
@@ -459,15 +465,23 @@ RTreeClassifier::train
.. c:function:: void train(vector<BaseKeypoint> const& base_set, RNG& rng, PatchGenerator& make_patch, int num_trees = RTreeClassifier::DEFAULT_TREES, int depth = DEFAULT_DEPTH, int views = DEFAULT_VIEWS, size_t reduced_num_dim = DEFAULT_REDUCED_NUM_DIM, int num_quant_bits = DEFAULT_NUM_QUANT_BITS, bool print_status = true)
{Vector of ``BaseKeypoint`` type. Contains image keypoints used for training}??
{Random-number generator is used for training}??
{Patch generator is used for training}??
{Number of randomized trees used in RTreeClassificator}??
{Maximum tree depth}??
:param base_set: Vector of ``BaseKeypoint`` type. Contains image keypoints used for training
:param rng: Random-number generator is used for training
:param make_patch: Patch generator is used for training
:param num_trees: Number of randomized trees used in RTreeClassificator
:param depth: Maximum tree depth
{Number of dimensions are used in compressed signature}??
{Number of bits are used for quantization}??
{Print current status of training on the console}??
:param views: The number of random views of each keypoint neighborhood to generate
:param reduced_num_dim: Number of dimensions are used in compressed signature
:param num_quant_bits: Number of bits are used for quantization
:param print_status: Print current status of training on the console
.. index:: RTreeClassifier::getSignature
@@ -479,8 +493,8 @@ RTreeClassifier::getSignature
.. c:function:: void getSignature(IplImage *patch, float *sig)
{Image patch to calculate signature for}
{Output signature (array dimension is ``reduced_num_dim)`` }
:param patch: Image patch to calculate signature for
:param sig: Output signature (array dimension is ``reduced_num_dim)``
.. index:: RTreeClassifier::getSparseSignature
@@ -489,11 +503,13 @@ RTreeClassifier::getSparseSignature
.. c:function:: void getSparseSignature(IplImage *patch, float *sig, float thresh)
Similarly to ``getSignaturebut`` , uses a threshold for removing all signature elements below the threshold so that the signature is compressed.??
Similarly to ``getSignature``, but it uses a threshold for removing all signature elements below the threshold so that the signature is compressed.
{Image patch to calculate signature for}??
{Output signature (array dimension is ``reduced_num_dim)``}??
{The threshold that is used for compressing the signature}??
:param patch: Image patch to calculate signature for
:param sig: Output signature (array dimension is ``reduced_num_dim)``
:param thresh: The threshold that is used for compressing the signature
.. index:: RTreeClassifier::countNonZeroElements
@@ -507,7 +523,7 @@ RTreeClassifier::countNonZeroElements
:param n: Input vector size.
{The threshold used for counting elements. We take all elements are less than ``tol`` as zero elements}??
:param tol: The threshold used for counting elements. We take all elements are less than ``tol`` as zero elements
.. index:: RTreeClassifier::read
@@ -531,11 +547,11 @@ RTreeClassifier::write
Writes the current RTreeClassifier to a file or stream.
.. c:function:: void write(std::ostream \&os) const
.. c:function:: void write(std::ostream &os) const
:param file_name: Name of the file where randomized tree data is stored.
:param is: Output stream associated with the file where randomized tree data is stored.
:param os: Output stream associated with the file where randomized tree data is stored.
.. index:: RTreeClassifier::setQuantization
@@ -545,7 +561,7 @@ RTreeClassifier::setQuantization
Applies quantization to the current randomized tree.
{Number of bits are used for quantization}??
:param num_quant_bits: Number of bits are used for quantization
The example below demonstrates the usage of ``RTreeClassifier`` for feature matching. There are test and train images and features are extracted from both with SURF. Output is
:math:`best\_corr` and