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

Added erGrouping function: Find groups of Extremal Regions that are organized as text blocks. Updated sample/cpp to use the complete text detection pipeline

Browse Source
This commit is contained in:
lluis
2013-09-17 23:45:23 +02:00
parent 3fa3722641
commit 2837bfd9fa
3 changed files with 2026 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

167
samples/cpp/erfilter.cpp
View File

@@ -16,9 +16,83 @@
using namespace std;
using namespace cv;
void er_draw(Mat &src, Mat &dst, ERStat& er);
void show_help_and_exit(const char *cmd);
void groups_draw(Mat &src, vector<Rect> &groups);
void er_draw(Mat &src, Mat &dst, ERStat& er);
void er_draw(Mat &src, Mat &dst, ERStat& er)
int main(int argc, const char * argv[])
{
if (argc < 2) show_help_and_exit(argv[0]);
Mat src = imread(argv[1]);
// Extract channels to be processed individually
vector<Mat> channels;
computeNMChannels(src, channels);
int cn = (int)channels.size();
// Append negative channels to detect ER- (bright regions over dark background)
for (int c = 0; c < cn-1; c++)
channels.push_back(255-channels[c]);
// Create ERFilter objects with the 1st and 2nd stage default classifiers
Ptr<ERFilter> er_filter1 = createERFilterNM1(loadClassifierNM1("trained_classifierNM1.xml"),8,0.00025,0.13,0.4,true,0.1);
Ptr<ERFilter> er_filter2 = createERFilterNM2(loadClassifierNM2("trained_classifierNM2.xml"),0.3);
vector<vector<ERStat> > regions(channels.size());
// Apply the default cascade classifier to each independent channel (could be done in parallel)
for (int c=0; c<(int)channels.size(); c++)
{
er_filter1->run(channels[c], regions[c]);
er_filter2->run(channels[c], regions[c]);
}
// Detect character groups
vector<Rect> groups;
erGrouping(channels, regions, groups);
// draw groups
groups_draw(src, groups);
imshow("grouping",src);
waitKey(-1);
// memory clean-up
er_filter1.release();
er_filter2.release();
regions.clear();
if (!groups.empty())
{
groups.clear();
}
}
// helper functions
void show_help_and_exit(const char *cmd)
{
cout << endl << cmd << endl << endl;
cout << "Demo program of the Extremal Region Filter algorithm described in " << endl;
cout << "Neumann L., Matas J.: Real-Time Scene Text Localization and Recognition, CVPR 2012" << endl << endl;
cout << " Usage: " << cmd << " <input_image> " << endl;
cout << " Default classifier files (trained_classifierNM*.xml) must be in current directory" << endl << endl;
exit(-1);
}
void groups_draw(Mat &src, vector<Rect> &groups)
{
for (int i=groups.size()-1; i>=0; i--)
{
if (src.type() == CV_8UC3)
rectangle(src,groups.at(i).tl(),groups.at(i).br(),Scalar( 0, 255, 255 ), 3, 8 );
else
rectangle(src,groups.at(i).tl(),groups.at(i).br(),Scalar( 255 ), 3, 8 );
}
}
void er_draw(Mat &src, Mat &dst, ERStat& er)
{
if (er.parent != NULL) // deprecate the root region
@@ -29,92 +103,3 @@ void er_draw(Mat &src, Mat &dst, ERStat& er)
}
}
int main(int argc, const char * argv[])
{
vector<ERStat> regions;
if (argc < 2) {
cout << "Demo program of the Extremal Region Filter algorithm described in " << endl;
cout << "Neumann L., Matas J.: Real-Time Scene Text Localization and Recognition, CVPR 2012" << endl << endl;
cout << " Usage: " << argv[0] << " input_image <optional_groundtruth_image>" << endl;
cout << " Default classifier files (trained_classifierNM*.xml) should be in ./" << endl;
return -1;
}
Mat original = imread(argv[1]);
Mat gt;
if (argc > 2)
{
gt = imread(argv[2]);
cvtColor(gt, gt, COLOR_RGB2GRAY);
threshold(gt, gt, 254, 255, THRESH_BINARY);
}
Mat grey(original.size(),CV_8UC1);
cvtColor(original,grey,COLOR_RGB2GRAY);
double t = (double)getTickCount();
// Build ER tree and filter with the 1st stage default classifier
Ptr<ERFilter> er_filter1 = createERFilterNM1(loadClassifierNM1("trained_classifierNM1.xml"));
er_filter1->run(grey, regions);
t = (double)getTickCount() - t;
cout << " --------------------------------------------------------------------------------------------------" << endl;
cout << "\t FIRST STAGE CLASSIFIER done in " << t * 1000. / getTickFrequency() << " ms." << endl;
cout << " --------------------------------------------------------------------------------------------------" << endl;
cout << setw(9) << regions.size()+er_filter1->getNumRejected() << "\t Extremal Regions extracted " << endl;
cout << setw(9) << regions.size() << "\t Extremal Regions selected by the first stage of the sequential classifier." << endl;
cout << "\t \t (saving into out_second_stage.jpg)" << endl;
cout << " --------------------------------------------------------------------------------------------------" << endl;
er_filter1.release();
// draw regions
Mat mask = Mat::zeros(grey.rows+2,grey.cols+2,CV_8UC1);
for (int r=0; r<(int)regions.size(); r++)
er_draw(grey, mask, regions.at(r));
mask = 255-mask;
imwrite("out_first_stage.jpg", mask);
if (argc > 2)
{
Mat tmp_mask = (255-gt) & (255-mask(Rect(Point(1,1),Size(mask.cols-2,mask.rows-2))));
cout << "Recall for the 1st stage filter = " << (float)countNonZero(tmp_mask) / countNonZero(255-gt) << endl;
}
t = (double)getTickCount();
// Default second stage classifier
Ptr<ERFilter> er_filter2 = createERFilterNM2(loadClassifierNM2("trained_classifierNM2.xml"));
er_filter2->run(grey, regions);
t = (double)getTickCount() - t;
cout << " --------------------------------------------------------------------------------------------------" << endl;
cout << "\t SECOND STAGE CLASSIFIER done in " << t * 1000. / getTickFrequency() << " ms." << endl;
cout << " --------------------------------------------------------------------------------------------------" << endl;
cout << setw(9) << regions.size() << "\t Extremal Regions selected by the second stage of the sequential classifier." << endl;
cout << "\t \t (saving into out_second_stage.jpg)" << endl;
cout << " --------------------------------------------------------------------------------------------------" << endl;
er_filter2.release();
// draw regions
mask = mask*0;
for (int r=0; r<(int)regions.size(); r++)
er_draw(grey, mask, regions.at(r));
mask = 255-mask;
imwrite("out_second_stage.jpg", mask);
if (argc > 2)
{
Mat tmp_mask = (255-gt) & (255-mask(Rect(Point(1,1),Size(mask.cols-2,mask.rows-2))));
cout << "Recall for the 2nd stage filter = " << (float)countNonZero(tmp_mask) / countNonZero(255-gt) << endl;
}
regions.clear();
}