OpenCV C++: How to find all the circles in an image - c++

Question

Hi I am trying to find all the circles in the following image and Identify the defect.
this is my code:
static void findCircles2(const Mat& image)
{
vector<Vec3f> circles;
int thresh1 = 5;
Mat pyr, timg, gray0(image.size(), CV_8U), gray;
pyrDown(image, pyr, Size(image.cols/2, image.rows/2));
pyrUp(pyr, timg, image.size());
for( int c = 0; c < 3; c++ )
{
int ch[] = {c, 0};
mixChannels(&timg, 1, &gray0, 1, ch, 1);
Canny(gray0, gray, 0, thresh1, 5);
//dilate(gray, gray, Mat(), Point(-1,-1));
gray = gray0 >= (1)*255/N;
gray = gray0 >= (2)*255/N;
gray = gray0 >= (6)*255/N;
namedWindow( "Hough Circle Transform Demo 1", CV_WINDOW_AUTOSIZE );
imshow( "Hough Circle Transform Demo 1", gray );
waitKey(0);
HoughCircles( gray, circles, CV_HOUGH_GRADIENT, 1, gray.rows/8, 200, 100, 0, 0 );
cout<<"size of circles: "<<circles.size()<<endl;
for( size_t i = 0; i < circles.size(); i++ )
{
Point center(cvRound(circles[i][0]), cvRound(circles[i][1]));
int radius = cvRound(circles[i][2]);
circle( gray, center, 3, Scalar(0,255,0), -1, 8, 0 );
circle( gray, center, radius, Scalar(0,0,255), 3, 8, 0 );
}
/// Show your results
namedWindow( "Hough Circle Transform Demo 2", CV_WINDOW_AUTOSIZE );
imshow( "Hough Circle Transform Demo 2", gray );
waitKey(0);
}
}
Picture:
however the code is unable to find anything, I played arround with the thresholds but it doesnt help. please advise.
Development platform: VS2010, Opencv version: 2.4.10

Answer 1

Because the circles are so small and not that standard, so you cann't just do HoughCircles on the binary image.
An alternative method is to findContours, then filter the contours by ratio between the value of contourArea and the value of minEnclosingCircle.