OpenCV circle detection C# implementation -

i need c# , or opencv experts in making circle detection script more accurate.

in opencv circle detection accomplished called houghcircles algorithm or framework.
http://docs.opencv.org/doc/tutorials/imgproc/imgtrans/hough_circle/hough_circle.html

i using c# wrapper of opencv (for unity)
opencvforunity hughcircles
in turn directly based on official java wrapper of opencv.

my circle detection code follows (without opencv dependencies of course) i've attached 2 images can see results. changes needed improve results? i've included original 2 images reference.

using unityengine; using system.collections; using system; using opencvforunity;   public class houghcirclesample : monobehaviour{     point pt;     // use initialization     void start ()             {                         texture2d imgtexture = resources.load ("balls2_bw") texture2d;                          mat imgmat = new mat (imgtexture.height, imgtexture.width, cvtype.cv_8uc3);                          utils.texture2dtomat (imgtexture, imgmat);                         //debug.log ("imgmat dst tostring " + imgmat.tostring ());                          mat graymat = new mat ();                         imgproc.cvtcolor (imgmat, graymat, imgproc.color_rgb2gray);                          imgproc.canny (graymat, graymat, 50, 200);                           mat circles = new mat();          int minradius = 0;        int maxradius = 0;          // apply hough transform find circles          imgproc.houghcircles(graymat, circles, imgproc.cv_hough_gradient, 3, graymat.rows() / 8, 200, 100, minradius, maxradius);         debug.log ("circles tostring " + circles.tostring ());         debug.log ("circles dump" + circles.dump ());          if (circles.cols() > 0)         (int x = 0; x < math.min(circles.cols(), 10); x++)          {                 double[] vcircle = circles.get(0, x);                  if (vcircle == null)                     break;                  pt = new point(math.round(vcircle[0]), math.round(vcircle[1]));                 int radius = (int)math.round(vcircle[2]);                 // draw found circle                   core.circle(imgmat, pt, radius, new scalar(255, 0, 0), 1);              }    texture2d texture = new texture2d (imgmat.cols (), imgmat.rows (), textureformat.rgba32, false);                         utils.mattotexture2d (imgmat, texture);                          gameobject.getcomponent<renderer> ().material.maintexture = texture;                  }          } 

this code in c++, can convert c#.

i needed change param2 of houghcircle 200, resulting in:

houghcircles(graymat, circles, cv_hough_gradient, 3, graymat.rows / 8, 200, 200, 0, 0); 

which is

the accumulator threshold circle centers @ detection stage. smaller is, more false circles may detected. circles, corresponding larger accumulator values, returned first.

you should't feed houghcircles "canny-ed" image, since take care of this. use graymat without canny edge detection step applied.

results shown below. second 1 more tricky, because of light conditions.

here whole code. again, it's c++, may useful reference.

#include <opencv2/opencv.hpp> using namespace cv;  int main(){      mat3b src = imread("path_to_image");     mat1b src_gray;     cvtcolor(src, src_gray, cv_bgr2gray);      vector<vec3f> circles;     houghcircles(src_gray, circles, cv_hough_gradient, 3, src_gray.rows / 8, 200, 200, 0, 0);      /// draw circles detected     (size_t = 0; < circles.size(); i++)     {         point center(cvround(circles[i][0]), cvround(circles[i][1]));         int radius = cvround(circles[i][2]);         // circle center         circle(src, center, 3, scalar(0, 255, 0), -1, 8, 0);         // circle outline         circle(src, center, radius, scalar(0, 0, 255), 3, 8, 0);     }      imshow("src", src);     waitkey();      return 0; }