Detect semicircle in OpenCV

Question

I am trying to detect full circles and semicircles in an image. enter image description here

I am following the below mentioned procedure: Process image (including Canny edge detection). Find contours and draw them on an empty image, so that I can eliminate unwanted components (The processed image is exactly what I want). Detect circles using HoughCircles. And, this is what I get:

enter image description here

I tried varying the parameters in HoughCircles but the results are not consistent as it varies based on lighting and the position of circles in the image. I accept or reject a circle based on its size. So, the result is not acceptable. Also, I have a long list of "acceptable" circles. So, I need some allowance in the HoughCircle params. As for the full circles, it's easy - I can simply find the "roundness" of the contour. The problem is semicircles!

Please find the edited image before Hough transform enter image description here

Is it right that you CAN detect which edges (after canny and hough) in the image belong to circles/semi-circles? And your problem is, that Hough results' circle locations aren't good enough? What about fitting a parametric circle with all the circle edges (or at least 3 correct circle edge pixels)? (Three points define a circle!) ... to make that more robust you could use a RANSAC algorithm (inlier/outlier counting => huge missing parts = semi-circle). Didnt try it, but might work?!? — Micka
Thanks Micka! What you say about parametric circle is Hough Transform algorithm itself, isn't it? And if you see the results of Hough, more than 3 points lie on the detected circle! I have no clue about RANSAC, I will check it out — harsh
can you provide the edge image before computing/plotting hough circles? And did you try drawing the contours with less line-thickness? — Micka
ah, I see... HoughTransform uses canny internally, so the line-thickness is needed, but for full circles it would be better to fill the contour. — Micka
I see that I do not need to draw contours on a blank image. This is Canny + Gaussian blur. — harsh

Micka Micka · Accepted Answer · 2013-12-20T14:43:57

Use houghCircle directly on your image, don't extract edges first. Then test for each detected circle, how much percentage is really present in the image:

int main()
{
    cv::Mat color = cv::imread("../houghCircles.png");
    cv::namedWindow("input"); cv::imshow("input", color);

    cv::Mat canny;

    cv::Mat gray;
    /// Convert it to gray
    cv::cvtColor( color, gray, CV_BGR2GRAY );

    // compute canny (don't blur with that image quality!!)
    cv::Canny(gray, canny, 200,20);
    cv::namedWindow("canny2"); cv::imshow("canny2", canny>0);

    std::vector<cv::Vec3f> circles;

    /// Apply the Hough Transform to find the circles
    cv::HoughCircles( gray, circles, CV_HOUGH_GRADIENT, 1, 60, 200, 20, 0, 0 );

    /// Draw the circles detected
    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]);
        cv::circle( color, center, 3, Scalar(0,255,255), -1);
        cv::circle( color, center, radius, Scalar(0,0,255), 1 );
    }

    //compute distance transform:
    cv::Mat dt;
    cv::distanceTransform(255-(canny>0), dt, CV_DIST_L2 ,3);
    cv::namedWindow("distance transform"); cv::imshow("distance transform", dt/255.0f);

    // test for semi-circles:
    float minInlierDist = 2.0f;
    for( size_t i = 0; i < circles.size(); i++ ) 
    {
        // test inlier percentage:
        // sample the circle and check for distance to the next edge
        unsigned int counter = 0;
        unsigned int inlier = 0;

        cv::Point2f center((circles[i][0]), (circles[i][1]));
        float radius = (circles[i][2]);

        // maximal distance of inlier might depend on the size of the circle
        float maxInlierDist = radius/25.0f;
        if(maxInlierDist<minInlierDist) maxInlierDist = minInlierDist;

        //TODO: maybe paramter incrementation might depend on circle size!
        for(float t =0; t<2*3.14159265359f; t+= 0.1f) 
        {
            counter++;
            float cX = radius*cos(t) + circles[i][0];
            float cY = radius*sin(t) + circles[i][1];

            if(dt.at<float>(cY,cX) < maxInlierDist) 
            {
                inlier++;
                cv::circle(color, cv::Point2i(cX,cY),3, cv::Scalar(0,255,0));
            } 
           else
                cv::circle(color, cv::Point2i(cX,cY),3, cv::Scalar(255,0,0));
        }
        std::cout << 100.0f*(float)inlier/(float)counter << " % of a circle with radius " << radius << " detected" << std::endl;
    }

    cv::namedWindow("output"); cv::imshow("output", color);
    cv::imwrite("houghLinesComputed.png", color);

    cv::waitKey(-1);
    return 0;
}

For this input:

enter image description here

It gives this output:

enter image description here

The red circles are Hough results.

The green sampled dots on the circle are inliers.

The blue dots are outliers.

Console output:

100 % of a circle with radius 27.5045 detected
100 % of a circle with radius 25.3476 detected
58.7302 % of a circle with radius 194.639 detected
50.7937 % of a circle with radius 23.1625 detected
79.3651 % of a circle with radius 7.64853 detected

If you want to test RANSAC instead of Hough, have a look at this.

Detect semicircle in OpenCV

5 Answers