Line detection in a binary image using opencv

Question

I am trying to detect the crossing lines in in the following binary image:

Using the HoughLine detection isn't producing the correct results

Any pointers or direction would be appreciated. Thanks

Answer 1

using the image directly as input, you will have to invert it (white = lines to detect).

I'll get those results with HoughLinesP

and if you dilate the inverted image once you get this result:

with this code:

int main()
{
    cv::Mat color = cv::imread("../inputData/LineDetectionCrosses.png");
    cv::Mat gray;

    // convert to grayscale
    cv::cvtColor(color, gray, CV_BGR2GRAY);

    cv::Mat mask = 255-gray;

    //cv::dilate(mask, mask, cv::Mat());

    // detect HoughLinesP
    std::vector<cv::Vec4i> lines;
    cv::HoughLinesP(mask, lines, 1, CV_PI/2880, 50, 300, 10 );
    for( size_t i = 0; i < lines.size(); i++ )
    {
        cv::Vec4i l = lines[i];
        cv::line( color, cv::Point(l[0], l[1]), cv::Point(l[2], l[3]), cv::Scalar(0,0,255), 3, CV_AA);
    }

    // display results
    cv::imshow("mask",mask);
    cv::imshow("output", color);
    cv::waitKey(0);

}

but if it was my project, I'd probably try to detect the circles first and find/extract lines with known center point!