alexcerry's profile - activity

@Callidi you are using this camera https://cn.bing.com/images/search?vie... ?

Hi.

edit1:

I try to get correct result. But its take time to adjust the correct parameter by the way you can check this out.

edit2:

Now i think result almost correct. after using canny and gaussian blur.

    int main()
    {
        cv::Mat img = cv::Mat::zeros(480, 640, CV_8UC3);
        cv::circle(img, cv::Point(200, 200), 175, cv::Scalar(0XFF), 1);
    Mat gray;

    cvtColor(img, gray, CV_RGB2GRAY);

Canny(gray, gray, 0, 10);

GaussianBlur(gray, gray, Size(9, 9), 2, 2);
    std::vector<cv::Vec3f> circles;

    bool exit = false;

    Point global;

    for (int i = 1; i < 200; i++)
    {
        HoughCircles(gray, circles, CV_HOUGH_GRADIENT,1, 20,200, i);
        cout << i << endl;

        for (size_t j = 0; j < circles.size(); j++)
        {
            Point center(cvRound(circles[j][0]), cvRound(circles[j][1]));
            int rad = circles[j][2];
            if (center.x > 199 && center.x < 201 && circles.size() < 45 && rad > 174)
            {
                global = center;
                exit = true;
            }
        }
        if (exit == true)
        {
            break;
        }
    }


    if (global.x > 0)
    {
    // circle center
    circle(img, global, 3, Scalar(0, 255, 0), 5, 8, 0);
    // circle outline
    circle(img, global, 175, Scalar(0, 0, 255), 3, 8, 0);

    }

    imshow("jk", img);
    waitKey(0);

    return 0;


}

@berak Sir, My question where would i found good documentation about ANN_MLP opencv 2 or 3. And book? I tired to search about this. I cannot found any proper documentation. Thank you very much for good explanation about labels. what is the range of predict. if fparam1 and fparam2 is 1, 1. And do you have any email?