Question

I successfully implemented the OpenCV square-detection example in my test application, but now need to filter the output, because it’s quite messy – or is my code wrong?

I’m interested in the four corner points of the paper for skew reduction (like that) and further processing …

Input & Output:

Original image:

click

Code:

double angle( cv::Point pt1, cv::Point pt2, cv::Point pt0 ) {
    double dx1 = pt1.x - pt0.x;
    double dy1 = pt1.y - pt0.y;
    double dx2 = pt2.x - pt0.x;
    double dy2 = pt2.y - pt0.y;
    return (dx1*dx2 + dy1*dy2)/sqrt((dx1*dx1 + dy1*dy1)*(dx2*dx2 + dy2*dy2) + 1e-10);
}

- (std::vector<std::vector<cv::Point> >)findSquaresInImage:(cv::Mat)_image
{
    std::vector<std::vector<cv::Point> > squares;
    cv::Mat pyr, timg, gray0(_image.size(), CV_8U), gray;
    int thresh = 50, N = 11;
    cv::pyrDown(_image, pyr, cv::Size(_image.cols/2, _image.rows/2));
    cv::pyrUp(pyr, timg, _image.size());
    std::vector<std::vector<cv::Point> > contours;
    for( int c = 0; c < 3; c++ ) {
        int ch[] = {c, 0};
        mixChannels(&timg, 1, &gray0, 1, ch, 1);
        for( int l = 0; l < N; l++ ) {
            if( l == 0 ) {
                cv::Canny(gray0, gray, 0, thresh, 5);
                cv::dilate(gray, gray, cv::Mat(), cv::Point(-1,-1));
            }
            else {
                gray = gray0 >= (l+1)*255/N;
            }
            cv::findContours(gray, contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE);
            std::vector<cv::Point> approx;
            for( size_t i = 0; i < contours.size(); i++ )
            {
                cv::approxPolyDP(cv::Mat(contours[i]), approx, arcLength(cv::Mat(contours[i]), true)*0.02, true);
                if( approx.size() == 4 && fabs(contourArea(cv::Mat(approx))) > 1000 && cv::isContourConvex(cv::Mat(approx))) {
                    double maxCosine = 0;

                    for( int j = 2; j < 5; j++ )
                    {
                        double cosine = fabs(angle(approx[j%4], approx[j-2], approx[j-1]));
                        maxCosine = MAX(maxCosine, cosine);
                    }

                    if( maxCosine < 0.3 ) {
                        squares.push_back(approx);
                    }
                }
            }
        }
    }
    return squares;
}

EDIT 17/08/2012:

To draw the detected squares on the image use this code:

cv::Mat debugSquares( std::vector<std::vector<cv::Point> > squares, cv::Mat image )
{
    for ( int i = 0; i< squares.size(); i++ ) {
        // draw contour
        cv::drawContours(image, squares, i, cv::Scalar(255,0,0), 1, 8, std::vector<cv::Vec4i>(), 0, cv::Point());

        // draw bounding rect
        cv::Rect rect = boundingRect(cv::Mat(squares[i]));
        cv::rectangle(image, rect.tl(), rect.br(), cv::Scalar(0,255,0), 2, 8, 0);

        // draw rotated rect
        cv::RotatedRect minRect = minAreaRect(cv::Mat(squares[i]));
        cv::Point2f rect_points[4];
        minRect.points( rect_points );
        for ( int j = 0; j < 4; j++ ) {
            cv::line( image, rect_points[j], rect_points[(j+1)%4], cv::Scalar(0,0,255), 1, 8 ); // blue
        }
    }

    return image;
}

Answer 1

This is a recurring subject in Stackoverflow and since I was unable to find a relevant implementation I decided to accept the challenge.

I made some modifications to the squares demo present in OpenCV and the resulting C++ code below is able to detect a sheet of paper in the image:

void find_squares(Mat& image, vector<vector<Point> >& squares)
{
    // blur will enhance edge detection
    Mat blurred(image);
    medianBlur(image, blurred, 9);

    Mat gray0(blurred.size(), CV_8U), gray;
    vector<vector<Point> > contours;

    // find squares in every color plane of the image
    for (int c = 0; c < 3; c++)
    {
        int ch[] = {c, 0};
        mixChannels(&blurred, 1, &gray0, 1, ch, 1);

        // try several threshold levels
        const int threshold_level = 2;
        for (int l = 0; l < threshold_level; l++)
        {
            // Use Canny instead of zero threshold level!
            // Canny helps to catch squares with gradient shading
            if (l == 0)
            {
                Canny(gray0, gray, 10, 20, 3); // 

                // Dilate helps to remove potential holes between edge segments
                dilate(gray, gray, Mat(), Point(-1,-1));
            }
            else
            {
                    gray = gray0 >= (l+1) * 255 / threshold_level;
            }

            // Find contours and store them in a list
            findContours(gray, contours, CV_RETR_LIST, CV_CHAIN_APPROX_SIMPLE);

            // Test contours
            vector<Point> approx;
            for (size_t i = 0; i < contours.size(); i++)
            {
                    // approximate contour with accuracy proportional
                    // to the contour perimeter
                    approxPolyDP(Mat(contours[i]), approx, arcLength(Mat(contours[i]), true)*0.02, true);

                    // Note: absolute value of an area is used because
                    // area may be positive or negative - in accordance with the
                    // contour orientation
                    if (approx.size() == 4 &&
                            fabs(contourArea(Mat(approx))) > 1000 &&
                            isContourConvex(Mat(approx)))
                    {
                            double maxCosine = 0;

                            for (int j = 2; j < 5; j++)
                            {
                                    double cosine = fabs(angle(approx[j%4], approx[j-2], approx[j-1]));
                                    maxCosine = MAX(maxCosine, cosine);
                            }

                            if (maxCosine < 0.3)
                                    squares.push_back(approx);
                    }
            }
        }
    }
}

After this procedure is executed, the sheet of paper will be the largest square in vector<vector<Point> >:

I’m letting you write the function to find the largest square. 😉