How to identify paper markers using OpenCV?

Question

I tried to find the best way to detect 4 black squares on paper and use them to isolate the paper in my own image.

Answer 1

It seems that your image has only 4 black squares, so you need to do the following:

• Convert Image to Gray
• At the doorstep
• Find black outlines (before doing this in OpenCV, you must invert your image, because by default, OpenCV finds white outlines)
• Scroll through these paths and find the bounding box.

• Make a check:

  A) The rectangle area is larger than some constant (in my solution it was 100 )

  B) The width / height of the rectangle is about 1.0 (in my soul it was [0.9, 1.1] )

The code:

Mat img = imread("test.jpg"), gray; vector<Vec4i> hierarchy; vector<vector<Point2i> > contours; cvtColor(img, gray, CV_BGR2GRAY); threshold(gray, gray, 100, 255, THRESH_BINARY); bitwise_not(gray, gray); findContours(gray, contours, hierarchy, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE); for(size_t i=0; i<contours.size(); i++) { Rect rect = boundingRect(contours[i]); double k = (rect.height+0.0)/rect.width; if (0.9<k && k<1.1 && rect.area()>100) { drawContours(img, contours, i, Scalar(0,0,255)); } } imshow("result", img); waitKey(); 

Result:

Also read this discussion. - you do not need these 4 squares to detect paper.