Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
I want to detect squares using OpenCV. Here’s the image I’m trying to process:
There are eleven colored squares, and the example in OpenCV at https://code.ros.org/trac/opencv/browser/trunk/opencv/samples/c/squares.c?rev=1429 won’t detect all the squares. What can I do to detect all of them?
Optimize the code according to the case.Study and play with it.
One other way to detect squares is to use a signature-based generalized hough voting framework. Create a square signature and then convolute it with the image. Accumulate the results in the “Hough Space” and find maxima (e.g. mean-shift).
To achieve scale-invariance, build a multi-scale signature.
Or you could try template matching. Use dense sampling or a keypoint detector (e.g. harris edge ), and build a spatial codebook using some descriptor (e.g. SURF,ORB). Then, you can use a sliding window for matching by thresholding codebook distances.