omr
omr copied to clipboard
perspective transform is not done correctly
Hi, Instead of detecting the corners as in the picture here, the calculation is made over the corners of the largest rectangle containing the contours (corner.png). How can we do this so that it detects the corners of each corner.png. I think we should develop this project. this project is one of the nice omr (made with python) projects on github. https://camo.githubusercontent.com/b3272c76cfe1dbd447255e330e5e7f8d4425621b26853b2724455b6b30502554/687474703a2f2f692e696d6775722e636f6d2f346e39664b46462e706e67