Open kwinkunks opened 9 years ago
I would probably try texture classification http://scikit-image.org/docs/dev/auto_examples/plot_glcm.html It should more or less easily separate: a) text b) data c) empty space around data
The alternative approach is corner/edge detection:
http://blog.ayoungprogrammer.com/2013/04/tutorial-detecting-multiple-rectangles.html?m=1 http://artsy.github.io/blog/2014/09/24/using-pattern-recognition-to-automatically-crop-framed-art/ http://vkedco.blogspot.ca/2012/08/edge-detection-with-python-pil.html
Right now you have to crop the borders off an image yourself, which is a pain because you have to go and find the pixel coordinates in GIMP or whatever.