It’s pretty simple to extract SURF descriptors using cv2 and Python. You just need to initialize the descriptor and apply it, using something along the lines of:
extractor = cv2.DescriptorExtractor_create("SURF")
But what about the OpponentColorDescriptorExtractor as mentioned here, towards the bottom of the page?
I have seen C++ code to create an Opponent Color extractor via this blog post, but I cannot find any Python bindings to go with it.
Does anyone know how to create an Opponent Color descriptor extractor using Python bindings?
I should have read the docs a little better. All you need to do is prepend opponent to the descriptor: