I'm trying to compare 2 images that are taken from a digital camera. Since there may be movement on the camera, I want to first make the pictures "match" and then compare (using some distant function).
To match them, I'm thinking about cropping the second picture and using SIFT to find it inside the first picture... it will probably have a small difference on scale/translation/rotation so then I'd need to find the transformation matrix that converts image 1 to image 2 (based on points found by SIFT)
any ideas on how to do that (or I guess that's a common problem that may have some opensource implementation?)?
thanks
If the movement is small or mostly translational it could be more easy to use phase correlation, or just compare Fourier moments. http://en.wikipedia.org/wiki/Phase_correlation Also check this question How to use SIFT algorithm to compute how similiar two images are?
来源：https://stackoverflow.com/questions/1612037/comparing-images-using-sift