Revision history [back]

I'd suggest warping images to the common coordinate system and then subtract warped results. You could use 2D some feature detector, for example, BRISK or SIFT, then calculate a homography matrix and transform one of images with it to another.

I'd suggest warping images to the common coordinate system and then subtract warped results. You could use any 2D some feature detector, for example, BRISK or SIFT, then calculate a homography matrix and transform one of images with it to another.

I'd suggest warping images to the common coordinate system and then subtract warped results. You could use any 2D feature detector, for example, BRISK or SIFT, then calculate a homography matrix and then use it to transform one of images with it to the coordinate system of another.

I'd suggest warping images to the common coordinate system and then subtract warped results. You could use any 2D feature detector, for example, BRISK or SIFT, then calculate a homography matrix and then use it to transform one of images to the coordinate system of another.

I'd suggest warping images to the common coordinate system and then subtract warped results. You could use detect 2D feature points with any 2D feature detector, for example, BRISK Harris corners, or BRISK, or SIFT, then calculate a homography matrix and then use it to transform one of images to the coordinate system of another.

Also, it would be useful to apply some filtering and morphology to make robust comparisons.