Image Registration Using Mexican-Hat Wavelets and Invariant Moments

Image registration is the process of determining the transformation which best matches, according to some similarity measure, two images or more of the same scene taken at different times or from different viewpoints so that corresponding pixels in the two images correspond to the same physical region of the scene being imaged. It is an essential step for a great variety of applications such as computer vision, stereo navigation, medical image analysis, pattern recognition etc. In this paper, an algorithm is proposed which consists of Feature point extraction, based on scale-interaction of Mexican-hat wavelets, Feature correspondence between the extracted features points using invariant Zernike moments of neighborhoods centered on feature points, and transformation parameter estimation and mapping.