A Comparative study of the Image Registration Process on the Multimodal Medical Images

Abstract

Registration of image is the process of overlaying one or more image to a reference image of the same image taken at different time, from different view point or taken from different sensor device. The difference in between images is limelight due to different imaging condition which contains yielding in maximum similarity between the input and the reference images. In this paper, we perform a comparative study of the image registration process on the multimodal medical images by using different genetic algorithm. We use simple genetic algorithm, sharing genetic algorithm and GA combined with hill climbing algorithm using two selection criteria as roulette-wheel selection and tournament selection. Results shows that hill climbing algorithm is a local search algorithm and its execution is fast.