An Algorithm Multi-Resolution Medical Image Registration Based on Firefly Algorithm and Powell

Abstract

In order to solve the problem that the mutual information function is easy to fall into local optimal values because of much local extremism in the mutual information registration method, a multi-resolution medical image registration algorithm based on firefly algorithm and Powell is put forward in this paper. The normalized mutual information is used as the similarity measure in the algorithm, and the multi-resolution strategy based on wavelet transformation is adopted in the process of searching the best value. In the lower resolution image, the firefly algorithm is used for the imprecise registration result, And in the higher resolution image, the Powell algorithm is adopted for the better registration result. The experimental results show that this algorithm can effectively overcome the problem that the mutual information function is easy to get into local optimal values and improve the precision of registration result obviously.