Genetic algorithm as the main optimizer for medical image registration

Mutual information (MI) has proved to be a quite reliable tool to measure the similarity between two images when they are evolving through a registration algorithm. In this paper we present an improved registration algorithm based on MI similarity measure, incorporating Genetic Algorithm (GA) capability of optimizing a multi-parameter optimization problem. For this to happen we made some modification to normalized form of MI. this modification made the MI of two images smoother with fewer fluctuation, enabling the GA to play the role of main optimizer. Slow moving and softening effects of some functions like natural logarithm is employed to hamper constant changes in MI between two images.