蚁群算法与粒子群算法结合的图像配准

Image registration based on mutual information is of high accuracy and high automatization .Hence, it has received much attention these years. Unfortunately, Mutual information function are often unsmooth. There are lots of local maximums, which has a large influence on optimization. In this paper, a hybrid algorithm combined by Ant Colony and PSO is proposed. In this method the mutual information is used as similarity measure and a hybrid algorithm combined by ant colony algorithm and PSO’s method as the search technique. Experiments show that this hybrid algorithm could efficiently restrain local maximums of mutual information function. Also the registration accruacy could be improved.