Multi-resolution medical image registration based on generalized mutual information

In this paper, a multi-resolution medical image registration algorithm has been proposed that bases Renyi entropy generalized mutual information, which uses the different characteristics removing some unwanted local optimum and having the depth of the basin of attraction. We use the particle swarm optimization algorithm to locate the measure function near the local extremes in low resolution images. Then we take the local extremes as initial point and use the Powell optimization algorithm to search for the global optimal solution in high resolution images. By simulating the medical images data, the experimental results have proven that this algorithm can not only get better precision but also accelerate the convergence rate.