Hybrid particle swarm with differential evolution for multimodal image registration

In this paper, we propose an algorithm of hybrid particle swarm with differential evolution (DE) operator, termed DEPSO, to solve the problem of multimodal image registration. This algorithm combines the robustness of entropy based measures and the search power of the DEPSO which provides the bell-shaped mutations with consensus on the population diversity, while keeps the particle swarm dynamics. The main idea is to find the best transformation that superimposes two multimodal images by maximizing the mutual information value through the DEPSO. We show that this algorithm, besides its simplicity, provides a robust and efficient way to rigidly register multimodal images in various situations.