An Artificial Bee Colony Algorithm Hybrid with Differential Evolution for Multi-temporal Image Registration

Image registration is a hot topic in the field of image processing, the aim of which is to find the best spatial transformation between two images by optimizing a similarity metric. Mutual information, as an effective and reliable criterion, is used in this paper. Local optimization technique always fail in this process because the function of this metric with respect to transformation parameters is usually non-convex and irregular, thus, global optimization method is required. This paper proposes an improved artificial bee colony algorithm hybrid with a differential evolution for image registration. Experiments are conducted to optimize the mutual information similarity metric in comparison with several evolutionary algorithms, results indicate that the hybrid algorithm produces more accuracy registration results.