Fast BlockMatching Registration with Entropy-based Similarity

This paper describes the implementation of a multidimensional block-matching nonrigid registration algorithm. The main features of the algorithm are its simplicity, its free form nature, the modularity of the similarity measure, which makes it possible using local entropy-based similarity measures and the avoidance of the optimization module. The algorithm implementation described in this paper is based on the method by Suarez et al. [5, 3]. This paper, which has already been submitted to the Insight Journal, is accompanied with the source code, input data, parameters and output data used for validating the algorithm described in it.