Multi-sensor image registration based-on local phase coherence

The major challenges in automatic multi-sensor image registration are the inconsistency in intensity or contrast patterns, and the exis-tence of partial or missing information between images. Here we propose a novel image registration method based on local phase co-herence features, which are insensitive to changes in intensity or contrast. Furthermore, a new objective function based on weighted mutual information is proposed, where less weight is given to the objects that have no correspondence between images. The proposed method has been tested on both synthetic and medical images and evaluated based on registration accuracy. Our experiments demon-strate good performance of the proposed approach with missing or partial data, with significant changes in contrast, and with the pres-ence of noise. Index Terms — image registration, local phase coherence, mu-tual information, weighted mutual information 1