Renyi divergence and non-deterministic subsampling in Rigid Image Registration

Abstract

The successful application and reported robustness of Mutual Information both in rigid and nonrigid image registration over the last decades gave rise to an ongoing research on other information based similarity metrics emanating from Renyi Divergence. To the best of our knowledge however, this is the first paper studying the effects of Renyi parameter in combination with a subsampling factor in image registration accuracy. To this end, a series of experiments are presented with respect to the effect of Renyi's parameter and the subsampling factor in registration accuracy. Our results show that the increase of the Renyi parameter and the percentage of the pixels used leads, on average, to the reduction of the registration error.