Registration and optimization in entropic graphs using branch skeleton features

In image registration process, it is necessary to find the similarity of the images and the translation, rotation and scaling transformation parameter values that maximize the similarity between the two images. When the similarity measure and related parameters are calculated, information theory based entropic graphs can be used. In this study, similarity and optimization measures are compared on different entropic graphs. It has been seen that skeleton branch feature points to build entropic graphs give successful results.