An efficient medical image registration method based on mutual information model

Multimodal image registration has played an increasingly important role in medical imaging. A new approach to the problem of multimodality medical image registration is proposed, using a basic concept from feature information, mutual information, and relative entropy, as a new matching criterion. Using Harris corner detection algorithm for image feature detection,and feature characteristics are taken into account to compute a joint probability distribution of corresponding edge points in two images. Mutual information based on this function is minimized to find the best alignment parameters. Finally, the translation parameters are calculated by Powell optimization algorithm. The experimental results demonstrate the effectiveness of the proposed registration scheme.