A Novel Medical Image Registration Algorithm Based on PSO and Wavelet Transformation Combined with 2v-SVM

Abstract

In order to realize fast, precise and robust image registration, we proposed a new registration method, which is based on image feature extraction by wavelet transform combined with 2v-SVM and particle swarm optimization (PSO) algorithm. We made the affine transform between the source image and the target image, took Mutual Information (MI) as the Similarity Metric and extracted the feature points of the two images by wavelet transform combined with 2v-SVM; finally we can obtain the optimal transform parameters using the PSO algorithm. Our experiment results show that the proposed registration algorithm is effectively and advantaged.