A spatio-frequency orientational energy based medical image fusion using non-sub sampled contourlet transform

Abstract

A novel medical image fusion method is proposed in this paper based on the non-subsampled contourlet transform (NSCT). Initially, the source images are decomposed through NSCT followed by the fusion of obtained low frequency sub images and high frequency sub images. The fusion of low frequency sub images is based on the angular consistency rule whereas the high frequency sub images are based on the dependencies of their energies. The proposed approach is compared with conventional approaches such as DWT, contourlet transform (CT), and some approaches based on NSCT over various test images. Performance evaluation is carried out visually and numerically. Both the visual and numerical results illustrate the effectiveness of proposed approach and also show the enhancement of proposed approach over conventional approaches.