Optimal multi-scale geometrie fusion based on non sub-sampled contourlet transform and modified central force optimization

Abstract

This paper introduces an optimization based contourlet image fusion approach in addition to a comparative study for the performance of both multi-resolution and multi-scale geometric effect on fusion quality. A new multi-scale fusion technique based on optimized Non Sub-sampled Contourlet Transform (NSCT) using the Modified Central Force Optimization (MCFO) and local contrast enhancement techniques is presented. The proposed algorithm has been evaluated subjectively and objectively using different quality metrics including average gradient, local contrast, standard deviation, edge intensity, entropy, PSNR, and QAB!F. Experimental results demonstrated that the proposed optimized NSCT using the MCFO technique and combined histogram matching and the adaptive histogram equalization has achieved a superior performance with extremely high values of average gradient, edge intensity, and standard deviation. Also, it introduces better local contrast, entropy, and a good quality factor. This produces much clear images and better visualization for different medical applications.