A New Optimization Approach Using Smoothed Images Based on ACO for Medical Image Registration

Abstract

This paper studies on image registration using Ant Colony Optimization technique of the medical images. Ant Colony Optimization algorithm has ability of global optimization and facilitates quick search of optimal parameters for image registration. In this paper, a modified Ant Colony Optimization algorithm on preprocessed images is proposed to improve the accuracy in terms of PSNR (peak signal to noise ratio), Entropy and convergence speed. Preprocessing of images is adopted to remove noise so that extracted features provide more accurate and precise information about the image and results are more suitable for further analysis. The experimental results demonstrate the performance of proposed methodology as compared with traditional approaches as very promising.