Image registration in noisy environment using particle swarm optimization

Image registration is a process of overlaying multiple images of the same scene taken from different viewpoints or by different sensors or at different times. The registration geometrically aligns multiple images with respect to a reference image. It has wide application in remote sensing, superresolution, medicine, cartography (map updating), and in computer vision (target localization, automatic quality control) etc. Traditional methods for image registration are sensitive to image degradations such as variations in noise, blur or illumination. In this paper an accurate rigid image registration technique based on Particle Swarm Optimization (PSO) is proposed which is robust to additive noise. It is observed that proposed algorithm shows same performance at different level of noise power. Experimental results confirm the claims of the algorithm.