Rigid medical image registration for monomodal images

Abstract

Image registration is the fundamental task used to match two or more partially overlapping images taken at different times, from different sensors, or from different viewpoints. It is a technique useful in integrating information from different sources. Image registration techniques can be based upon image gray-scale or image features. Feature based registration gives a coarse result. Thus, using some intensity based method, fine or accurate registration is obtained. This paper presents a registration method for medical images based on contour lines of images and mutual information. First of all, a coarse registration is obtained using contour lines of images obtained from canny detector and then fine registration is accomplished using mutual information maximization.