Multimodal Image Registration using Contourlet Transform

Abstract: Registration is the determination of a geometrical transformation that aligns points in one view of an object with corresponding points in another view of that object or another object. Image Registration deals with the matching of two images. Relationship between type of distortion and the type of image registration is the most important task. Image registration is becoming a crucial step in most image processing tasks. It is a key technology in computer vision, remote sensing, image processing, medical image analysis and other fields. The main objective is to match two or multiple images got at different times by different sensors or different angle. This is the fundamental task in image processing which can be used to match two or more pictures taken at different time or from different sensors or from different viewpoints. Various transforms can be used for the purpose. Medical imaging is the technique and process used to create images of the human body for clinical purposes seeking to reveal, diagnose medical science. It is often perceived to designate the set of techniques that noninvasively produce images of the internal aspect of the body. Medical image registration is to find a spatial transformation to match all the anatomical points and diagnostic points on the image. This paper presents a new technique for registration of multi modal images using mutual information.

Keywords: Image Registration; Feature detection; Contourlet transform (CT); Mutual Information