A BAYESIAN TECHNIQUE FOR IMAGE CLASSIFYING REGISTRATION

We address a complex image registration issue arising when the dependencies between intensities of images to be registered are not spatially homogeneous. Such a situation is frequently encountered in medical imaging when pathology present in one of the images modifies locally intensity dependencies observed on normal tissues. Usual image registration models, which are based on a single global intensity similarity criterion, fail to register such images, as they are blind to local deviations of intensity dependencies. Such a limitation is also encountered in contrast enhanced images where t here exist multiple pixel classes having different properties of contrast agent absorption .Medical image registration is critical for the fusion of complementary information about patient anatomy and physiology, for the longitudinal study of a human organ over time and the monitoring of disease development or treatment effect, for the statistical analysis of a population variation in comparison to a so - called digital atlas, for image - guided therapy, etc. Segmentation of the various elements among the parti cles is very important to medical decision. In order to eliminate the background noises of images, we need pre - processing of images. After the pre - processing method, Bayesian classifier is used for classifying of particles in the image. Bayesian classifier is a powerful probabilistic graphical model that has been applied in computer vision. In this paper, we adapted some of the existing segmentation algorithms using Bayesian classifier and focused the effect of Bayesian classifier in segmentation algorithms