Study Of Medical Image Segmentation Based On Model

Image segmentation is an important part of image processing and image analysis, the purpose is to extract the region of interest in the image, and make it be close to anatomical structure, so as to provide the reliable basis for the subsequent image analysis. The structure of medical image organization is complex, and medical image has the characteristics of irregular shape and heterogeneity, it is difficult to achieve the ideal segmentation using the traditional methods.This article studies medical image segmentation based on active contour model, the model can be used in many fields such as image processing, computer vision. In this article, we firstly review the existing image segmentation methods, and analyze their advantages and disadvantages. Then active contour model and level set method are introduced, the traditional Chan-Vese model has a large amount of calculation and the speed is slow, according to the medical image characteristic, the paper put forward a segmentation algorithm improved based on the level set, introducing the local information based on global information of the image reduces the curve evolution iterations and improves the segmentation speed. The two-dimensional image segmentation is extended to semi-automatic segmentation of medical image sequence, the current segmentation is taken as initial contour of the next image using the similarity between two images, which reduces random from artificial selection of initial contour curve and improves the efficiency of image segmentation.The correlation algorithms are realized in MATLAB, and the experiments verify the reliability and accuracy of the algorithms, the method can extract the object interested in the image quickly and exactly, it is an ideal method for medical image segmentation.