Abstract: The tongue diagnosis is an important diagnostic method in Traditional Chinese Medicine (TCM). Human tongue is one of the important organs which contain the information of health status. Image segmentation has always been a fundamental problem and complex task in the field of image processing and computer vision. Its goal is to change the representation of an image into something that is more meaningful and easier to analyze. In other words, it is used to partition a given image into several parts, each of them the intensity is homogeneous. In order to achieve an automatic tongue diagnostic system, an effective segmentation method for detecting the edge of tongue is very important. We mainly compare the two steps Chan Vese Method and Canny algorithm for edge segmentation. The segmentation using Canny algorithm may produce many false edges; thus, it is not a good edge detection operator. But, for our two steps Chan Vese method can automatically select the seed regions first and then segments the tongue body successfully. Therefore, it may be useful in clinical automated tongue diagnosis system. Experiments show the results of these techniques.