The tongue diagnosis is an important diagnostic method in Traditional Chinese Medicine (TCM). Human tongue is one of the important organs which contains 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 another one with more meaningful which is 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 is necessary for detecting the edge of tongue. We mainly address by using different colormap for color segmentation and Two-Step-Chan Vese Method for edge detection. The use of colormap for color segmentation will help the initial guess of boundary contour to detect the edges of tongue body by Chan Vese Method. Therefore, it may be useful for developing a clinical automated tongue diagnosis system. The results of experiments implement the proposed methods.
