The extraction of tongue area from digital photos is essential to an automatic tongue diagnostic system in traditional Chinese medicine. Simple segmentation methods couldn't be effective due to the weak edge of tongue and the details on the tongue's surface. In this paper, we propose a unique segmentation method based on the combination of the watershed transform and active contour model (ACM). The watershed transform is used to get the initial contour, and an active contour model, or "snakes", is used to converge to the precise edge. This method is proved to be effective and steady in experiments on tongue image.