The improvement of the tooth-marked recognition method on the tongue images

Tongue diagnosis is widely used in Traditional Chinese Medicine (TCM). A tooth-marked tongue is an important objective index of the diagnosis of qi (yang) deficiency syndrome. In view of the existing problems of the method based on the tongue edge to determine the tooth-marked, this paper studies the improved method. Firstly it judges whether the top of tongue body has recessed area and then adopts the Graham algorithm to construct the convex hull of tongue to get accurate locating of tooth-marked. Secondly it chooses the optimal threshold of tooth-marked area pixel. The experiment results demonstrate the efficiency of the improved method.