A novel tongue segmentation approach utilizing double geodesic flow

Abstract

Tongue diagnosis is one of the most important instruments in traditional Chinese medicine (TCM). While the tongue body segmentation acts an indispensable role in the automatic tongue diagnosis system. This study utilizes geodesic active contour model (level set function) to forward a novel segmentation approach. The tongue image is firstly divided into two parts according to the prior knowledge of tongue shape and location. Then, a double geodesic flow is applied, respectively, in which way both flows get their suitable evolutional modes. Experimental results show that the proposed approach can enhance the accuracy and practicability obviously, compared to the other state-of-arts works. © 2012 IEEE.