Color Active Contour Models Based Tongue Segmentation in Traditional Chinese Medicine

Automated tongue image segmentation in tongue diagnosis system of traditional Chinese medicine is difficult due to two factors: There are lots of pathological details on the surface of tongue, and the shapes of tongue bodies are quite different. By adequately considering color information of tongue images, knowledge-based initial tongue body boundary detection and a color gradient are introduced into the gradient vector flow snake. The roughly detected tongue body boundary is employed to lead the usage of color gradient and the convergence of snake. The experiments results show robustness and accuracy of the algorithm. This work establishes a solid foundation for feature analysis of tongue diagnosis.