Tongue Image Segmentation via Color Decomposition and Thresholding

Tongue diagnosis is one of the most important diagnosis methods in Traditional Chinese Medicine (TCM). Tongue image segmentation is a crucial step of developing automatic tongue diagnosis system. After exploring the characteristics of different color models, we propose a tongue image segmentation method via thresholding in HSI and RGB color models. The proposed method first determines initial tongue body region via transforming and thresholding on the hue component of HSI (Hue, Saturation and Intensity) color model. Then, image thresholding on the red component of RGB color model is conducted to find the gap region between the tongue body root and the upper lip. Finally, the initial tongue body region is refined by removing fake object regions such as the upper lip with the help of morphological operations on the above gap region to obtain final tongue image segmentation result. Experiment results on a variety of tongue images demonstrate the effectiveness of the proposed method.