An automatic tongue detection and segmentation framework for computer-aided tongue image analysis

Traditional Chinese Medicine (TCM) has a long history and has been recognised as a popular alternative medicine in western countries. Tongue diagnosis is a significant procedure in computer–aided TCM, where tongue image analysis plays a dominant role. In this paper, we propose a fully automatic tongue detection and segmentation framework that includes a Principal Component Analysis (PCA)–based tongue detection algorithm as well as a new hybrid tongue segmentation algorithm that fully exploits the robustness of the Mean Shift algorithm and the efficiency of the Canny Edge Detection algorithm, together with the outlier removal capability of the Tensor Voting algorithm. Compared with other existing methods, our method is fully automatic without the need of adjusting parameters for different images and do not need any initialisation.