Exploratory tongue color analysis with manifold learning

With the increasing of tongue image data, exploratory data analysis would provide an effective means to obtain knowledge and to verify the correctness of several traditional tongue diagnosis findings. This paper proposes an exploratory tongue color analysis method by using the manifold learning technique. We further present an evaluation criterion to determine the optimal parameters. With the help of the evaluation criterion, we choose the value of the manifold learning algorithm and determine the appropriate color space for exploratory tongue color analysis. Experimental results show that the proposed method is effective in visualizing typical tongue color types and the trend of normal tongue color to abnormal color.