This paper addressed the standardization of tongue diagnosis using image processing approach. To analyze the tongue features locally, a tongue image is divided into a number of blocks with size 36 * 36. Two algorithms are developed to analyze the color and texture features of each block. A hierarchical K-means clustering algorithm in CIE L * u * v * color space is developed to determine the color cluster. Tongue textures are analyzed using Gabor wavelet opponent color features and the linear discriminant analysis. 121 tongue images are used to test the proposed algorithms and the results are encouraging.