The retrieval of the medical tongue images based on color analysis

Tongue diagnosis is one of the important topics in the field of Chinese traditional medicine (TCM), and color is the basic element of tongue image, it has important diagnostic value. This paper presents a novel approach to extract color feature of tongue images. First, we use iterative method to extract initial main color and initial number of main color, then we adopt GLA(Generalized Loyd Algorithm) algorithm to get the histogram of main color. Experimental results show that the proposed method can improve the detection rate of lesion in tongue image relative to single feature retrieval.