JSEG Based Color Separation of Tongue Image in Traditional Chinese Medicine

The process of color separation of tongue image in traditional Chinese medicine (TCM) is decomposed into two steps: region partition and color classification. In the first step, a partition method based on JSEG is proposed to obtain homogenous regions in the tongue. In the second step, a priori template and some standard color patches are designed to assist the classification according to a priori knowledge from the TCM experts, where the nearest neighbour classifier is applied for color classification. The experimental results show that the proposed approach is greatly promising to computerized tongue diagnosis.

[1]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[2]  B. S. Manjunath,et al.  Unsupervised Segmentation of Color-Texture Regions in Images and Video , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Jae-Hyung Jang,et al.  Development of the digital tongue inspection system with image analysis , 2002, Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology.

[4]  Chuang-Chien Chiu,et al.  A novel approach based on computerized image analysis for traditional Chinese medical diagnosis of the tongue , 2000, Comput. Methods Programs Biomed..

[5]  David G. Stork,et al.  Pattern Classification , 1973 .