Tongue Inspection Based On Image Processing Technology

Tongue diagnosis is an important diagnostical method of Traditional Chinese Medicine(TCM),and is one of the principal characteristics of traditional Chinese medicine. Tongue diagnosis also reflects physiological and pathological changes in the most sensitive indicators Chinese medicine clinics, also in the process, which is of great practical value in TCM. Therefore, Using image processing technology and combining the modern information technology and the clinic experience of TCM expert to realize the impersonality and standardization of tongue diagnosis of TCM is the only way of TCM development.In the tongue diagnosis, the tongue image of patient can be obtained by using digital instrument, for example, digital canmera. Automatic interested region segmentation must be carried out before the tongue image processing. It makes the segmentation of tongue image an important part between image acquiring and image processing. Quality of the segmentation will affect the subsequent work of tongue analysis directly. According to the characteristics of tongue image, this paper presents a new segmentation algorithm based on Mean Shift. The algorithm can use the spatial characteristic, effectively eliminate interference, and achieved good segmentation effect.In the study of the Mean Shift algorithm, this algorithm can be found further marking some part of special tongue, thereupon this paper presents a new recognition algorithm based on the Mean Shift in recognizing the corrupt and greasy tongue fur. Gained majority corrupt and greasy tongue fur via Mean Shift and quantitative analysis. The color and the texture analysis are the observation of the tongue aspects, however continuously the Chinese medicine theory quite has been fuzzy to these aspect definition and the classification. Therefore, this paper unifies traditional the Chinese medicine theory to fuse it the tongue color in the distinction, transforms the image to the improvement HSI color space and the Maxwell right angle triangle chromaticity space, divides the threshold value using color space each channel, carries on to the tongue color classifies. In the tongue texture characteristic recognition, this paper proposed the texture spectrum characteristic and the Fourier energy method, will obtain the characteristic value application of Rough Set theory will carry on the reduction and the establishment weight, thus will carry on the quantitative analysis. Through the experiment, the algorithm which this paper proposed to the identified greasy tongue coating recognition rate of accuracy above 75%, to the tongue color classification rate of accuracy above 85%, to the tongue image texture classification rate of accuracy above 80%, has the very high practical value, and point out a new path and direction for the further study of the objective tongue inspection of TCM.