Color Image Segmentation And Its Application To Tongue Image Processing For TCM

With the development of medical science technology, basic diagnosis methods of Traditional Chinese Medicine (TCM) face demand of modernization. "Viewing" diagnosis, especially the tongue is important content of basic diagnosis methods of TCM. It can get the physiological function and pathology of the organism changes by means of observing the tongue and have very important meaning to make a definite diagnosis in earlier stage of a lot of diseases. However, traditional tongue diagnosis only depends on doctor's observation. It is difficult to make exact diagnosis because of the factor of personality. Therefore, 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 camera. 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. Region Of Interest (ROI) is used in pretreatment of tongue image segmentation in this paper. A new algorithm that can automatically detect the ROI with the method of image projection is proposed. After analyzing many existed algorithms of image segmentation and combining the characteristics of tongue image, a new algorithm that can choose threshold automatically is presented based on histogram in RGB space of color image. Because the processing in carried out in gray level, the complexity and data reduces notably. In addition. a method based on self-organizing feature map neural network for the region segmentation of tongue image is also presented in this paper. and its effectiveness is proved by experimental results. Finally. an open-source image library ofOpenCV is introduced. Based on VC+OpenCV platform, both the splitting-merging method with pyramid structure and region-growing method with gray level difference are realized in the segmentation of color tongue image. The introducing of the library reduces the complexity and can achieve satisfied result.