Texture-Based Tongue Classification And Its Application

Recently, Tongue Diagnosis has gained more and more affirmation and application from domestic to abroad because of its simplicity and immediacy. Meanwhile, as the development of the modern science and technology, it is important and valuable to the development and application of Tongue Diagnosis to combine the computer technology such as digital image process and pattern recognition and Tongue Diagnosis in order to avoid the defect of inquantitativeness and subjectiveness of Tongue Diagnosis. In this dissertation, we research classification of the states of tongue by texture analysis method, and we do research on the automatic diagnosis of diseases and symptoms too.In this dissertation, towards different states of tongue, we define different tongue pathology areas, propose relevant sub-images selection methods and gets research objects; according different states of tongue, this dissertation compares different ways to extract texture features and classifies states of tongue well using the most appropriate features, making preparation for the auto-diagnosis of symptoms and diseases; the dissertation sets up a texture-based symptom diagnosis model and diagnoses asthenia and sthenia syndrome and external and internal syndrome more accurately ;moreover, based on expert knowledge, this dissertation uses texture, colors and shape information of tongue images, to survey diagnosis of some diseases.First, the red prickles classification is studied in the dissertation. According to the observation and analysis of tongue image with red prickles, Gabor wavelet and wavelet are employed to extract texture features, then we do some classification experiments to compare the classification result of the two methods, and the results prove that the Gabor wavelet method can work well. Second, we do research on asthenia syndrome and sthenia syndrome. We first select sub-images from tongue image along the polygonal edge of the tongue, then based on the analysis of the texture properties of the sub-images, gray level co-matrix is used to extract features. The classification precision with theses features is higher.Third, the thickness of tongue coating is researched in the dissertation. we...