A Novel Computerized Method Based on Support Vector Machine for Tongue Diagnosis

Abstract

The tongue diagnosis is an important diagnostic method in traditional chinese medicine (TCM). In this paper, we present a novel computerized tongue inspection method based on support vector machine (SVM). First, two kinds of quantitative features, chromatic and textural measures, are extracted from tongue images by using popular image processing techniques. Then, support vector machine and Bayesian network are employed to build the mapping relationships between these features and diseases, respectively. Finally, we present a comparison between SVM and BN classification. The experiment results show that we can use SVM to classify the tongue images more excellently and get a relative reliable prediction of diseases based on these features.