A Novel Approach for Tongue Image Extraction Based on Combination of Color and Space Information

Tongue inspection is one of the most important methods of Traditional Chinese Medicine diagnoses. Traditional tongue inspection mainly depends on observations to tongue substance, tongue coating and tongue pattern and diagnostic experience of the doctors. Diagnostic results are restricted by doctor's knowledge level, their experience as well as other subjective factors and affected by the light and temperature of external environment. In order to solve this problem, we should combine Traditional Chinese Medicine experts' diagnostic experience with modern information technologies, check and analyze tongues quantitively and objectively, and make scientific diagnoses. However, to realize quantitive and objective tongue checks and analyses, extracting tongue from the mouth and face is the first important step. A novel approach for tongue image extraction is proposed to solve this problem in this article. It utilizes greedy rules to combine color information and space information to search object tongue area in the 2-dimensional sample space, and the start position of the search, intensity threshold and hue threshold are selected fully automatically. Comparison experiment results indicate that this method can extract tongue from the raw image effectively and we have made a breakthrough in extracting the tongues with thick coating. Moreover, the tongue images extracted by this method can be used as valid bases for the later quantitive analyses.