Features for automated tongue image shape classification
Inspection of the tongue is a key component in Traditional Chinese Medicine. Chinese medical practitioners diagnose the health status of a patient based on observation of the color, shape, and texture characteristics of the tongue. The condition of the tongue can objectively reflect the presence of certain diseases and aid in the differentiation of syndromes, prognosis of disease and establishment of treatment methods. Tongue shape is a very important feature in tongue diagnosis. A different tongue shape other than ellipse could indicate presence of certain pathologies. In this paper, we propose a novel set of features, based on shape geometry and polynomial equations, for automated recognition and classification of the shape of a tongue image using supervised machine learning techniques. We also present a novel method to correct the orientation/deflection of the tongue based on the symmetry of axis detection method. Experimental results obtained on a set of 303 tongue images demonstrate that the proposed method improves the current state of the art method. © 2012 IEEE.
geometric feature, machine learning, Medical biometrics, Tongue shape classification
Obafemi-Ajayi, Tayo, Ratchadaporn Kanawong, Dong Xu, Shao Li, and Ye Duan. "Features for automated tongue image shape classification." In 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, pp. 273-279. IEEE, 2012.
Proceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012