A Novel Feature Extraction Method of Toothprint on Tongue in Traditional Chinese Medicine

The toothprint on tongue is an important objective index for revealing the human sub-health state, and thus the extraction and description of toothprint is of great significance in clinical applications. Current toothprint detection methods are only based on concave point. These methods, however, heavily depend on the accuracy of the segmentation of the tongues from the background, and are difficult to detect the weak toothprint on tongue. In this paper, we propose an effective method to make toothprint detection more robust and accurate. The proposed method first extracts both the curvature feature and the color feature around the contour of the tongue, and then analyses the toothprint using these two kinds of features. Experimental results show that the proposed method is promising for the detection of both the obvious and the weak toothprints.

[1]  David Zhang,et al.  On automated tongue image segmentation in Chinese medicine , 2002, Object recognition supported by user interaction for service robots.