A novel segmentation of tongue image

Abstract

The segmentation of the body of tongue is a premise to establishing a system of automatic diagnosis by the feature of tongue in Traditional Chinese Medicine (TCM), whose qualities affect the performance of tongue diagnosis. Because of similar colour between tongue body and background, it is difficult to segment tongue. To overcome two key difficulties with the initialisation and boundary concavities (important to the analysis of tooth's marks), a novel method for tongue contour extraction based on improved level set curve evolution is proposed. We present an automatic initialisation of contour by the feature of tongue in the HSV colour space. Improved level set method takes tongue contour shape constraint represented by energy function between the evolving curve and parametric shape model. In addition, the regularity of the level set function is intrinsically preserved by the level set regularisation term to ensure accurate computation. Experimental results for the large database of tongue images show desirable performances of our method.