The Segmentation of the Body of Tongue Based on the Improved Level Set in TCM

Abstract

The segmentation of the body of tongue pays an important role for automatic tongue diagnosis in Traditional Chinese Medicine. If there are similar grayscales near the margins of the body of tongue, it is difficult to extract the body of tongue desirably with some popular methods directly. In order to overcome this difficulty, a method that combines priori knowledge with improved level set method is presented. First, the contour of tongue is initialized in the HSV color space and a method which enhances the contrast between tongue and other parts of the tongue image is introduced. Then, a new region-based signed pressure force function is proposed, which can efficiently stop the contour at weak edges. Finally, we use a Gaussian filtering process to further regularize the level set function instead of reinitializing signed distance function. Experiments by numerous real tongue images show desirable performances of our method.