Tongue image segmentation method based on sparse representation

Abstract

The invention relates to a tongue image segmentation method based on sparse representation. According to the method, a measuring degree based on color similarity is firstly defined for measuring the similarity of a local image block corresponding to a test pixel point and a local image block corresponding to a neighbor point on a training image in a neighborhood region of the test pixel point; the similarity measuring degree is used for executing screening on the training image block; the screened training image block is used for building a dictionary required by sparse representation; next, the sparse representation of the training image block in the dictionary is used for representing the test image block to obtain the sparse representation coefficient; further, the belonging probability of the current test pixel point to an objective (tongue body) is calculated according to the sparse representation coefficient and a segmentation mark of the corresponding pixel point in the training image; finally, the maximum posteriori criterion is used for obtaining the segmentation mark of the current test pixel point; the initial tongue mage segmentation result is obtained; then, a morphological filtering method is used for optimizing the segmentation result; and the final tongue image segmentation result is obtained. The accuracy and the robustness of the tongue image segmentation are obviously improved by the algorithm.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a tongue image segmentation method based on sparse representation, which is used to segment tongue images collected in automatic tongue diagnosis in traditional Chinese medicine, and extract the tongue body from backgrounds such as faces, for It provides a basis for the follow-up identification work of automatic tongue diagnosis in traditional Chinese medicine. Background technique [0002] Tongue diagnosis is one of the main contents of "inspection" in traditional Chinese medicine, and it is one of the traditional diagnostic methods with Chinese characteristics. Tongue image is the most sensitive index to reflect the physiological function and pathological changes of the human body, and it has important application value in the process of diagnosis and treatment of traditional Chinese medicine. Applying image processing technology to establish an objective quantificati...

AI Technical Summary

Problems solved by technology

However, once the tongue body in the collected tongue image is close to the surrounding image, the above-mentioned prior assumptions will cause errors in the background label, resulting in a large deviation in the initial outline of the tongue body obtained by region merging, resulting in serious mis-segmentation of the tongue image

[0008](3) Existing methods fail to find an efficient way to simultaneously solve two difficult problems in tongue image segmentation

However, while the GVF-RM method smoothes out some noise and trivial image details, it will also weaken the real tongue contour and increase the difficulty of extracting the real tongue contour.

[0009] In summary, the existing tongue image segmentation methods have certain limitations, and the segmentation effect and robustness need to be further improved

Images