A method for identifying greasy tongue coating based on texture and distribution features

Abstract

The invention discloses a method for identifying decayed tongue fur based on texture, roughness and distribution characteristics. The steps are as follows: (1) Use the existing tongue surface image sample map to establish a training sample set that combines Gabor texture, Tamura roughness and tongue coating distribution characteristics; (2) Use support vector machine to train the training sample set to construct a tongue coating Classifier; (3) Use the established tongue fur classifier to identify whether the tongue surface image to be recognized belongs to a rancid tongue image. This method obtains the texture, roughness and tongue coating distribution feature vector of the tongue surface image, uses the support vector machine as the classifier, and simulates the recognition of the tongue coating image by the experts of traditional Chinese medicine, which is repeatable; this method does not need any manual guidance and parameters in the recognition stage The setting makes the judging mechanism of greasy tongue phenomenon more intuitive and fair; simulates the recognition of greasy tongue phenomenon by traditional Chinese medicine, and overcomes the shortcomings of strong subjectivity and poor repeatability of visual observation of greasy tongue phenomenon in traditional Chinese medicine.

Description

technical field [0001] The invention relates to a method for identifying greasy tongue fur based on texture and distribution features, and belongs to the fields of pattern recognition and image processing. Background technique [0002] There are four basic methods of TCM diagnosis, namely: looking, smelling, asking, and feeling. The main contents of tongue inspection include tongue quality and tongue coating. Tongue coating is a layer of fur attached to the tongue surface. The color, thickness and degree of decay of the tongue coating can all reflect the health of the internal organs. Tongue fur can be divided into rotten fur and greasy fur according to the degree of greasy tongue fur. Greasy fur is characterized by fine and dense moss particles, which are fused into sheets, thick in the middle and thin around, and cling to the tongue surface, which cannot be wiped off, and is not easy to fall off when scraped. On the other hand, rotten fur is characterized by coarse part...

AI Technical Summary

Problems solved by technology

Use computer to simulate Chinese medicine experts to identify tongue coating, and then overcome the disadvantages of strong subjectivity and poor repeatability of traditional identification of rotten tongue coating

Images