Image recognition and separation method of tongue body and tongue coating

Abstract

The invention discloses a method for identifying and separating tongue body and tongue coating images. Step 1: collecting tongue image pictures; step 2: performing color correction on the acquired tongue image pictures in different ways according to different collection devices, so as to improve the accuracy of subsequent image processing algorithms. Accuracy; Step 3: Locating the tongue body area in the tongue image, including arbitrarily cropping the tongue image into sub-blocks, and using the trained convolutional neural network to train the sub-blocks, according to the face The position of the left and right eyes, the position of the nose tip and the position of the left and right corners of the mouth are used to locate the tongue body to obtain a complete rectangular image including the tongue body; Step 4: Realize the segmentation of the tongue body and non-tongue body; Step 5: According to the different colors of the tongue coating and the tongue body , to realize the separation of moss on the tongue image after segmentation. The beneficial effect of the present invention is that the color of the collected tongue image is corrected, the influence of color deviation on the subsequent analysis of the characteristics of the tongue is improved, and the accurate separation of the tongue and the moss is realized.

Description

technical field [0001] The invention relates to the technical field of traditional Chinese medicine tongue image processing, in particular to a method for identifying and separating images of tongue body and tongue coating. Background technique [0002] Tongue diagnosis, as a characteristic diagnosis method of traditional Chinese medicine, has a relatively complete theoretical basis. It reveals the objective phenomena of human physiology and pathology through appearance, and is widely accepted and recognized by people. Tongue diagnosis, as an effective and characteristic diagnostic method of traditional Chinese medicine, still plays an important role in today's clinical practice. So far, tongue diagnosis is still one of the clear, easy-to-use and effective diagnostic methods for syndrome diagnosis. It plays an important role in disease understanding, medication guidance, and efficacy evaluation. With the development of computer technology, people began to use deep learning,...

AI Technical Summary

Problems solved by technology

However, in the process of collecting tongue images with photographic equipment, due to factors such as different accuracy of the acquisition equipment and different ambient light, it is very easy to cause a certain color cast in the collected tongue images.

This will not only affect the subsequent tongue positioning and segmentation, color feature extraction and analysis of the algorithm, but also cause some interference to the diagnosis of users and clinicians

Images