Tongue picture segmentation method and device and storage medium

Abstract

The invention relates to a tongue picture segmentation method and device and a storage medium, and the method comprises the steps: obtaining a tongue picture training set which comprises a plurality of human body tongue picture images; performing feature extraction and feature fusion on the human body tongue picture images in the tongue picture training set to obtain a tongue mask set and taking the tongue mask set as a real label set; inputting the tongue picture training set and the paired real label set into a preset conditional generative adversarial network, and respectively updating a generator and a discriminator of the conditional generative adversarial network through iterative adversarial training to obtain a trained conditional generative adversarial network; and obtaining a to-be-recognized tongue picture image, inputting the to-be-recognized tongue picture image into the trained conditional generative adversarial network for tongue picture segmentation, and generating a tongue body image. Manual labeling is not needed, and the tongue picture segmentation precision can be effectively improved under the condition that the tongue picture data set is small.

Description

technical field [0001] The present application relates to the technical field of image segmentation, in particular to a tongue image segmentation method, device and storage medium. Background technique [0002] Tongue diagnosis in TCM is the first step in TCM, and it is also the most intuitive step. The tongue image can show the physiological conditions and pathological changes in the human body to the doctor one by one, which plays an important role in the doctor's diagnosis. Therefore, the objectification and quantification of tongue diagnosis has also become an important topic in the modernization of Chinese medicine in my country. [0003] With the increasing application of image processing technology in various fields, there are more and more tongue image segmentation technologies. According to whether there are labels, it is divided into four network structures: fully supervised segmentation network structure, semi-supervised segmentation network structure, Weakly sup...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present application provides a tongue image segmentation method, device and storage medium to solve the problem that a large amount of manpower and material resources are required for pixel-level labeling in the existing deep learning-based tongue image segmentation technology

Images