A Multi-label Classification Method for Tongue Image Based on Graph Convolutional Network

Abstract

The invention discloses a tongue image multi-label classification method based on a graph convolutional network, comprising the following steps: S1, performing tongue body detection on the original image, and extracting the tongue body image; S2, performing the tongue body image extracted in step S1 Carry out image preprocessing, the preprocessing includes de-reflective point processing, sharpening processing and straightening processing; S3, for each label, semi-automatically label the preprocessed tongue body image to obtain a large-sample multi-label data set; S4. Using the graph convolutional network to train and infer the large-sample multi-label data set obtained in step S3, and obtain a tongue body multi-label classification model based on the graph convolutional network. The present invention simultaneously classifies and diagnoses multiple labels of tongue images through a graph convolutional network, fully learns the dependencies between labels, and makes the process of machine tongue diagnosis more efficient and accurate.

Description

technical field [0001] The invention relates to the technical field of detection and classification of machine vision for tongue diagnosis in traditional Chinese medicine, in particular to a new method for tongue detection, tongue preprocessing, tongue semi-automatic labeling process and tongue image multi-label classification based on graph convolutional network. Background technique [0002] Among the four diagnoses "look, smell, ask, and feel" based on the diagnosis of traditional Chinese medicine, "look" is the most important. "Tongue observation" is an important part of "examination", because the internal organs of the human body are connected to the tongue through meridians, and changes in the human body can be reflected in the tongue. Tongue diagnosis in traditional Chinese medicine is observed with the naked eye, which is highly subjective. Therefore, quantitative analysis methods can provide a basis for more accurate tongue diagnosis. [0003] Tongue diagnosis is ...

AI Technical Summary

Problems solved by technology

[0004] In the past, most of the classification studies on tongue images classified each label separately, ignoring the dependencies between labels, and the results output multiple classification models, which means that multiple models need to be loaded during inference. thereby affecting efficiency

A small number of studies using multi-label either did not use deep learning technology, or did not fully mine the dependencies between labels, which affected the accuracy

Images