Visceral organ feature coding method based on face image multi-stage relationship learning

Abstract

The invention discloses a visceral organ feature coding method based on face image multi-stage relation learning, and the method comprises the steps: collecting face images, obtaining labels marked for each face image, wherein the labels comprise visceral organ labels and organ feature labels associated with each visceral organ; after data augmentation is carried out on the face image, carrying out normalization and standardization on RGB three channels to acquire a training set and simultaneously performing supervised learning of two subtask branches on the face image training set by utilizing visceral organ tags and organ feature tags to embed priori guidance knowledge of visceral features, and finally obtaining a visceral feature coding model embedded with the priori knowledge. According to the method, the relevance among the face image, the visceral organ labels and the organ feature labels can be fully considered, modeling and analysis are carried out on the multi-stage relation learning model, and a visual and objective basic support is provided for human body health care and health preservation through the coding result of the human body visceral organ features.

Description

technical field [0001] The invention relates to the technical field of machine learning, and more specifically relates to a method for encoding features of internal organs based on multi-stage relationship learning of human face images. Background technique [0002] The ancient Chinese book "Huangdi Neijing" records that "there are twelve meridians, three hundred and sixty-five channels, and the blood and qi are all on the face and go through the hole", which shows that the human internal organs will be manifested in the relevant areas of the face. Observing people's facial complexion can grasp the internal organs of the user, and then adjust the internal organs through diet, exercise and improvement of living habits, so as to achieve the purpose of health preservation. For example, people with dampness usually have spots, acne, oily face, red nose, etc. on the face, so the moisture in the body can be expressed through facial features. The moisture in the body is related to...

AI Technical Summary

Problems solved by technology

[0004] However, the current deep supervised learning methods require a large amount of labeled data support, otherwise the model training will easily fall into overfitting, resulting in insufficient generalization ability of the model to effectively express the distinguishing characteristics of the data

However, the collection of labeled data is very expensive, and it is almost impossible to collect enough training data for each task

Images