Traditional Chinese medicine face diagnosis auxiliary diagnosis method and device based on face feature detection and storage medium

Abstract

The invention discloses a traditional Chinese medicine face diagnosis auxiliary diagnosis method based on face feature detection, and the method comprises the steps: collecting a face image, marking the face diagnosis key features of the face image for the training of a face feature detection model, and enabling the face diagnosis key features to comprise at least one of spots, nevi, acnes, blood streaks and cross grains; acquiring a face area required by face diagnosis by adopting a face key point detection algorithm, and performing traditional Chinese medicine face diagnosis partitioning on the face image according to face key point positioning; the face diagnosis key features of the face image are extracted through a convolutional neural network structure, and the convolutional neural network structure at least comprises one-time convolutional layer, one-time pooling layer, one-time feature fusion and one-time feature pyramid; and in combination with the face diagnosis key features and the traditional Chinese medicine face diagnosis partitions, a traditional Chinese medicine face diagnosis result is obtained according to medical logic judgment. The method can automatically extract face key features such as spots, nevi, acnes, cross grains and the like, and effectively supports the improvement of the diagnosis accuracy of traditional Chinese medicine face diagnosis.

Description

technical field [0001] This specification relates to the technical field of computer software, and in particular to a method, device, storage medium and electronic equipment for an auxiliary diagnosis method, device, storage medium and electronic equipment based on facial feature detection in traditional Chinese medicine. Background technique [0002] Face-to-face diagnosis is a diagnosis method to know visceral diseases and health conditions through facial reflex areas, so as to quickly cure them. This is a simple and effective method for discovering diseases, which is of great significance to medicine. Traditional Chinese medicine observes the whole face and facial five sense organs through the four diagnosis methods of looking, smelling, asking, and feeling, so as to judge the whole body and local lesions of the human body. Abnormal changes in the body may occur before or after the appearance of facial changes. Visceral functions and qi and blood conditions of the human ...

AI Technical Summary

Problems solved by technology

At present, many TCM facial diagnosis instruments only extract a small amount of facial feature information such as the color and gloss of the face area when performing facial diagnosis, and the accuracy and reliability of these extracted features are not high, which seriously affects the results of facial diagnosis. the accuracy of

Because the extracted face features are relatively simple, and face feature information such as facial spots, moles, acne, blood streaks, and horizontal lines are not used, the results of the face-to-face diagnosis cannot accurately reflect the actual situation of the patient, and most of the face-to-face diagnosis results are one-sided. , the reliability of the diagnostic results is not high, which limits the widespread dissemination and application of face-to-face consultation among the general public

Images