Depression identification method based on micro-expression analysis

Abstract

The invention discloses a depression identification method based on micro-expression analysis. The depression identification method comprises the following steps: S1, dynamically capturing a facial picture of a user through a front camera of a mobile terminal of the user; S2, performing preprocessing, face detection and face feature extraction on the face picture in sequence; s3, inputting the extracted face features into a trained face recognition model for micro-expression recognition; and S4, performing emotion classification on the human face by using a valence state-awakening degree theory. The facial image of the user is dynamically captured by using the front camera of the mobile phone, and the data report is finally generated through a micro-expression recognition technology and provided for a doctor for adjuvant therapy, so that the diagnosis is more accurate, and the defects of small coverage range, high operation difficulty and high technical requirements of a professional depression recognition system are overcome.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a method for identifying depression based on micro-expression analysis. Background technique [0002] According to estimates by authoritative organizations, the number of pan-depressed people in China is close to 100 million. Now that the growth rate of depression is so high, it is difficult for people to distinguish between bad mood and depression, causing delays in seeking medical treatment or wasting public resources. With the development of the field of machine learning, the emotional information processing of depression patients has become a frontier scientific issue and research hotspot. The existing depression detection methods are single, the detection equipment is expensive, and the accuracy rate is low. Therefore, the industry needs to develop a machine vision-based depression recognition method with simple equipment and high detection accuracy. Contents of th...

AI Technical Summary

Problems solved by technology

Now that the growth rate of depression is so high, it is difficult for people to distinguish between bad mood and depression, causing delays in seeking medical treatment or wasting public resources

With the development of the field of machine learning, the emotional information processing of depression patients has become a cutting-edge scientific issue and research hotspot. The existing depression detection methods are single, the detection equipment is expensive, and the accuracy rate is low.

Images