Method for establishing emotion perception model based on individual face analysis in video

Abstract

The invention provides a method for establishing an emotion perception model based on individual face analysis in a video, comprising the following steps: evaluating the emotional states of a plurality of tested individuals through a positive and negative emotion scale, and respectively obtaining positive emotion and negative emotion scores corresponding to the emotional states of the tested individuals; collecting tested face video data, wherein the tested face video data corresponds to the tested emotional state score; performing data denoising preprocessing on the face key points in the acquired video data in a two-dimensional space; selecting facial feature points representing emotion perception by calculating a difference measurement variance between adjacent frames; carrying out feature extraction, feature dimension reduction and feature selection on the facial feature points, and optimizing a feature set through a classifier by adopting a sequence backward selection (SBS) algorithm; and adopting a regression algorithm in machine learning and taking the obtained scores of the individual positive emotion and negative emotion as annotation data to perform model training and verification, thereby obtaining and storing a prediction model for the individual positive emotion and negative emotion. According to the method, the user does not need to report by himself/herself, thetimeliness is high, and the correlation coefficient of the model prediction score and the scale evaluation score can reach the medium-to-strong correlation level.

Description

technical field [0001] The invention relates to the technical field of emotion perception, in particular to a method for establishing an emotion perception model based on individual face analysis in videos. Background technique [0002] Everyone in modern society has more or less psychological problems, such as nervousness, irritability, anxiety and depression. A healthy mental state and positive emotions can promote social harmony. On the contrary, an unhealthy mental state or negative emotions will bring certain influence and harm to society. The suicide rate in my country is about 23 / 100,000 per year, which is 2.3 times the international average. The incidence of mental illness is between 15-17.5%, and the incidence of severe mental illness is about 1-1.5%. There are about 100 million mental patients in the country. The number of people with psychological problems in China is nearly seven-tenths of the total population. Therefore, it is very important to be able to perc...

AI Technical Summary

Problems solved by technology

Other assessment methods often use a limited number of ordinal ratings to determine the severity of psychological problems. This method has many problems: first, the operational definition is often vague, such as moderate, mild, etc. The description is more like a qualitative description, It is difficult to unify standards among different raters; secondly, it is not sensitive to changes, and it is easy to miss subtle changes by using observation methods to judge changes in others

However, there are also some problems with the self-report method: firstly, the self-report method is limited by the interviewer's observation and expression ability, and people cannot always accurately assess and report their own symptoms and their severity; secondly, the self-report method reflects the The interviewer’s assessment of his / her own condition is purely subjective, which is prone to concealment and false reporting; third, the questionnaire can distinguish patients from ordinary people to a certain extent, and it is difficult to distinguish patients with different diseases

[0004] At the same time, due to the lack of deep understanding of psychological problems, many people do not realize that they are suffering from psychological problems, and do not know whether to seek help when they have problems with their physical and mental health.

Images