An automatic evaluation system for depression degree based on facial expression analysis

Abstract

The invention discloses a facial expression analysis-based depression degree automatic evaluation system. The facial expression analysis-based depression degree automatic evaluation system includes a data acquisition module, a preprocessing and feature extraction module, a related feature extraction module, a prediction model training module, a new video annotation module and a new video prediction module. The facial expression analysis-based depression degree automatic evaluation system of the invention has the advantages of full-process automation, no invasion and no requirements for long-time cooperation of a tested object, and can work for a long time. With the facial expression analysis-based depression degree automatic evaluation system provided by the invention adopted, objective evaluation standards are provided, and objective and effective evaluation can be realized actually without relying on subjective experiences required. The facial expression analysis-based depression degree automatic evaluation system is not limited to isolated analysis on individual objects.

Description

technical field [0001] The invention relates to a system for assessing the degree of depression, in particular to an automatic assessment system for the degree of depression based on facial expression analysis. Background technique [0002] Depression is a psychosomatic disease with abnormal behavior and low mood as the main symptoms, often accompanied by emotional cognitive impairment, and has the characteristics of high morbidity, refractory cure and high suicide rate. According to the statistics of the World Health Organization, the annual prevalence rate of depression is 10%, and the lifetime prevalence rate is 17%. About 1 million people die by suicide every year. Moreover, according to the prediction of the World Health Organization, depression will become the second largest cause of disability in the world by 2020, and depression will become the largest disease burden by 2030. [0003] Traditional depression assessments use clinical questionnaires and interviews, whi...

AI Technical Summary

Problems solved by technology

[0004] (1) Clinical questionnaires and interviews have high requirements for doctors' professional knowledge and clinical experience, and are easily affected by doctors' subjective factors;

[0005] (2) The clinical questionnaires and interviews require the active cooperation of the subjects for a long time, which has caused the subjects' restlessness;

[0006] (3) Clinical questionnaires and interviews ignore the unconscious expressions or movements of patients with depression, making objective and effective analysis and assessment impossible

In addition, clinical questionnaires and interviews are inefficient and consume a lot of resources

Images