Emotion prediction method based on micro-expression recognition and eye movement tracking

An eye-tracking and micro-expression technology, applied in the field of pattern recognition, can solve the problems of missing and unable to learn facial features, and achieve the effect of avoiding psychological problems

Active Publication Date: 2020-11-20
HOHAI UNIV
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the previous research process, there was a lack of facial expression databases for negative and subtle emotions such as depression, anxiety, and stress, and it was impossible to learn the facial features displayed by such emotions through a large number of sample learning methods.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Emotion prediction method based on micro-expression recognition and eye movement tracking
  • Emotion prediction method based on micro-expression recognition and eye movement tracking
  • Emotion prediction method based on micro-expression recognition and eye movement tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Such as figure 1 As shown, the method for predicting depression, anxiety, and stress based on micro-expression recognition and eye movement tracking of the present invention firstly obtains the facial video taken by the observed person when receiving a certain psychological stimulus, and performs the video respectively Microexpression recognition and eye tracking. In the micro-expression recognition, the video is read by frame and converted into a face image; the candidate face image is obtained after the data is denoised; then the facial features are extracted by using the AAM model; The facial features are constructed as a parametric model; then, through the SVM mechanism, the parameterized facial feature information is marked according to the facial AU intensity level to form a vector; the single-frame image intensity level vector is normalized, and the intensity of 30 consecutive frames is Level vectors are combined to construct a facial matrix FM; the matrix FM is...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an emotion prediction method based on micro-expression recognition and eye movement tracking. The method comprises the following steps: (1) inputting a face video of an observed person after the observed person is stimulated by a certain signal, and carrying out the micro-expression recognition; (2) inputting a face video of an observed person after receiving certain signalstimulation, and carrying out eye movement tracking; and (3) fusing the micro-expression recognition result in the step (1) with the eye movement tracking result in the step (2), and judging the depression, anxiety and stress emotion states of the current observed person. By combining the emotional state ratio recognized by the micro-expression and the emotional state ratio tracked by the eye movement, the negative emotional states of depression, anxiety and stress of an observed person after facing a certain psychological stimulation signal can be predicted more accurately.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a method for predicting emotions based on micro-expression recognition and eye tracking. Background technique [0002] With the rapid development of computer vision and pattern recognition technology, facial expression recognition has also achieved many results. However, the current facial expression recognition mainly focuses on expressing the six basic emotions based on AUs provided by EFACS to express happiness, sadness, anger, disgust, fear, and surprise. For the current social background, "mental sub-health" is mainly reflected in Depression, anxiety, stress and other negative hidden emotions. [0003] In the previous research process, there was a lack of facial expression databases for negative and hidden emotions such as depression, anxiety, and stress, and it was impossible to learn the facial features displayed by such emotions through a large number of samp...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/174G06V40/161G06V40/168G06V40/172G06N3/047G06N3/045G06F18/25
Inventor 赵淑雯王敏
Owner HOHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap