Supercharge Your Innovation With Domain-Expert AI Agents!

Facial expression recognition method under partial occlusion working condition

A facial expression and recognition method technology, applied in character and pattern recognition, acquisition/recognition of facial features, image analysis, etc., can solve problems such as missing facial occlusion features, and achieve improved recognition accuracy, accuracy and robustness. Effect

Active Publication Date: 2021-02-26
TONGJI UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a facial expression recognition method under partially occluded working conditions in order to overcome the above-mentioned defects in the prior art, which helps to solve the problem of missing features that may be caused by facial occlusion in real environments, and Improve the application range and robustness of expression recognition technology

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
  • Facial expression recognition method under partial occlusion working condition
  • Facial expression recognition method under partial occlusion working condition
  • Facial expression recognition method under partial occlusion working condition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0054] Such as figure 1 As shown, the present invention provides a facial expression recognition method under partial occlusion working conditions, comprising the following steps:

[0055]S1: Obtain the unoccluded facial image of the recognized object, calculate the average face information entropy map, and construct the facial projection space;

[0056] S2: Obtain a partially occluded facial image of the same recognition object, calculate the information entropy map of the partially occluded face, and project the partially occluded facial image into the facial projection space to obtain a projection vector;

[0057] S3: Use the average face information entropy map and the occluded face information entropy map to obtain the location of the occluded area;

[0058] S4: Using the facial projection space and occluded area positioning, reconstruct the unoccluded facial reconstructed image;

[0059] S5: Obtain a reconstructed facial image by using the occluded area in the unocclud...

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 relates to a facial expression recognition method under a partial occlusion working condition, and the method comprises the following steps: S1, obtaining a non-occluded face image of arecognition object, calculating an average face information entropy graph, and constructing a face projection space; s2, acquiring a partially-occluded facial image of the same recognition object, calculating a partially-occluded facial information entropy graph, and projecting a partially-occluded expression to a facial projection space; s3, utilizing the average face information entropy graph and the occluded face information entropy graph to obtain occluded area positioning; s4, performing positioning by utilizing the face projection space and the occluded area, and performing reconstructing to obtain a non-occluded face reconstructed image; s5, obtaining a reconstructed face image by using the occlusion area in the non-occlusion face reconstruction image and the non-occluded area in the partially occluded face image; and S6, performing feature extraction and classification on the reconstructed face image to obtain an expression recognition result. Compared with the prior art, the method has the advantages of high robustness and the like.

Description

technical field [0001] The invention relates to the fields of computer vision and pattern recognition, in particular to a facial expression recognition method under partial occlusion conditions. Background technique [0002] With the development of automobile intelligence, the interaction between drivers and passengers has gradually become a hot spot of competition, such as differentiated human-computer interaction, emotional detection of people in the car, motion detection, voice semantic judgment, etc. The most direct means of detecting the emotions of the occupants is the real-time capture of facial expressions by the camera. This means can be realized by placing an expression recognizer in the car. The expression recognizer can monitor and detect whether there is a change in the expression of the occupants in the vehicle, and then interpret the physiological and psychological changes of the occupants in the vehicle, thereby achieving real-time regulation of the driving ...

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): G06K9/00G06K9/38G06K9/46G06K9/62G06T5/30G06T5/40
CPCG06T5/30G06T5/40G06T2207/10024G06T2207/30201G06V40/165G06V40/174G06V40/171G06V40/172G06V10/446G06V10/28G06F18/2135G06F18/2411
Inventor 张立军蒋秋宇孟德建李聪聪
Owner TONGJI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More