Facial expression recognition method and system based on regional grouping and internal association fusion

A facial expression recognition and facial expression technology, applied in the field of facial expression recognition, can solve problems such as poor recognition effect of facial expression recognition methods, and achieve the effect of improving accuracy

Active Publication Date: 2022-08-09
SHANDONG UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For frontal faces with natural occlusions, the recognition effect of unoccluded facial expression recognition methods is poor
Therefore, facial expression recognition under unlimited occlusion is still a challenge

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 and system based on regional grouping and internal association fusion
  • Facial expression recognition method and system based on regional grouping and internal association fusion
  • Facial expression recognition method and system based on regional grouping and internal association fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] The purpose of this embodiment is to provide a facial expression recognition method based on the fusion of region grouping and internal association.

[0038] In the real world, faces are subject to unpredictable occlusions under natural conditions. Facial occlusion can be caused by changes in head posture, lighting, masks, glasses, etc. For the frontal face with natural occlusion, the recognition effect of the unoccluded facial expression recognition method is poor. Therefore, facial expression recognition under unlimited occlusion is still a challenge.

[0039] In order to solve this problem, the present disclosure proposes an Interrelated Fusion CNN (IRF-CNN) to achieve the extraction and fusion of multi-semantic expression features of occluded face images. See the overall architecture of the network. figure 1 . IRF-CNN mainly includes three modules, namely Partial-occlusion Pre-processing module (POPM), Statistical Patches Grouping module (SPGM) and Interrelated R...

Embodiment 2

[0127] The purpose of this embodiment is to provide a facial expression recognition system based on regional grouping and internal association fusion.

[0128] A facial expression recognition system based on regional grouping and internal association fusion, including:

[0129] a data acquisition module, which is used to acquire the facial expression image to be recognized, and perform preprocessing;

[0130] A model building module, which is used to build a convolutional neural network model of intrinsic association fusion;

[0131] A facial expression recognition module, which is used to perform expression recognition on facial expression images by using a pre-trained convolutional neural network model, and output an expression recognition result;

[0132] Wherein, the convolutional neural network model includes an occlusion preprocessing module, a patch grouping module, and an intrinsic correlation reasoning fusion module, wherein the partial occlusion preprocessing module...

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 present disclosure provides a method and system for facial expression recognition based on the fusion of regional grouping and internal association. The solution is based on the fact that the face will be unpredictably occluded under natural conditions. For the frontal face with natural occlusion, no occlusion The problem of poor recognition effect of facial expression recognition method; through the proposed Interrelated Fusion CNN (IRF‑CNN), the key recognition features are obtained from three semantic dimensions of local area, context and overall image , and through the class pooling unit based on statistical indicators, the face is grouped reasonably according to the criticality of the face, further focusing on the independence and complementary information between the local and the global face, and effectively improving the accuracy of facial expression recognition.

Description

technical field [0001] The present disclosure belongs to the technical field of facial expression recognition, and in particular, relates to a facial expression recognition method and system based on the fusion of regional grouping and internal association. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] In recent years, facial expression recognition technology has received more and more attention because it can not only reflect the emotional state of traders, but also contain rich intention information of the interactors. It has certain potential application prospects in human-computer interaction, driver fatigue monitoring, lie detection, surveillance, entertainment robots, etc. [0004] Although standard frontal unobstructed facial expression recognition achieves good results. However, the inventors found that in the real world, huma...

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 Patents(China)
IPC IPC(8): G06V40/16G06V10/764G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/174G06N3/045G06F18/25G06F18/241
Inventor 马昕澹台姝昱宋锐荣学文李贻斌
Owner SHANDONG 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