Research on a Microexpression Recognition Technology Based on Multimodal Fusion

Microexpressions have extremely high due value in national security, public safety, medical, and other fields. However, microexpressions have characteristics that are obviously different from macroexpressions, such as short duration and weak changes, which greatly increase the difficulty of microexp...

Full description

Saved in:
Bibliographic Details
Main Authors: Jie Kang, Xiao Ying Chen, Qi Yuan Liu, Si Han Jin, Cheng Han Yang, Cong Hu
Format: Article
Language:English
Published: Wiley 2021-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2021/5221950
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849683748403019776
author Jie Kang
Xiao Ying Chen
Qi Yuan Liu
Si Han Jin
Cheng Han Yang
Cong Hu
author_facet Jie Kang
Xiao Ying Chen
Qi Yuan Liu
Si Han Jin
Cheng Han Yang
Cong Hu
author_sort Jie Kang
collection DOAJ
description Microexpressions have extremely high due value in national security, public safety, medical, and other fields. However, microexpressions have characteristics that are obviously different from macroexpressions, such as short duration and weak changes, which greatly increase the difficulty of microexpression recognition work. In this paper, we propose a microexpression recognition method based on multimodal fusion through a comparative study of traditional microexpression recognition algorithms such as LBP algorithm and CNN and LSTM deep learning algorithms. The method couples the separate microexpression image information with the corresponding body temperature information to establish a multimodal fusion microexpression database. This paper firstly introduces how to build a multimodal fusion microexpression database in a laboratory environment, secondly compares the recognition accuracy of LBP, LSTM, and CNN + LSTM networks for microexpressions, and finally selects the superior CNN + LSTM network in the comparison results for model training and testing on the test set under separate microexpression database and multimodal fusion database. The experimental results show that a microexpression recognition method based on multimodal fusion designed in this paper is more accurate than unimodal recognition in multimodal recognition after feature fusion, and its recognition rate reaches 75.1%, which proves that the method is feasible and effective in improving microexpression recognition rate and has good practical value.
format Article
id doaj-art-cec08454bf1b4ca6bc7a9c97db54510d
institution DOAJ
issn 1099-0526
language English
publishDate 2021-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-cec08454bf1b4ca6bc7a9c97db54510d2025-08-20T03:23:43ZengWileyComplexity1099-05262021-01-01202110.1155/2021/5221950Research on a Microexpression Recognition Technology Based on Multimodal FusionJie Kang0Xiao Ying Chen1Qi Yuan Liu2Si Han Jin3Cheng Han Yang4Cong Hu5College of Mechanical & Electrical EngineeringCollege of Mechanical & Electrical EngineeringCollege of Mechanical & Electrical EngineeringCollege of Mechanical & Electrical EngineeringCollege of Mechanical & Electrical EngineeringGuangxi Key Laboratory of Automatic Detecting Technology and InstrumentsMicroexpressions have extremely high due value in national security, public safety, medical, and other fields. However, microexpressions have characteristics that are obviously different from macroexpressions, such as short duration and weak changes, which greatly increase the difficulty of microexpression recognition work. In this paper, we propose a microexpression recognition method based on multimodal fusion through a comparative study of traditional microexpression recognition algorithms such as LBP algorithm and CNN and LSTM deep learning algorithms. The method couples the separate microexpression image information with the corresponding body temperature information to establish a multimodal fusion microexpression database. This paper firstly introduces how to build a multimodal fusion microexpression database in a laboratory environment, secondly compares the recognition accuracy of LBP, LSTM, and CNN + LSTM networks for microexpressions, and finally selects the superior CNN + LSTM network in the comparison results for model training and testing on the test set under separate microexpression database and multimodal fusion database. The experimental results show that a microexpression recognition method based on multimodal fusion designed in this paper is more accurate than unimodal recognition in multimodal recognition after feature fusion, and its recognition rate reaches 75.1%, which proves that the method is feasible and effective in improving microexpression recognition rate and has good practical value.http://dx.doi.org/10.1155/2021/5221950
spellingShingle Jie Kang
Xiao Ying Chen
Qi Yuan Liu
Si Han Jin
Cheng Han Yang
Cong Hu
Research on a Microexpression Recognition Technology Based on Multimodal Fusion
Complexity
title Research on a Microexpression Recognition Technology Based on Multimodal Fusion
title_full Research on a Microexpression Recognition Technology Based on Multimodal Fusion
title_fullStr Research on a Microexpression Recognition Technology Based on Multimodal Fusion
title_full_unstemmed Research on a Microexpression Recognition Technology Based on Multimodal Fusion
title_short Research on a Microexpression Recognition Technology Based on Multimodal Fusion
title_sort research on a microexpression recognition technology based on multimodal fusion
url http://dx.doi.org/10.1155/2021/5221950
work_keys_str_mv AT jiekang researchonamicroexpressionrecognitiontechnologybasedonmultimodalfusion
AT xiaoyingchen researchonamicroexpressionrecognitiontechnologybasedonmultimodalfusion
AT qiyuanliu researchonamicroexpressionrecognitiontechnologybasedonmultimodalfusion
AT sihanjin researchonamicroexpressionrecognitiontechnologybasedonmultimodalfusion
AT chenghanyang researchonamicroexpressionrecognitiontechnologybasedonmultimodalfusion
AT conghu researchonamicroexpressionrecognitiontechnologybasedonmultimodalfusion