Res-RBG Facial Expression Recognition in Image Sequences Based on Dual Neural Networks

Facial expressions involve dynamic changes, and facial expression recognition based on static images struggles to capture the temporal information inherent in these dynamic changes. The resultant degradation in real-world performance critically impedes the integration of facial expression recognitio...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiangwei Mou, Yongfu Song, Xiuping Xie, Mingxuan You, Rijun Wang
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/12/3829
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433957845696512
author Xiangwei Mou
Yongfu Song
Xiuping Xie
Mingxuan You
Rijun Wang
author_facet Xiangwei Mou
Yongfu Song
Xiuping Xie
Mingxuan You
Rijun Wang
author_sort Xiangwei Mou
collection DOAJ
description Facial expressions involve dynamic changes, and facial expression recognition based on static images struggles to capture the temporal information inherent in these dynamic changes. The resultant degradation in real-world performance critically impedes the integration of facial expression recognition systems into intelligent sensing applications. Therefore, this paper proposes a facial expression recognition method for image sequences based on the fusion of dual neural networks (ResNet and residual bidirectional GRU—Res-RBG). The model proposed in this paper achieves recognition accuracies of 98.10% and 88.64% on the CK+ and Oulu-CASIA datasets, respectively. Moreover, the model has a parameter size of only 64.20 M. Compared to existing methods for image sequence-based facial expression recognition, the approach presented in this paper demonstrates certain advantages, indicating strong potential for future edge sensor deployment.
format Article
id doaj-art-07a6610f5ff3461dadd141ebde79bd2b
institution Kabale University
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-07a6610f5ff3461dadd141ebde79bd2b2025-08-20T03:26:51ZengMDPI AGSensors1424-82202025-06-012512382910.3390/s25123829Res-RBG Facial Expression Recognition in Image Sequences Based on Dual Neural NetworksXiangwei Mou0Yongfu Song1Xiuping Xie2Mingxuan You3Rijun Wang4College of Electronic and Information Engineering/Integrated Circuits, Guangxi Normal University, Guilin 541004, ChinaCollege of Electronic and Information Engineering/Integrated Circuits, Guangxi Normal University, Guilin 541004, ChinaCollege of Electronic and Information Engineering/Integrated Circuits, Guangxi Normal University, Guilin 541004, ChinaCollege of Electronic and Information Engineering/Integrated Circuits, Guangxi Normal University, Guilin 541004, ChinaTeachers College for Vocational and Technical Education, Guangxi Normal University, Guilin 541004, ChinaFacial expressions involve dynamic changes, and facial expression recognition based on static images struggles to capture the temporal information inherent in these dynamic changes. The resultant degradation in real-world performance critically impedes the integration of facial expression recognition systems into intelligent sensing applications. Therefore, this paper proposes a facial expression recognition method for image sequences based on the fusion of dual neural networks (ResNet and residual bidirectional GRU—Res-RBG). The model proposed in this paper achieves recognition accuracies of 98.10% and 88.64% on the CK+ and Oulu-CASIA datasets, respectively. Moreover, the model has a parameter size of only 64.20 M. Compared to existing methods for image sequence-based facial expression recognition, the approach presented in this paper demonstrates certain advantages, indicating strong potential for future edge sensor deployment.https://www.mdpi.com/1424-8220/25/12/3829facial expression recognitionfeature extractiondeep learningBi-GRUresidual structureattention mechanism
spellingShingle Xiangwei Mou
Yongfu Song
Xiuping Xie
Mingxuan You
Rijun Wang
Res-RBG Facial Expression Recognition in Image Sequences Based on Dual Neural Networks
Sensors
facial expression recognition
feature extraction
deep learning
Bi-GRU
residual structure
attention mechanism
title Res-RBG Facial Expression Recognition in Image Sequences Based on Dual Neural Networks
title_full Res-RBG Facial Expression Recognition in Image Sequences Based on Dual Neural Networks
title_fullStr Res-RBG Facial Expression Recognition in Image Sequences Based on Dual Neural Networks
title_full_unstemmed Res-RBG Facial Expression Recognition in Image Sequences Based on Dual Neural Networks
title_short Res-RBG Facial Expression Recognition in Image Sequences Based on Dual Neural Networks
title_sort res rbg facial expression recognition in image sequences based on dual neural networks
topic facial expression recognition
feature extraction
deep learning
Bi-GRU
residual structure
attention mechanism
url https://www.mdpi.com/1424-8220/25/12/3829
work_keys_str_mv AT xiangweimou resrbgfacialexpressionrecognitioninimagesequencesbasedondualneuralnetworks
AT yongfusong resrbgfacialexpressionrecognitioninimagesequencesbasedondualneuralnetworks
AT xiupingxie resrbgfacialexpressionrecognitioninimagesequencesbasedondualneuralnetworks
AT mingxuanyou resrbgfacialexpressionrecognitioninimagesequencesbasedondualneuralnetworks
AT rijunwang resrbgfacialexpressionrecognitioninimagesequencesbasedondualneuralnetworks