A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition

Adult facial expression recognition (FER) is essential for human-computer interaction, mental health assessment, and social robotics applications because it improves user experiences and emotional well-being. This study presents a novel attention mechanism-based transformer approach designed to capt...

Full description

Saved in:
Bibliographic Details
Main Authors: Uzma Nawaz, Zubair Saeed, Kamran Atif
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10943176/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770160676667392
author Uzma Nawaz
Zubair Saeed
Kamran Atif
author_facet Uzma Nawaz
Zubair Saeed
Kamran Atif
author_sort Uzma Nawaz
collection DOAJ
description Adult facial expression recognition (FER) is essential for human-computer interaction, mental health assessment, and social robotics applications because it improves user experiences and emotional well-being. This study presents a novel attention mechanism-based transformer approach designed to capture detailed patterns in facial features and dynamically focus on the most relevant regions for enhanced accuracy. Unlike conventional deep learning approaches, our method integrates an adaptive attention mechanism and dynamic token pruning, which optimizes computational efficiency while maintaining high accuracy. The model is evaluated on five widely used datasets: FER2013, CK+, AffectNet, RAF-DB, and AFEW. It achieves state-of-the-art performance, with accuracies of 98.67% on FER2013, 99.52% on CK+, 99.3% on AffectNet, 96.3% on AFEW, and 98.45% on RAF-DB. An ablation study further validates the contribution of each model component, and comparisons with CNN-based and transformer-based approaches confirm the effectiveness of the model. These findings establish the proposed method as a significant advancement in FER, which offers a scalable and efficient solution for real-world applications.
format Article
id doaj-art-cc97f9ec93d54a4ab050b76ac790546e
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-cc97f9ec93d54a4ab050b76ac790546e2025-08-20T03:03:07ZengIEEEIEEE Access2169-35362025-01-0113564855650810.1109/ACCESS.2025.355551010943176A Novel Transformer-Based Approach for Adult’s Facial Emotion RecognitionUzma Nawaz0https://orcid.org/0009-0003-3805-8101Zubair Saeed1https://orcid.org/0000-0001-5302-7133Kamran Atif2Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering, Knowledge and Data Science Research Centre, National University of Science and Technology, Islamabad, PakistanDepartment Electrical and Computer Engineering, Texas A&M University, College Station, TX, USADepartment of Civil Engineering, Deakin University, Melbourne, VIC, AustraliaAdult facial expression recognition (FER) is essential for human-computer interaction, mental health assessment, and social robotics applications because it improves user experiences and emotional well-being. This study presents a novel attention mechanism-based transformer approach designed to capture detailed patterns in facial features and dynamically focus on the most relevant regions for enhanced accuracy. Unlike conventional deep learning approaches, our method integrates an adaptive attention mechanism and dynamic token pruning, which optimizes computational efficiency while maintaining high accuracy. The model is evaluated on five widely used datasets: FER2013, CK+, AffectNet, RAF-DB, and AFEW. It achieves state-of-the-art performance, with accuracies of 98.67% on FER2013, 99.52% on CK+, 99.3% on AffectNet, 96.3% on AFEW, and 98.45% on RAF-DB. An ablation study further validates the contribution of each model component, and comparisons with CNN-based and transformer-based approaches confirm the effectiveness of the model. These findings establish the proposed method as a significant advancement in FER, which offers a scalable and efficient solution for real-world applications.https://ieeexplore.ieee.org/document/10943176/Facial emotion recognitiontransformersdeep learningFER2013CK+AffectNet
spellingShingle Uzma Nawaz
Zubair Saeed
Kamran Atif
A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
IEEE Access
Facial emotion recognition
transformers
deep learning
FER2013
CK+
AffectNet
title A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_full A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_fullStr A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_full_unstemmed A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_short A Novel Transformer-Based Approach for Adult’s Facial Emotion Recognition
title_sort novel transformer based approach for adult x2019 s facial emotion recognition
topic Facial emotion recognition
transformers
deep learning
FER2013
CK+
AffectNet
url https://ieeexplore.ieee.org/document/10943176/
work_keys_str_mv AT uzmanawaz anoveltransformerbasedapproachforadultx2019sfacialemotionrecognition
AT zubairsaeed anoveltransformerbasedapproachforadultx2019sfacialemotionrecognition
AT kamranatif anoveltransformerbasedapproachforadultx2019sfacialemotionrecognition
AT uzmanawaz noveltransformerbasedapproachforadultx2019sfacialemotionrecognition
AT zubairsaeed noveltransformerbasedapproachforadultx2019sfacialemotionrecognition
AT kamranatif noveltransformerbasedapproachforadultx2019sfacialemotionrecognition