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...
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |