DEFOG: Deep Learning with Attention Mechanism Enabled Cross-Age Face Recognition
As individuals age, their facial features change, which can hinder the accuracy of face recognition technology. To address this challenge, a new cross-age face recognition algorithm, leveraging deep learning and a loss function (Loss), has been proposed in this article. The Retinaface algorithm detects faces in images, while the Resnet-50 model is enhanced by incorporating an attention mechanism and improved softmax loss (Arcface) to extract facial features. This approach has been tested on publicly available and custom-built datasets, and its performance has been compared to other cross-age face recognition techniques. The results show that the model effectively recognizes faces across different age groups.
Authors
- Jie Song (ORCID: https://orcid.org/0000-0003-0704-3217)
- Fulin Wu
- Yanxi Wang
- Jiali Wu (ORCID: https://orcid.org/0000-0001-8521-331X)
- Jumin Zhao (ORCID: https://orcid.org/0000-0002-9049-4053)
- Xiaochun Hu (ORCID: https://orcid.org/0009-0005-7254-2989)
- Sanman Liu (ORCID: https://orcid.org/0000-0001-9586-4618)
- Lu Li (ORCID: https://orcid.org/0000-0003-3638-618X)
- Feng Li (ORCID: https://orcid.org/0009-0004-0136-7098)
- Biaokai Zhu (ORCID: https://orcid.org/0000-0001-7661-3266)
- Zhaojie Zhang (ORCID: https://orcid.org/0009-0008-8695-7415)
- Shengnan Zhu
Institutions
- China Mobile (China) (CN)
- Science and Technology Department of Sichuan Province (CN)
- Taiyuan University of Technology (CN)
Publication Details
- Journal
- Tsinghua Science & Technology
- Published
- 2024-12-30
- DOI
- https://doi.org/10.26599/tst.2024.9010107
- Citations
- 2
- Primary Topic
- Face recognition and analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.50
Funders
- National Natural Science Foundation of China