AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (7.1 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

DEFOG: Deep Learning with Attention Mechanism Enabled Cross-Age Face Recognition

Shanxi Police College, Taiyuan 030401, China
China Mobile Communications Group Shaanxi Co., Ltd., Xi’an 710076, China
Intelligent Policing Key Laboratory of Sichuan Province, Luzhou 646000, China
Taiyuan University of Technology, Jinzhong 030600, China
Show Author Information

Abstract

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.

References

[1]
W. Ouarda, H. Trichili, A. M. Alimi, and B. Solaiman, Face recognition based on geometric features using support vector machines, in Proc. 6 th Int. Conf. Soft Computing and Pattern Recognition, Tunis, Tunisia, 2014, pp. 89–95.
[2]

P. I. Wilson and J. Fernandez, Facial feature detection using Haar classifiers, J. Comput. Sci. Coll., vol. 21, no. 4, pp. 127–133, 2006.

[3]
X. Yuan, J. Lu, and T. Yahagi, A method of 3D face recognition based on principal component analysis algorithm, in Proc. 2005 IEEE Int. Symp. Circuits and Systems, Kobe, Japan, 2005, pp. 3211–3214.
[4]
X. Xie, Z. Yuan, W. Guo, and Y. Zhang, Color face image denoising based on noisy pixel detection and neighborhood weight interpolation, (in Chinese), Journal of Tsinghua University (Science & Technology), vol. 54, no. 4, pp. 536–539, 2014.
[5]

X. Hou, X. Zhang, H. Liang, L. Shen, and Z. Ming, Lifelong age transformation with a deep generative prior, IEEE Trans. Multimed., vol. 25, pp. 3125–3139, 2023.

[6]
E. Liu and M. Zhi, Review of cross-age face recognition in discriminative models, in Proc. 8 th Int. Conf. Image, Vision and Computing, Dalian, China, 2023, pp. 124–130.
[7]
S. Chen, D. Zhang, L. Yang, and P. Chen, Age-invariant face recognition based on sample enhancement of generative adversarial networks, in Proc. 6th Int. Conf. Systems and Informatics, Shanghai, China, 2019, pp. 388–392.
[8]

D. C. Wang, Z. J. Tsai, C. C. Chen, and G. J. Horng, Development of a face prediction system for missing children in a smart city safety network, Electronics, vol. 11, no. 9, p. 1440, 2022.

[9]
C. Shi, J. Zhang, Y. Yao, Y. Sun, H. Rao, and X. Shu, CAN-GAN: Conditioned-attention normalized GAN for face age synthesis, Pattern Recognit. Lett., vol. 138, pp. 520–526, 2020.
[10]
A. Krizhevsky, I. Sutskever, and G. E. Hinton, ImageNet classification with deep convolutional neural networks, in Proc. 26 th Int. Conf. Neural Information Processing Systems, Lake Tahoe, NV, USA, 2012, pp. 1106–1114.
[11]
Y. Taigman, M. Yang, M. A. Ranzato, and L. Wolf, DeepFace: Closing the gap to human-level performance in face verification, in Proc. 2014 IEEE Conf. Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 1701–1708.
[12]
Y. Li, G. Wang, L. Lin, and H. Chang, A deep joint learning approach for age invariant face verification, in Proc. CCCV Chinese Conf. Computer Vision, Xi'an, China, 2015, pp. 206–305.
[13]
Y. Wen, Z. Li, and Y. Qiao, Latent factor guided convolutional neural networks for age-invariant face recognition, in Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 4893–4901.
[14]
G. S. J. Hsu, H. Y. Wu, and M. H. Yap, A comprehensive study on loss functions for cross-factor face recognition, in Proc. 2020 IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA, 2020, pp. 3604–3611.
[15]
X. Ren, J. Wang, and S. Li, MAM: Multiple attention mechanism neural networks for cross-age face recognition, Wireless Commun. Mobile Comput., vol. 2022, p. 8546029, 2022.
[16]
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, Gradient-based learning applied to document recognition, in Intelligent Signal Processing, S. Haykin and B. Kosko, eds. New York, NY, USA: Wiley-IEEE Press, 2001, pp. 306–351.
[17]
K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition, presented at the 3rd Int. Conf. Learning Representations, San Diego, CA, USA, 2015.
[18]
K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proc. 2016 IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 770–778.
[19]
V. Mnih, N. Heess, A. Graves, and K. Kavukcuoglu, Recurrent models of visual attention, in Proc. 27 th Int. Conf. Neural Information Processing Systems, Montreal, Canada, 2014, pp. 2204–2212.
[20]
H. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, Z. Li, and W. Liu, CosFace: Large margin cosine loss for deep face recognition, in Proc. 2018 IEEE/CVF Conf. Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 5265–5274.
[21]
T. Xie, L. Yu, C. Luo, H. Xie, and Y. Zhang, Survey of deep face manipulation and fake detection, (in Chinese), Journal of Tsinghua University (Science & Technology), vol. 63, no. 9, pp. 1350–1365, 2023.
[22]
J. Deng, J. Guo, E. Ververas, I. Kotsia, and S. Zafeiriou, RetinaFace: Single-shot multi-level face localisation in the wild, in Proc. 2020 IEEE/CVF Conf. Computer Vision and Pattern Recognition, Seattle, WA, USA, 2020, pp. 5202–5211.
[23]

H. Li, H. Zou, and H. Hu, Modified hidden factor analysis for cross-age face recognition, IEEE Signal Process. Lett., vol. 24, no. 4, pp. 465–469, 2017.

[24]
Y. Wang and Q. Wu, Research on face recognition technology based on PCA and SVM, in Proc. 7 th Int. Conf. Big Data Analytics, Guangzhou, China, 2022, pp. 248–252.
[25]
Y. H. Lin, C. H. Tang, Z. T. Chen, G. S. J. Hsu, M. Shopon, and M. Gavrilova, Age-style and alignment augmentation for facial age estimation, in Proc. 19 th Int. Conf. Computer Analysis of Images and Patterns, Virtual Event, 2021, pp. 297–307.
[26]
D. Gong, Z. Li, D. Lin, J. Liu, and X. Tang, Hidden factor analysis for age invariant face recognition, in Proc. 2013 IEEE Int. Conf. Computer Vision, Sydney, Australia, 2013, pp. 2872–2879.
Tsinghua Science and Technology
Pages 1342-1358
Cite this article:
Zhu B, li L, Hu X, et al. DEFOG: Deep Learning with Attention Mechanism Enabled Cross-Age Face Recognition. Tsinghua Science and Technology, 2025, 30(3): 1342-1358. https://doi.org/10.26599/TST.2024.9010107

55

Views

7

Downloads

0

Crossref

0

Web of Science

0

Scopus

0

CSCD

Altmetrics

Received: 17 February 2024
Revised: 10 May 2024
Accepted: 12 June 2024
Published: 30 December 2024
© The Author(s) 2025.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return