Volume 21, Issue 1 (6-2024)
JSDP 2024, 21(1): 53-70 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Ahmadi S M, Dianat R. A two-stage clustering-based distributed framework for large-scale face identification. JSDP 2024; 21 (1) : 5
URL: http://jsdp.rcisp.ac.ir/article-1-1362-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1362-en.html
University of Qom
Abstract: (493 Views)
Face recognition poses challenges in accuracy, memory efficiency, and computational complexity. This study proposes a two-stage, three-module approach: Subnetwork modules, Cluster-Finder unit, and Final-Decision module. Unlike random distribution methods, our approach employs clustering for distribution. Each subnetwork, a supervised deep neural network, is trained with cluster-specific data. The Cluster-Finder unit compares test data similarity with each subnetwork’s representative. The Final-Decision module selects the best class. Results indicate superior accuracy, recall, and F1 score compared to competitive methods. The approach is faster and more accurate than non-distribution methods, with comparable speed and higher accuracy than random distribution methods. Experiments on VGGFace2, MS-Celeb-1M, and Glint360K datasets confirm both superior performance and scalability. The proposed method, using KMeans for distribution, outperforms Softmax Dissection and Dynamic Active Class Selection. It simplifies training without additional manipulations, offering efficiency over methodologies like Softmax Dissection and ArcFace parallelization. In conclusion, this study focuses on pre-processing and post-processing without added training complexity. A divide-and-conquer approach addresses accuracy and efficiency challenges. In this study, various sources leading to errors in face recognition systems have been examined. These sources include: imprecise features, overfitting, challenging classes, distribution issues, and decision-making complexities. Various classification scenarios are explored, including non-distributed and models with random and intelligent distributions. Inaccurate features uniformly impact all scenarios, with overfitting posing the greatest challenge in non-distributed scenarios. Challenging classes are better distinguished in intelligent distribution scenarios. Inappropriate distribution has less impact in intelligent scenarios, and decision-making challenges exist in both distributions
Article number: 5
Type of Study: Research |
Subject:
Paper
Received: 2023/03/7 | Accepted: 2024/02/24 | Published: 2024/08/3 | ePublished: 2024/08/3
Received: 2023/03/7 | Accepted: 2024/02/24 | Published: 2024/08/3 | ePublished: 2024/08/3
References
1. Sun, Y., et al., Deep learning face representation by joint identification-verification. Advances in neural information processing systems, 2014. 27.
2. Schroff, F., D. Kalenichenko, and J. Philbin. Facenet: A unified embedding for face recognition and clustering. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. [DOI:10.1109/CVPR.2015.7298682]
3. Boutros, F., et al., Synthetic data for face recognition: Current state and future prospects. Image and Vision Computing, 2023: p. 104688. [DOI:10.1016/j.imavis.2023.104688]
4. Alansari, M., et al., GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations. IEEE Access, 2023. 11: p. 35429-35446. [DOI:10.1109/ACCESS.2023.3266068]
5. Ahmadi, MA., Dianat, R., Introducing a method for extracting features from facial images based on applying transformations to features obtained from convolutional neural networks. Signal and Data Processing, 2020. 17(3): p. 141-156. [DOI:10.29252/jsdp.17.3.141]
6. احمدی، مرتضیعلی، و دیانت، روح الله. (1399). ارائه یک روش استخراج ویژگی از تصاویر چهره مبتنی بر اعمال تبدیل روی ویژگی های به دست آمده از شبکه های عصبی کانولوشن. پردازش علایم و داده ها، 17(3 (پیاپی 45) )، 141-156.
7. Yang, S., et al., Faceness-net: Face detection through deep facial part responses. IEEE transactions on pattern analysis and machine intelligence, 2017. 40(8): p. 1845-1859. [DOI:10.1109/TPAMI.2017.2738644]
8. Zhang, K., et al., Joint face detection and alignment using multitask cascaded convolutional networks. IEEE signal processing letters, 2016. 23(10): p. 1499-1503. [DOI:10.1109/LSP.2016.2603342]
9. Hu, P. and D. Ramanan. Finding tiny faces. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. [DOI:10.1109/CVPR.2017.166]
10. Mamieva, D., et al., Improved face detection method via learning small faces on hard images based on a deep learning approach. Sensors, 2023. 23(1): p. 502. [DOI:10.3390/s23010502]
11. Si, T., F. He, and P. Li, Hybrid feature constraint with clustering for unsupervised person re-identification. The Visual Computer, 2022. [DOI:10.1007/s00371-022-02649-1]
12. Zhao, W., et al., Face recognition: A literature survey. ACM computing surveys (CSUR), 2003. 35(4): p. 399-458. [DOI:10.1145/954339.954342]
13. Campadelli, P., R. Lanzarotti, and C. Savazzi. A feature-based face recognition system. in 12th International Conference on Image Analysis and Processing, 2003. Proceedings. 2003. IEEE.
14. Bern, M. and D. Eppstein, Mesh generation and optimal triangulation, in Computing in Euclidean geometry. 1995, World Scientific. p. 47-123. [DOI:10.1142/9789812831699_0003]
15. Yim, J., et al. Rotating your face using multi-task deep neural network. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
16. Jin, X. and X. Tan, Face alignment in-the-wild: A survey. Computer Vision and Image Understanding, 2017. 162: p. 1-22. [DOI:10.1016/j.cviu.2017.08.008]
17. Galbally, J. and S. Marcel. Face anti-spoofing based on general image quality assessment. in 2014 22nd international conference on pattern recognition. 2014. IEEE. [DOI:10.1109/ICPR.2014.211]
18. Galbally, J., S. Marcel, and J. Fierrez, Biometric antispoofing methods: A survey in face recognition. IEEE Access, 2014. 2: p. 1530-1552. [DOI:10.1109/ACCESS.2014.2381273]
19. Yu, Z., et al. Flexible-modal face anti-spoofing: A benchmark. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023. [DOI:10.1109/CVPRW59228.2023.00675]
20. Zhou, E., Z. Cao, and Q. Yin, Naive-deep face recognition: Touching the limit of LFW benchmark or not? arXiv preprint arXiv:1501.04690, 2015.
21. Jalal, A.S., D.K. Sharma, and B. Sikander, Suspect face retrieval using visual and linguistic information. The Visual Computer, 2022: p. 1-27. [DOI:10.1007/s00371-022-02482-6]
22. Nasution, M.I.P., et al. Face recognition login authentication for digital payment solution at COVID-19 pandemic. in 2020 3rd International Conference on Computer and Informatics Engineering (IC2IE). 2020. IEEE. [DOI:10.1109/IC2IE50715.2020.9274654]
23. Talahua, J.S., et al., Facial recognition system for people with and without face mask in times of the covid-19 pandemic. Sustainability, 2021. 13(12): p. 6900. [DOI:10.3390/su13126900]
24. Wang, F., et al., NormFace: L2 Hypersphere Embedding for Face Verification, in Proceedings of the 25th ACM international conference on Multimedia. 2017, Association for Computing Machinery: Mountain View, California, USA. p. 1041-1049. [DOI:10.1145/3123266.3123359]
25. Liu, W., et al., Large-margin softmax loss for convolutional neural networks. arXiv preprint arXiv:1612.02295, 2016.
26. Liu, W., et al. Sphereface: Deep hypersphere embedding for face recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. [DOI:10.1109/CVPR.2017.713]
27. Wang, F., et al. Normface: L2 hypersphere embedding for face verification. in Proceedings of the 25th ACM international conference on Multimedia. 2017. [DOI:10.1145/3123266.3123359]
28. Wang, H., et al. Cosface: Large margin cosine loss for deep face recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2018. [DOI:10.1109/CVPR.2018.00552]
29. Deng, J., et al. Arcface: Additive angular margin loss for deep face recognition. in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019. [DOI:10.1109/CVPR.2019.00482]
30. He, L., et al. Softmax dissection: Towards understanding intra-and inter-class objective for embedding learning. in Proceedings of the AAAI Conference on Artificial Intelligence. 2020. [DOI:10.1609/aaai.v34i07.6729]
31. Zhang, X., et al. Accelerated training for massive classification via dynamic class selection. in Proceedings of the AAAI Conference on Artificial Intelligence. 2018. [DOI:10.1609/aaai.v32i1.12337]
32. An, X., et al. Partial fc: Training 10 million identities on a single machine. in Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021. [DOI:10.1109/ICCVW54120.2021.00166]
33. Wu, Y., et al. Deep convolutional neural network with independent softmax for large scale face recognition. in Proceedings of the 24th ACM international conference on Multimedia. 2016. [DOI:10.1145/2964284.2984060]
34. Cao, Q., et al. Vggface2: A dataset for recognising faces across pose and age. in 2018 13th IEEE international conference on automatic face & gesture recognition (FG 2018). 2018. IEEE. [DOI:10.1109/FG.2018.00020]
35. Guo, Y., et al. Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. in Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14. 2016. Springer. [DOI:10.1007/978-3-319-46487-9_6]
36. Hadsell, R., S. Chopra, and Y. LeCun. Dimensionality reduction by learning an invariant mapping. in 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06). 2006. IEEE.
37. Nguyen, B., C. Morell, and B. De Baets, Distance metric learning for ordinal classification based on triplet constraints. Knowledge-Based Systems, 2018. 142: p. 17-28. [DOI:10.1016/j.knosys.2017.11.022]
38. Wen, Y., et al. A discriminative feature learning approach for deep face recognition. in Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part VII 14. 2016. Springer.
39. Wang, K., et al. An efficient training approach for very large scale face recognition. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022. [DOI:10.1109/CVPR52688.2022.00405]
40. Liu, Y. and Q. Liu. Convolutional neural networks with large-margin softmax loss function for cognitive load recognition. in 2017 36th Chinese control conference (CCC). 2017. IEEE. [DOI:10.23919/ChiCC.2017.8027991]
41. Dietterich, T.G. and G. Bakiri, Solving multiclass learning problems via error-correcting output codes. Journal of artificial intelligence research, 1994. 2: p. 263-286. [DOI:10.1613/jair.105]
42. Zhang, Q., et al. Large scale classification in deep neural network with label mapping. in 2018 IEEE International Conference on Data Mining Workshops (ICDMW). 2018. IEEE. [DOI:10.1109/ICDMW.2018.00163]
43. Xu, Y., et al. High performance large scale face recognition with multi-cognition softmax and feature retrieval. in Proceedings of the IEEE International Conference on Computer Vision Workshops. 2017. [DOI:10.1109/ICCVW.2017.224]
44. He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. [DOI:10.1109/CVPR.2016.90]
45. Tim, E. Face Recognition Using Pytorch. 2022 2023/11/02; Available from: https://github.com/timesler/facenet-pytorch.
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
