Email this article 
(Universitas Negeri Semarang, Indonesia)(2) Anan Nugroho
(Universitas Negeri Semarang, Indonesia)(3) Subiyanto Subiyanto
(Universitas Negeri Semarang, Indonesia)(4) Arthur Gregorius Pongoh
(Universitas Negeri Semarang, Indonesia)*corresponding author
AbstractReal-time face recognition systems encounter a critical trade-off between high-security demands and computational efficiency, particularly when deployed in unconstrained open-set environments. This study presents a comprehensive benchmarking of four distinct deep learning backbones ResNet100, GhostFaceNet, LAFS, and TransFace specifically trained using the Adaptive Margin Loss (AdaFace) function to handle image quality variations. The primary objective is to identify the optimal architecture for secure attendance systems operating on standard hardware with limited training data. The evaluation protocol employs a rigorous real-world open-set test to quantify performance using False Acceptance Rate (FAR) and False Rejection Rate (FRR). The experimental results demonstrate that ResNet100 establishes the highest security standard, achieving a 0.00% FAR at strict thresholds. Meanwhile, GhostFaceNet emerges as the most balanced solution for resource-constrained deployments, delivering competitive accuracy above 93% with significantly lower computational complexity. Conversely, the Vision Transformer (TransFace) fails to generalize in this low-data regime, resulting in unacceptable false acceptance rates. These findings definitively recommend GhostFaceNet for efficient edge-based implementations, while ResNet100 remains the superior choice for mission-critical security applications. KeywordsFace recognition, Deep learning, Biometrics, Backbone networks, Open-Set Recognition
|
DOIhttps://doi.org/10.29099/ijair.v9i1.1.1641 |
Article metrics10.29099/ijair.v9i1.1.1641 Abstract views : 48 | PDF views : 0 |
Cite |
Full Text Download
|
References
M. Hassaballah and S. Aly, “Face recognition: Challenges, achievements and future directions,” Aug. 01, 2015, Institution of Engineering and Technology. doi: 10.1049/iet-cvi.2014.0084.
Y. Xu et al., “Artificial intelligence: A powerful paradigm for scientific research,” Nov. 28, 2021, Cell Press. doi: 10.1016/j.xinn.2021.100179.
A. K. . Jain, P. J. . Flynn, and A. A. . Ross, Handbook of biometrics. Springer, 2008.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” Dec. 2015, [Online]. Available: http://arxiv.org/abs/1512.03385
B. Prihasto et al., “A survey of deep face recognition in the wild,” in 2016 International Conference on Orange Technologies (ICOT), 2016, pp. 76–79. doi: 10.1109/ICOT.2016.8278983.
M. Wang and W. Deng, “Deep face recognition: A survey,” Neurocomputing, vol. 429, pp. 215–244, Mar. 2021, doi: 10.1016/j.neucom.2020.10.081.
A. Zhalgas, B. Amirgaliyev, and A. Sovet, “Robust Face Recognition Under Challenging Conditions: A Comprehensive Review of Deep Learning Methods and Challenges,” Sep. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/app15179390.
H. Lee, S. H. Park, J. H. Yoo, S. H. Jung, and J. H. Huh, “Face recognition at a distance for a stand-alone access control system,” Sensors (Switzerland), vol. 20, no. 3, Feb. 2020, doi: 10.3390/s20030785.
P. Chitrapu, M. Kumar Morampudi, and H. Kumar Kalluri, “Robust Face Recognition Using Deep Learning and Ensemble Classification,” IEEE Access, vol. 13, pp. 99957–99969, 2025, doi: 10.1109/ACCESS.2025.3575192.
F. Perez-Montes, J. Olivares-Mercado, G. Sanchez-Perez, G. Benitez-Garcia, L. Prudente-Tixteco, and O. Lopez-Garcia, “Analysis of Real-Time Face-Verification Methods for Surveillance Applications,” J Imaging, vol. 9, no. 2, Feb. 2023, doi: 10.3390/jimaging9020021.
M. Alansari, O. A. Hay, S. Javed, A. Shoufan, Y. Zweiri, and N. Werghi, “GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations,” IEEE Access, vol. 11, pp. 35429–35446, 2023, doi: 10.1109/ACCESS.2023.3266068.
S. Sunardi, A. Yudhana, and S. A. Wijaya, “Face Detection Analysis of Digital Photos Using Mean Filtering Method,” International Journal of Artificial Intelligence Research, vol. 6, no. 2, Jul. 2022, doi: 10.29099/ijair.v6i2.307.
J. Deng, J. Guo, N. Xue, and S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4685–4694. doi: 10.1109/CVPR.2019.00482.
M. Kim, A. K. Jain, and X. Liu, “AdaFace: Quality Adaptive Margin for Face Recognition,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 18729–18738. doi: 10.1109/CVPR52688.2022.01819.
Z. Sun, C. Feng, I. Patras, and G. Tzimiropoulos, “LAFS: Landmark-Based Facial Self-Supervised Learning for Face Recognition,” in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 1639–1649. doi: 10.1109/CVPR52733.2024.00162.
A. Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” Jun. 2021, [Online]. Available: http://arxiv.org/abs/2010.11929
J. Dan et al., “TransFace: Calibrating Transformer Training for Face Recognition from a Data-Centric Perspective,” Aug. 2023, [Online]. Available: http://arxiv.org/abs/2308.10133
S. Khan, M. Naseer, M. Hayat, S. W. Zamir, F. S. Khan, and M. Shah, “Transformers in Vision: A Survey,” Jan. 2022, doi: 10.1145/3505244.
H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, and H. Jégou, “Training data-efficient image transformers & distillation through attention,” 2021.
M. Rodrigo, C. Cuevas, and N. García, “Comprehensive comparison between vision transformers and convolutional neural networks for face recognition tasks,” Sci Rep, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-72254-w.
M. Huber, A. T. Luu, P. Terhörst, and N. Damer, “Efficient Explainable Face Verification based on Similarity Score Argument Backpropagation,” Nov. 2023, [Online]. Available: http://arxiv.org/abs/2304.13409
V. K. Hahn and S. Marcel, “Biometric Template Protection for Neural-Network-Based Face Recognition Systems: A Survey of Methods and Evaluation Techniques,” IEEE Transactions on Information Forensics and Security, vol. 18, pp. 639–666, 2023, doi: 10.1109/TIFS.2022.3228494.
S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine-learning-based science,” Patterns, vol. 4, no. 9, Sep. 2023, doi: 10.1016/j.patter.2023.100804.
A. Firmansyah, T. F. Kusumasari, and E. N. Alam, “Comparison of Face Recognition Accuracy of ArcFace, Facenet and Facenet512 Models on Deepface Framework,” in ICCoSITE 2023 - International Conference on Computer Science, Information Technology and Engineering: Digital Transformation Strategy in Facing the VUCA and TUNA Era, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 535–539. doi: 10.1109/ICCoSITE57641.2023.10127799.
J. Xiang and G. Zhu, “Joint Face Detection and Facial Expression Recognition with MTCNN,” in 2017 4th International Conference on Information Science and Control Engineering (ICISCE), 2017, pp. 424–427. doi: 10.1109/ICISCE.2017.95.
A. Paszke et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” Dec. 2019, [Online]. Available: http://arxiv.org/abs/1912.01703
C. R. Harris et al., “Array programming with NumPy,” Sep. 17, 2020, Nature Research. doi: 10.1038/s41586-020-2649-2.
F. Pedregosa FABIANPEDREGOSA et al., “Scikit-learn: Machine Learning in Python Gaël Varoquaux Bertrand Thirion Vincent Dubourg Alexandre Passos PEDREGOSA, VAROQUAUX, GRAMFORT ET AL. Matthieu Perrot,” 2011. [Online]. Available: http://scikit-learn.sourceforge.net.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
________________________________________________________
The International Journal of Artificial Intelligence Research
Organized by: Prodi Teknik Informatika Fakultas Teknologi Bisnis dan Sains
Published by: Universitas Dharma Wacana
Jl. Kenanga No. 03 Mulyojati 16C Metro Barat Kota Metro Lampung
Email: jurnal.ijair@gmail.com
This work is licensed under Creative Commons Attribution-ShareAlike 4.0 International License.