Siamese Model-Based Face Verification Using CNN and MobileNetV2
DOI:
https://doi.org/10.29207/resti.v10i2.6996Keywords:
convolutional neural network, face verification, MobileNetV2, real-time, siamese neural networkAbstract
Face verification plays an important role in computer vision, especially in mobile and embedded systems with limited computational capacity. This study proposes a face verification system based on the Siamese Neural Network (SNN) architecture by integrating six embedding models. These models consist of a standard CNN, an L2-normalized CNN, a baseline MobileNetV2, a structurally adjusted MobileNetV2, a pre-trained MobileNetV2, and a fine-tuned MobileNetV2. The dataset includes facial images captured from three webcams and additional samples obtained from the Labeled Faces in the Wild and ImageNet datasets. The experimental procedure includes image preprocessing, construction of balanced positive and negative image pairs, model training, and evaluation using accuracy, precision, recall, F1-score, and AUC. The results show that the pre-trained MobileNetV2 and the standard CNN achieve the highest verification accuracy, reaching 100 percent and 99.998 percent, respectively. Among all models, the structurally adjusted MobileNetV2 presents the best trade-off by combining high accuracy, computational efficiency, and training stability while successfully avoiding overfitting. The real-time implementation involves only the structurally adjusted MobileNetV2 model due to its lightweight structure and consistent performance. This model produces low embedding distances, low latency, and high throughput during CPU-based inference. The performance outperforms GPU execution in one-by-one image processing. The proposed system offers a practical and efficient face verification solution for deployment in identity authentication applications on resource-constrained platforms. These findings support the development of scalable and adaptive biometric security systems that rely on deep learning.
Downloads
References
D. Zeng, R. Veldhuis, L. Spreeuwers, and R. Arendsen, “Occlusion-invariant face recognition using simultaneous segmentation,” IET Biometrics, vol. 10, pp. 679–691, 2021, doi: 10.1049/BME2.12036.
Q. Zhou, T. Lu, Y. Zhang, Z. Xiong, H. Chen, and Y. Wu, “Context-aware based discriminative Siamese Neural Network for face verification,” in Proceedings of the International Conference on Pattern Recognition, pp. 113–124, 2020, doi: 10.1007/978-3-030-56178-9_9.
T. Lu, Q. Zhou, W. Fang, and Y. Zhang, “Discriminative metric learning for face verification using enhanced Siamese neural network,” Multimedia Tools and Applications, vol. 80, pp. 8563–8580, 2020, doi: 10.1007/s11042-020-09784-8.
R. Zong, “On privileged information driven robust face verification: A Siamese convolutional neural network approach,” in Proceedings of the 2020 IEEE International Conference on Big Data (Big Data), pp. 5874–5878, 2020, doi: 10.1109/BigData50022.2020.9378074.
M. Liu, “Masked Face Recognition Using MobileNetV2,” in Proceedings of the 2022 International Conference on Computing and Data Science, 2022, doi: 10.1145/3561613.3561650.
A. S. Mohammad, T. G. Jarullah, M. T. S. Al-Kaltakchi, J. Alshehabi Al-Ani, and S. Dey, “IoT-MFaceNet: Internet-of-Things-Based Face Recognition Using MobileNetV2 and FaceNet Deep-Learning Implementations on a Raspberry Pi-400,” Journal of Low Power Electronics and Applications, vol. 14, no. 3, Art. no. 46, 2024, doi: 10.3390/jlpea14030046.
A. A. A. Aboluhom and I. Kandilli, “Face recognition using deep learning on Raspberry Pi,” The Computer Journal, vol. 67, no. 10, pp. 3020–3030, 2024, doi: 10.1093/comjnl/bxae066.
F. Boutros, P. Siebke, M. Klemt, N. Damer, F. Kirchbuchner, and A. Kuijper, “PocketNet: Extreme lightweight face recognition network using neural architecture search and multistep knowledge distillation,” IEEE Access, vol. 10, pp. 46823–46833, 2022, doi: 10.1109/ACCESS.2022.3170561.
A. Tsai, Y.-Y. Ou, W.-C. Wu, and J.-F. Wang, “Integrated SSD and pre-trained CNN for partially occluded face recognition,” IEEE Access, vol. 9, pp. 164148–164158, 2021, doi: 10.1109/ACCESS.2021.3133446.
Q. Guo, “Occluded face recognition based on deep learning,” Frontiers in Computer Intelligence System., vol. 5, no. 2, 2023, doi: 10.54097/fcis.v5i2.13134.
M. Rodrigo, C. Cuevas, and N. García, “Comprehensive comparison between vision transformers and convolutional neural networks for face recognition tasks,” Scientific Reports, vol. 14, 2024, doi: 10.1038/s41598-024-72254-w.
F. Zhao, P. Zhang, R. Zhang, and M. Li, “DGFaceNet: Lightweight and efficient face recognition,” Engineering Applications of Artificial Intelligence, vol. 124, Art. no. 106513, 2023, doi: 10.1016/j.engappai.2023.106513.
M. Rouhsedaghat, Y. Wang, S. Hu, S. You, and C.-C. J. Kuo, “Low-Resolution Face Recognition in Resource-Constrained Environments,” Pattern Recognition Letters, vol. 149, pp. 193–199, 2021, doi: 10.1016/j.patrec.2021.05.009.
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,” Journal of Imaging, vol. 9, no. 2, Art. no. 21, 2023, doi: 10.3390/jimaging9020021.
J. Zhumagalieva and D. Kumalakov, “Face recognition with Siamese Neural Networks,” Journal of Problems in Computer Science and Information Technology, vol. 3, 2025, doi: 10.26577/jpcsit20253102.
Miftakhurrokhmat, R. A. Rajagede, and R. Rahmadi, “Classroom Attendance Based on Smiling Face Patterns and Nearby Wifi with Deep Learning,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 5, no. 1, pp. 31–38, 2021, doi: 10.29207/resti.v5i1.2575.
D. Liu, M. Liang, and Y. Guo, “Face recognition using CNN based on Euclidean distance,” Journal of Physics: Conference Series, vol. 1820, no. 1, Art. no. 012087, 2021, doi: 10.1088/1742-6596/1820/1/012087.
A. Zhalgas, B. Amirgaliyev, and A. Sovet, “Robust Face Recognition Under Challenging Conditions: A Comprehensive Review of Deep Learning Methods and Challenges,” Applied Sciences, vol. 15, no. 17, Art. no. 9390, 2025, doi: 10.3390/app15179390.
Z. Rasheed, H. Maqsood, K. S. Al-Maqroun, S. Ditta, M. Manzoor, and I. Ashraf, “Automated classification of brain tumors from magnetic resonance imaging using deep learning,” Brain Sciences, vol. 13, no. 4, Art. no. 602, 2023, doi: 10.3390/brainsci13040602.
S. Seenath and M. Dharmaraj, “Conformer-Based Human Activity Recognition Using Inertial Measurement Units,” Sensors, vol. 23, no. 17, Art. no. 7357, 2023, doi: 10.3390/s23177357.
S. Tehsin, A. Hassan, F. Riaz, I. M. Nasir, N. L. Fitriyani, and M. Syafrudin, “Enhancing Signature Verification Using Triplet Siamese Similarity Networks in Digital Documents,” Mathematics, vol. 12, no. 17, Art. no. 2757, 2024, doi: 10.3390/math12172757.
N. El Fadel, “Facial Recognition Algorithms: A Systematic Literature Review,” Journal of Imaging, vol. 11, no. 2, Art. no. 58, 2025, doi: 10.3390/jimaging11020058.
G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, “Labeled faces in the wild: A database for studying face recognition in unconstrained environments,” Technical Report 07-49, University of Massachusetts, Amherst, Oct. 2007. [Online]. Available: http://vis-www.cs.umass.edu/lfw/.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, Jun. 2018, pp. 4510–4520, doi: 10.1109/CVPR.2018.00474.
H. Kawai, K. Ito, H.-T. Chen, and T. Aoki, “FSErasing: Improving face recognition with data augmentation using face parsing,” IET Biometrics, 2024, doi: 10.1049/2024/6663315.
B. Desai and S. Satapathy, “Facial recognition using Siamese Neural Network and data augmentation techniques,” in Proceedings of the 2024 2nd World Conference on Communication & Computing (WCONF), IEEE, 2024, pp. 1–6, doi: 10.1109/WCONF61366.2024.10692075.
S. Jain, A. Pundir, S. Singh, and G. Saxena, “Exploring face recognition: A comparative study using loss-based methodologies,” in Proceedings of the 2023 IEEE 2nd International Conference on Data, Decision and Systems (ICDDS), IEEE, 2023, pp. 1–5, doi: 10.1109/ICDDS59137.2023.10434764.
S. Soleymani, B. Chaudhary, A. Dabouei, J. Dawson, and N. M. Nasrabadi, “Differential morphed face detection using deep Siamese networks,” in Lecture Notes in Computer Science (LNCS), vol. 12535, Springer, 2020, pp. 495–506, doi: 10.1007/978-3-030-68780-9_44.
B. Ciapas and P. Treigys, “Centre-loss: A preferred class verification approach over sample-to-sample in self-checkout products datasets,” IET Computer Vision, vol. 18, no. 1, pp. 1–12, 2024, doi: 10.1049/cvi2.12302.
H. Prashanth and M. Rao, “Roofline performance analysis of DNN architectures on CPU and GPU systems,” in Proceedings of the 2024 25th International Symposium on Quality Electronic Design (ISQED), IEEE, Mar. 2024, pp. 1–8, doi: 10.1109/ISQED60706.2024.10528752.
Z. Lyu, D. Zhang, and J. Luo, “A GPU-free real-time object detection method for apron surveillance video based on quantized MobileNet-SSD,” IET Image Processing, vol. 16, no. 8, pp. 2196–2209, 2022, doi: 10.1049/ipr2.12483.
C. Song, C. Ye, Y. Sim, and D. S. Jeong, “Hardware for Deep Learning Acceleration,” Advanced Intelligent Systems, vol. 6, no. 10, 2024, doi: 10.1002/aisy.202300762.
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
