Arsitektur Verifikasi Biometrik Menggunakan YOLOv8 dan ArcFace untuk Validasi Identitas pada Platform Ta’aruf Islami Zawajna
DOI:
https://doi.org/10.26905/jisad.v4i2.17744Keywords:
Biometrics;, YOLOv8;, ArcFace;, Ta’aruf;Abstract
This research aims to implement a facial biometric verification system on an Islamic matchmaking platform Zawajna to prevent profile identity fraud or catfishing. The system works by validating the authenticity of each new profile picture uploaded by the user against a previously verified genuine face serving as master data. Model performance testing was conducted using 79 image datasets consisting of 33 genuine subject images and 46 imposter images. This study comparatively evaluates four combinations of face detection and recognition architectures: RetinaFace with ArcFace, YOLOv8 with ArcFace, YOLOv8 with FaceNet, and YOLOv8 with GhostFaceNet. The main evaluation metrics include Accuracy, Precision, Recall, and execution speed. The evaluation results showed that RetinaFace + ArcFace achieved the highest accuracy (88.61%) but was highly inefficient with extreme computational time spikes of over 700 seconds. In contrast, the YOLOv8 + ArcFace architecture is recommended as a solution providing a well-balanced performance trade-off. This model produced 87.34% Accuracy, 84.85% Precision, and 84.85% Recall, supported by a stable average processing time of under 3 seconds. This combination has proven to be efficient and demonstrates adequate reliability for real-time profile identity validation operations within the scope of this limited testing.
Downloads
References
[1] O. o, “Online Matchmaking Using Collaborative Filtering an Reciprocal Recommender Systems,” vol. 7, no. 2, 2018.
[2] E. B. Pramana dan A. Sunandar, “Analisa rancang bangun aplikasi biro jodoh islami menggunakan algoritma profile matching berdasarkan platform android,” Arcitech J. Comput. Sci. Artif. Intell., vol. 2, no. 2, hal. 123, Dec. 2022, doi: 10.29240/arcitech.v2i2.5834.
[3] C. E. Putri dan R. E. Hamzah, “Analisis fenomena penipuan identitas diri (catfishing) pada literasi digital pengguna media sosial”.
[4] K. Verma, R. Kumar, A. P. Rao, dan R. Ranjan, “Efficient e-KYC Authentication System: Redefining Customer Verification in Digital Banking,” dalam 2023 9th International Conference on Signal Processing and Communication (ICSC), NOIDA, India: IEEE, Dec. 2023, hal. 319–324. doi: 10.1109/ICSC60394.2023.10441596.
[5] B. T. Utomo, I. Fitri, dan E. Mardiani, “Penerapan face recognition pada aplikasi akademik online,” 2020.
[6] J. Deng, J. Guo, E. Ververas, I. Kotsia, and S. Zafeiriou, “RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild,” dalam 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA: IEEE, Jun. 2020, hal. 5202–5211. doi: 10.1109/CVPR42600.2020.00525.
[7] J. Deng, J. Guo, N. Xue, dan S. Zafeiriou, “ArcFace: Additive Angular Margin Loss for Deep Face Recognition”.
[8] M. Alansari, O. A. Hay, S. Javed, A. Shoufan, Y. Zweiri, dan N. Werghi, “GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations,” IEEE Access, vol. 11, hal. 35429–35446, 2023, doi: 10.1109/ACCESS.2023.3266068.
[9] J. Terven, D.-M. Córdova-Esparza, dan J.-A. Romero-González, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Mach. Learn. Knowl. Extr., vol. 5, no. 4, hal. 1680–1716, Nov. 2023, doi: 10.3390/make5040083.
[10] A. K. Jain, D. Deb, dan J. J. Engelsma, “Biometrics: Trust, But Verify,” IEEE Trans. Biom. Behav. Identity Sci., vol. 4, no. 3, hal. 303–323, Jul. 2022, doi: 10.1109/TBIOM.2021.3115465.
[11] M. Wang dan W. Deng, “Deep face recognition: A survey,” Neurocomputing, vol. 429, hal. 215–244, Mar. 2021, doi: 10.1016/j.neucom.2020.10.081.
[12] R. Padilla, S. L. Netto, dan E. A. B. Da Silva, “A Survey on Performance Metrics for Object-Detection Algorithms,” dalam 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), Niterói, Brazil: IEEE, Jul. 2020, hal. 237–242. doi: 10.1109/IWSSIP48289.2020.9145130.
[13] J. Patil, “Fake Profile Detection on Social Media using Machine Learning”.
[14] S. Raschka, Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python, 1 ed. Birmingham: Packt Publishing Limited, 2022.
[15] S. I. Serengil dan A. Ozpinar, “LightFace: A Hybrid Deep Face Recognition Framework,” dalam 2020 Innovations in Intelligent Systems and Applications Conference (ASYU), Istanbul, Turkey: IEEE, Okt. 2020, hal. 1–5. doi: 10.1109/ASYU50717.2020.9259802.
[16] Supiyandi Supiyandi, Adinda Fita Hidayah, Luthfie Budie, Nurhalijah Berutu, dan Fakhita Fahraini, “Pengenalan Gambar Dasar Menggunakan Python dan OpenCV,” J. Sist. Inf. Dan Ilmu Komput., vol. 2, no. 4, hal. 52–61, Nov. 2024, doi: 10.59581/jusiik-widyakarya.v2i4.4200.
[17] C. R. Harris et al., “Array programming with NumPy,” Nature, vol. 585, no. 7825, hal. 357–362, Sep. 2020, doi: 10.1038/s41586-020-2649-2.
[18] A. Tharwat, “Classification assessment methods,” Appl. Comput. Inform., vol. 17, no. 1, hal. 168–192, Jan. 2021, doi: 10.1016/j.aci.2018.08.003.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information System and Application Development
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish in this journal agree to the following terms:
(1) Copyright of the published articles will be transferred to the journal as the publisher of the manuscripts. Therefore, the author confirms that the journal has managed the copyright.
(2) Publisher of JISAD: Journal of Information System and Application Development is the University of Merdeka Malang.
(3) The copyright follows Creative Commons Attribution ShareAlike License (CC BY SA): This license allows to Share - copy and redistribute the material in any medium or format, Adapt - remix, transform, and build upon the material, for any purpose, even commercially.
