Sistem Absensi Pengenalan Wajah Real-Time Menggunakan Algoritma YOLOv8 dan FaceNet
Abstrak
Beberapa studi telah mengeksplorasi integrasi teknologi pengenalan wajah ke dalam sistem absensi untuk mengatasi keterbatasan metode absensi manual, seperti ketidakakuratan dan kecurangan, termasuk penggantian absensi. Terlepas dari kemajuan ini, evaluasi komprehensif yang membandingkan metrik kinerja sistem, khususnya kecepatan deteksi dan akurasi pengenalan, masih terbatas. Studi ini bertujuan untuk mengatasi kesenjangan ini dengan mengembangkan sistem absensi berbasis pengenalan wajah secara real-time yang memanfaatkan You Only Look Once versi 8 (YOLOv8) dan algoritma FaceNet. Proses penelitian dimulai dengan pengumpulan data dan literatur, diikuti dengan pra-pemrosesan dataset Labeled Faces in the Wild (LFW) ke dalam format yang sesuai. Dua konfigurasi model kemudian diimplementasikan: YOLOv8+FaceNet dan Dlib-ResNet, yang masing-masing digunakan untuk deteksi wajah dan pengenalan wajah. Kinerja sistem dievaluasi dalam hal akurasi pengenalan dan kecepatan pemrosesan untuk menilai kelayakannya untuk aplikasi dunia nyata. Hasil eksperimen menunjukkan bahwa model YOLOv8+FaceNet mencapai Equal Error Rate (EER) sebesar 0,013, dengan False Acceptance Rate (FAR) sebesar 0,010 dan False Rejection Rate (FRR) sebesar 0,016 pada ambang batas optimal 0,4273. Sementara itu, model Dlib-ResNet memperoleh EER sebesar 0,010, dengan nilai FAR dan FRR masing-masing sebesar 0,008 dan 0,012, pada ambang batas optimal 0,3909. Evaluasi kinerja menggunakan ambang batas yang dioptimalkan menunjukkan bahwa model YOLOv8+FaceNet yang diusulkan mencapai akurasi pengenalan yang sedikit lebih tinggi daripada Dlib-ResNet, yaitu 98,7% dibandingkan dengan 98,6%.
Kata kunci: absensi, pengenalan wajah, yolo, facenet, dlib-resnet, biometrik.
Referensi
A. Mufron and Z. Wei, “Applying biometric technology in school attendance and security management,” Al-Hijr: Journal of Adulearn World, vol. 3, no. 2, 2024.
Z. Yernazarov, “Development of a contemporary access control system using face recognition,” Journal of Problems in Computer Science and Information Technologies, vol. 1, no. 3, 2023.
M. M. Hidayat, A. A. Mubarrok, B. P. B. Utomo, and M. I. Zacharia, “Online presence system design based on data granted validity,” Journal of Information Systems, Digitization and Business, vol. 1, no. 1, pp. 8–14, 2022.
P. Shrivastav, A. Singh, A. Sharma, C. Gupta, L. Banda, and K. Jain, “A systematic review and research perspective on attendance management system,” 2024.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” arXiv preprint, 2015.
F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A unified embedding for face recognition and clustering,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 815–823.
G. F. Mumtaz, J. Zeniarja, A. Luthfiarta, and A. N. I. Muttaqin, “Optimizing face recognition and emotion detection in student identification using FaceNet and YOLOv8 models,” INFORM: Jurnal Ilmiah Teknologi Informasi dan Komunikasi, vol. 10, no. 1, pp. 34–44, 2025.
A. G. Putrada and M. Abdurohman, “Increasing the security of RFID-based classroom attendance system with Shamir secret share,” International Journal on Information and Communication Technology (IJoICT), vol. 6, no. 1, pp. 10–22, 2020.
A. G. Putrada and N. G. Ramadhan, “A proposed hidden Markov model method for dynamic device pairing on Internet of Things end devices,” Journal of ICT Research and Applications, vol. 14, no. 3, 2021.
H. Bagaskara, A. G. Putrada, and E. Ariyanto, “Proximity and dynamic device pairing based authentication for IoT end devices with decision tree method,” in Proc. 6th Int. Conf. Interactive Digital Media (ICIDM), 2020, pp. 1–5.
N. G. Pham, N. L. Bui, Q. H. Tran, L. T. H. Tong, and H. N. Tran, “An effective approach to face recognition with artificial intelligence and the Internet of Things using NVIDIA Jetson Nano,” Dalat University Journal of Science, pp. 39–64, 2024.
B. P. Prayogo, E. Mulyana, W. Hermawan, et al., “A novel approach for face recognition: YOLO-based face detection and FaceNet,” in Proc. 9th Int. Conf. Wireless and Telematics (ICWT), 2023, pp. 1–6.
K. P. Hasaraddi, G. Thambkar, A. P. Bidargaddi, A. P. Patil, and G. Betageri, “YOLOv8-enhanced facial recognition for one-shot learning attendance system,” in Proc. 5th Int. Conf. Emerging Technology (INCET), 2024, pp. 1–7.
K. N. Lam, T. T. La, K. D. Nguyen, M. M. Le, V. T. Truong, and A. Ware, “Monitoring attendance and checking school uniforms using YOLOv8,” in Proc. Int. Conf. Intelligent Systems and Data Science, 2023, pp. 200–207.
T.-N. Pham, N.-P. Nguyen, N.-M.-Q. Dinh, and T. Le, “Tracking student attendance in virtual classes based on MTCNN and FaceNet,” in Proc. Asian Conf. Intelligent Information and Database Systems, 2022, pp. 382–394.
W. Kuang and A. Baul, “A real-time attendance system using deep-learning face recognition,” in Proc. ASEE Virtual Annual Conf., Jun. 2020.
G. B. Huang, M. Mattar, T. Berg, and E. Learned-Miller, “Labeled faces in the wild: A database for studying face recognition in unconstrained environments,” in Workshop on Faces in Real-Life Images: Detection, Alignment, and Recognition, 2008.
W. Xu, H. Li, G. Li, Y. Ji, J. Xu, and Z. Zang, “Improved YOLOv8n-based bridge crack detection algorithm under complex background conditions,” Scientific Reports, vol. 15, no. 1, pp. 1–18, 2025.
T. Li, Y. Zhang, Q. Li, and T. Zhang, “AB-DLM: An improved deep learning model based on attention mechanism and BiFPN for driver distraction behavior detection,” IEEE Access, vol. 10, pp. 83138–83151, 2022.
L. Han, X. Ma, M. Dai, and L. Bai, “A WAD-YOLOv8-based method for classroom student behavior detection,” Scientific Reports, vol. 15, no. 1, pp. 1–15, 2025.
M. M. I. Al-Ghiffary, N. R. D. Cahyo, E. H. Rachmawanto, C. Irawan, and N. Hendriyanto, “Adaptive deep learning based on FaceNet convolutional neural network for facial expression recognition,” Journal of Soft Computing Exploration, vol. 5, no. 3, pp. 271–280, 2024.
M. Xu, D. Chen, and G. Zhou, “Real-time face recognition based on Dlib,” in Innovative Computing (IC 2020), 2020, pp. 1451–1459.
Y. Yang and F. Fan, “Ancient thangka Buddha face recognition based on the Dlib machine learning library and comparison with secular aesthetics,” Heritage Science, vol. 11, no. 1, pp. 1–16, 2023.
L. Zhang, X. Wang, E. Cooper, N. Evans, and J. Yamagishi, “Range-based equal error rate for spoof localization,” arXiv preprint arXiv:2305.17739, 2023.
H. V. Dixit, A. Saxena, D. S. Sharma, et al., “Face recognition-based attendance system,” 2024.
G. Sunitha, V. S. Priya, V. S. Kumar, G. G. Priya, and T. N. Kumar, “Road object detection using YOLOv8,” in Proc. 5th Int. Conf. Electronics and Sustainable Communication Systems (ICESC), 2024, pp. 847–853.
M. Bae, A. Razdan, and G. E. Farin, “Automated 3D face authentication and recognition,” in Proc. IEEE Conf. Advanced Video and Signal-Based Surveillance, 2007, pp. 45–50.
H.-R. Chou, J.-H. Lee, Y.-M. Chan, and C.-S. Chen, “Data-specific adaptive threshold for face recognition and authentication,” in Proc. IEEE Conf. Multimedia Information Processing and Retrieval (MIPR), 2019, pp. 153–156.
