Penerapan Algoritma MTCNN dan Facenet Pada Sistem Presensi Digital Berbasis Pengenalan Wajah
DOI:
https://doi.org/10.37859/coscitech.v7i2.11762
Abstract
Conventional attendance systems in higher education institutions still face various challenges, including low efficiency in attendance recording, a high risk of administrative errors, and the potential for fraudulent practices such as proxy attendance. This study aims to develop a digital attendance system based on facial recognition using deep learning technology to improve the accuracy, security, and effectiveness of student attendance processes. The research method employed is Design and Development Research (DDR), which includes the stages of needs analysis, system design, development, and evaluation. The system was developed by implementing the Multi-Task Cascaded Convolutional Networks (MTCNN) algorithm for face detection and FaceNet for facial feature extraction in the form of numerical embeddings. The testing results indicate that the system achieved an accuracy rate of 96%, precision of 100%, recall of 95%, and an F1-score of 97.4%, demonstrating excellent facial recognition performance. In addition, the system security evaluation produced a False Acceptance Rate (FAR) of 0%, indicating that the system successfully rejected all unregistered faces in the database. Meanwhile, the False Rejection Rate (FRR) of 5% indicates that recognition failures still occurred under certain conditions. Operational testing showed that the system performed optimally when faces were positioned frontally and captured at distances ranging from 30 cm to 100 cm. However, the system performance decreased under extreme face tilt conditions and at distances exceeding 150 cm. Based on the research findings, the proposed facial recognition-based digital attendance system is considered feasible for implementation.
Downloads
References
A. Alparisi and A. Maslan, “IMPLEMENTASI DEEP LEARNING DALAM SISTEM ABSENSI SISWA DENGAN FACE RECOGNITION,” JURNAL COMASIE, vol. 11, no. 03, 2024.
M. A. Khair, P. Aldiyuda, N. E. Pakpahan, M. Z. Zukhrufa, and M. Adrezo, “Perancangan Sistem Absensi Mahasiswa Berbasis Face Recognition di Lingkungan UPN Veteran Jakarta,” JURNAL INFORMATIK, pp. 35–42, 2024.
L. Susanti, N. K. Daulay, and B. Intan, “Sistem Absensi Mahasiswa Berbasis Pengenalan Wajah Menggunakan Algoritma YOLOv5,” JURIKOM (Jurnal Riset Komputer), vol. 10, no. 2, p. 640, Apr. 2023, doi: 10.30865/jurikom.v10i2.6032.
M. Hasyim Nasrun, “ANALISIS PENGGUNAAN TEKNOLOGI FACE ID DALAM SISTEM ABSENSI UNTUK MENINGKATKAN KETEPATAN WAKTU KEHADIRAN PESERTA DIDIK DI SMA NEGERI 14 MAKASSAR ANALYSIS OF THE USE OF FACE ID TECHNOLOGY IN THE ATTENDANCE SYSTEM TO IMPROVE THE TIMELINESS OF STUDENT ATTENDANCE AT PUBLIC HIGH SCHOOL 14 MAKASSAR,” VARIABLE RESEARCH JOURNAL, vol. 02, p. 1, 2025.
Q. Hasanah, A. Sucipto, S. A. Wulandari, A. F. Rosyady, and Asmunir, “Digital Signal Processing and Machine Learning for Exam Fraud Detection,” International Journal of Studies in Social Sciences and Humanities, vol. 2, no. 1, pp. 10–20, Jul. 2025, doi: 10.25047/ijossh.v2i1.5667.
K. D. Anggara, D. P. Kartikasari, and F. A. Bakhtiar, “Implementasi Algoritma MTCNN dalam Mekanisme Autentikasi berbasis Pengenalan Wajah,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 7, no. 8, pp. 3613–3621, 2023, [Online]. Available: http://j-ptiik.ub.ac.id
J. Yuan, P. Barmpoutis, and T. Stathaki, “Pedestrian Detection Using Integrated Aggregate Channel Features and Multitask Cascaded Convolutional Neural-Network-Based Face Detectors,” Sensors, vol. 22, no. 9, p. 3568, May 2022, doi: 10.3390/s22093568.
Y. Lou and F. Li, “Design of an online education student learning status evaluation model based on dual-improved neural networks,” Intelligent Systems with Applications, vol. 22, Jun. 2024, doi: 10.1016/j.iswa.2024.200370.
S. Serengil and A. Ozpinar, “CipherFace: A Fully Homomorphic Encryption-Driven Framework for Secure Cloud-Based Facial Recognition,” Feb. 2025, [Online]. Available: http://arxiv.org/abs/2502.18514
J. Zhang and N. Hu, “Accuracy and robustness evaluation of deep learning algorithms in facial recognition systems,” Systems and Soft Computing, vol. 7, Dec. 2025, doi: 10.1016/j.sasc.2025.200252.
J. Zhang, “Student Apartment Access Control System Based on MTCNN-FaceNet Algorithm,” Int. J. Comput. Intell. Appl., vol. 24, no. 01, Mar. 2025, doi: 10.1142/S1469026824500226.
A. R. Razalli et al., “Development of Prayer Mobile Application Software for The Hearing Impaired (Deaf) Based on Malaysian Sign Language,” International Journal of Academic Research in Business and Social Sciences, vol. 11, no. 6, 2021, doi: 10.6007/ijarbss/v11-i6/10243.
F. Handayani, B. Baidarus, S. Sunanto, B. A. Putra, C. Anggraini, and R. M. Taufiq, “Klasifikasi Citra Penyakit Daun Tomat Menggunakan Metode Convolutional Neural Network (CNN) Dengan Arsitektur VGG-19,” Jurnal CoSciTech (Computer Science and Information Technology), vol. 6, no. 3, pp. 405–413, Dec. 2025, doi: 10.37859/coscitech.v6i3.10699.
R. Saputra, Y. Rianto, and M. R. Kusuma, “Tinjauan Penerapan CNN dan YOLO Pada Pengolahan Citra Agraria Medis Industri Cerdas,” Jurnal CoSciTech (Computer Science and Information Technology), vol. 7, no. 1, pp. 121–129, 2026, doi: 10.37859/coscitech.v7i1.10988.
V. Rajasekar et al., “Enhanced multimodal biometric recognition approach for smart cities based on an optimized fuzzy genetic algorithm,” Sci. Rep., vol. 12, no. 1, p. 622, Jan. 2022, doi: 10.1038/s41598-021-04652-3.
