AI-based Efficient Hallway Attendance Monitoring using Confidence-driven Face Recognition

Mokhamad Arfan Wicaksono (Software Engineering Technology Department, Akademi Digital Bandung, Jalan Rancamekar Blok Lio, Kel. Cipamokolan, Kec. Rancasari, Bandung 40292)
Ibrahim Faizal Burhan (Software Engineering Technology Department, Akademi Digital Bandung, Jalan Rancamekar Blok Lio, Kel. Cipamokolan, Kec. Rancasari, Bandung 40292)
Hadi Permana (Akademi Digital Bandung)
Muhung Anggarawan (Software Engineering Technology Department, Akademi Digital Bandung, Jalan Rancamekar Blok Lio, Kel. Cipamokolan, Kec. Rancasari, Bandung 40292)
Bakhriyah Firdausi (Software Engineering Technology Department, Akademi Digital Bandung, Jalan Rancamekar Blok Lio, Kel. Cipamokolan, Kec. Rancasari, Bandung 40292)
Muhamad Naufal Azwar Iftikar (School of Computer Science, The University of Sydney, 1 Cleveland Street, Darlington, NSW 2008,)
Ratnasari Nur Rohmah (Department of Electrical Engineering, Universitas Muhammadiyah Surakarta, Jalan Ahmad Yani, Tromol Pos 1, Pabelan, Kartasura, Sukoharjo 57169)
Yoanes Bandung (School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Jalan Ganesa No. 10, Bandung 40132)

Journal of ICT Research and Applications
Vol. 20 No. 3 (2026)

Attendance monitoring deployed at entrance areas offers reliable tracking for institutional environments. We propose an efficient face-recognition-based framework combining YOLOv11-based face detection, motion-based tracking, and FaceNet-based recognition. Our key contribution is a confidence-driven face selection method that collects multiple face images per track and selects the highest-quality image for recognition. Experiments on real-world 60-second hallway footage (1,800 frames at 30 FPS) demonstrated up to 77.7% improvement in processing speed (79.36 FPS vs. 44.66 FPS baseline) while maintaining equivalent recognition accuracy. Collection windows of 5 to 7 images provide optimal balance between latency and throughput (73.67–75.86 FPS), demonstrating that strategic recognition frequency reduction enables real-time attendance monitoring suitable for resource-constrained environments