Performance Analysis of Smart Technology with Face Detection using YOLOv3 and InsightFace for Student Attendance Monitoring
Keywords:
YOLOv3, InsightFace, Face Detection, Classroom Monitoring, Real-time MonitoringAbstract
In this paper, we propose a comparative evaluation for smart technologies of two state-of-the-art face detection models, YOLOv3 and InsightFace (SCRFD-10GF), within a classroom environment for real-time monitoring applications. The primary objective of this study is to assess and compare the models' detection accuracy, robustness, and computational efficiency across various settings, including different camera positions and lighting conditions. We employ a dataset consisting of videos captured from three distinct classrooms—Lab 1, Lab 3, and Room 1—each presenting unique challenges such as obstructions (e.g., computers) and varying angles and lighting conditions. The study aims to address the challenge of comparing these models in real-world environments with demanding conditions. The results reveal that YOLOv3 consistently outperforms InsightFace in terms of confidence scores across all environments and camera positions. YOLOv3's superior architecture, featuring multi-scale detection and advanced feature extraction capabilities, enables it to maintain high accuracy and confidence, with an average confidence score reaching 0.83. InsightFace, though slightly less accurate, is advantageous in resource-constrained settings due to its lightweight architecture. The findings suggest that YOLOv3 is ideal for systems requiring high accuracy, while InsightFace is better suited for environments with limited computational resources. We conclude that a hybrid approach leveraging both models could offer a balanced solution tailored to specific requirements of educational environments.
Downloads
References
T. Luan and M. A. E. Damian, “A Study on the Application of Deep Learning-based Media Tampering Detection Technology in Higher Education Teaching Resource Protection,” Contemporary Education and Teaching Research, 2023, [Online]. Available: https://api.semanticscholar.org/CorpusID:259718600
L. Ni, J. Shi, B. Han, N. Zhang, Q. Lan, and Z. Su, “Classroom Roll Call System Based on Face Detection Technology,” 2022 10th International Conference on Information and Education Technology (ICIET), pp. 42–46, 2022, [Online]. Available: https://api.semanticscholar.org/CorpusID:249101012
M. A. M. Ali, T. Aly, A. T. Raslan, M. Gheith, and E. A. Amin, “Advancing Crowd Object Detection: A Review of YOLO, CNN and ViTs Hybrid Approach,” Journal of Intelligent Learning Systems and Applications, vol. 16, no. 3, pp. 175–221, 2024.
X. Zhang, X. Dong, Q. Wei, and K. Zhou, “Real-time object detection algorithm based on improved YOLOv3,” J Electron Imaging, vol. 28, no. 5, p. 53022, 2019.
S. Liu, Y. Xu, L. Guo, M. Shao, G. Yue, and D. An, “Multi-scale personnel deep feature detection algorithm based on Extended-YOLOv3,” Journal of Intelligent & Fuzzy Systems, vol. 40, no. 1, pp. 773–786, 2021.
N. Głowacka and J. Rumiński, “Face with Mask Detection in Thermal Images Using Deep Neural Networks,” Sensors, vol. 21, no. 19, 2021, doi: 10.3390/s21196387.
L. Tan, T. Huangfu, L. Wu, and W. Chen, “Comparison of RetinaNet, SSD, and YOLO v3 for real-time pill identification,” BMC Med Inform Decis Mak, vol. 21, no. 1, pp. 1–11, 2021, doi: 10.1186/s12911-021-01691-8.
R. Shamim and Y. Farhaoui, “An In-depth Comparative Study: YOLOv3 vs. Faster R-CNN for Object Detection in Computer Vision,” in Artificial Intelligence, Big Data, IOT and Block Chain in Healthcare: From Concepts to Applications, Y. Farhaoui, Ed., Cham: Springer Nature Switzerland, 2024, pp. 266–277.
K. Wang, M. Liu, and Z. Ye, “An advanced YOLOv3 method for small-scale road object detection,” Appl Soft Comput, vol. 112, p. 107846, 2021, doi: https://doi.org/10.1016/j.asoc.2021.107846.
D. Wanyonyi and T. Celik, “Open-source face recognition frameworks: A review of the landscape,” IEEE Access, vol. 10, pp. 50601–50623, 2022.
N. Sadman, K. A. Hasan, E. Rashno, F. Alaca, Y. Tian, and F. Zulkernine, “Vulnerability of Open-Source Face Recognition Systems to Blackbox Attacks: A Case Study with InsightFace,” in 2023 IEEE Symposium Series on Computational Intelligence (SSCI), 2023, pp. 1164–1169.
O. Yakovleva, A. Kovtunenko, V. Liubchenko, V. Honcharenko, and O. Kobylin, “Face Detection for Video Surveillance-based Security System,” in CEUR Workshop Proceedings, 2023, pp. 69–86.
J. Guo, J. Deng, and A. Lattas, “Sample and Computation Redistribution for Efficient Face Detection”.
K. Gkrispanis, N. Gkalelis, and V. Mezaris, “Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 280–289.
Z. Trabelsi, F. Alnajjar, M. M. A. Parambil, M. Gochoo, and L. Ali, “Real-Time Attention Monitoring System for Classroom: A Deep Learning Approach for Student’s Behavior Recognition,” Big Data and Cognitive Computing, vol. 7, no. 1, 2023, doi: 10.3390/bdcc7010048.
J.-H. Won, D. Lee, K.-M. Lee, and C.-H. Lin, “An Improved YOLOv3-based Neural Network for De-identification Technology,” 2019 34th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), pp. 1–2, 2019, [Online]. Available: https://api.semanticscholar.org/CorpusID:199540948
S. Mukherjee, T. Sharma, A. Singh, S. S. Gayathri, and S. Dhanalakshmi, “Multi-Pedestrian Detection using Hybrid ML Algorithms for Autonomous Vehicles,” 2023 International Conference on Recent Advances in Science and Engineering Technology (ICRASET), pp. 1–4, 2023, [Online]. Available: https://api.semanticscholar.org/CorpusID:267575819
M. Widiasri, A. Z. Arifin, N. Suciati, E. R. Astuti, and R. Indraswari, “Alveolar Bone Detection from Dental Cone Beam Computed Tomography using YOLOv3-tiny,” 2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS), pp. 1–6, 2021, [Online]. Available: https://api.semanticscholar.org/CorpusID:236191711
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
