Intelligent Proctoring System Based on Edge Computing

doi:10.3969/j.issn.1006-2475.2025.12.004

Abstract

Abstract: Abstract: To address the lack of remote supervision technologies, non-traceability of exam behavior, and difficulty in real-time verification of examinee identities in online remote examinations, this paper proposes an intelligent proctoring system based on edge computing. The system consists of exam terminals, teacher terminals, exam site servers, and a provincial service cluster. On the exam terminals, the CLAHE method is used to equalize image illumination before the images are transmitted to the model, with OpenVINO employed to accelerate the detection process. During the examination, the camera randomly captures desktop images containing the examinee’s face, and these images are processed by the model on the exam terminal. These images are temporarily stored on the exam site server, and after the exam, the records are sent to the provincial cluster server for post-exam verification. Experimental results demonstrate that the system has low hardware performance requirements, improves robustness to lighting variations, achieves a model accuracy of approximately 95%, and shows better fault tolerance in network performance. The system has already been deployed and applied in a remote border region.

Key words: Key words: edge computing, face recognition, behavior detection, real time invigilation, deep learning

CLC Number:

中图分类号:TP391.41

LI Jingyang1, XUE Huajian2, 3, YANG Yong1, REN Ge1. Intelligent Proctoring System Based on Edge Computing[J]. Computer and Modernization, 2025, 0(12): 26-31.

References

[1] 陈晋音,王桢,陈劲聿,等. 基于深度学习的智能教学系统的设计与研究[J]. 计算机科学, 2019,46(6A):550-554.
[2] 李伟,金梁. 基于WAMP架构的Web在线考试系统设计 [J]. 自动化技术与应用, 2023,42(5):162-165.
[3] 尹力威,王瀚林,雷奕达,等. 基于计算机视觉的学校智能监考系统[J]. 物联网技术, 2020,10(12):46-48.
[4] XUE J, WU W, CHENG Q K. Intelligent invigilator system based on target detection[J]. Multimedia Tools and Applications, 2023,23(82):44673-44695.
[5] 封彦,鲁磊. 基于YOLOV5和Dlib的在线违规行为监控识别算法[J]. 光电子技术, 2023,43(3):276-282.
[6] SU W X, LI L F, LIU F, et al. AI on the edge: A comprehensive review[J]. Artificial Intelligence Review, 2022,55(8):6125-6183.
[7] 李亚国,李冠良,张凯,等. 基于人工智能与边缘代理的物联网框架设计[J]. 计算机工程, 2023,49(10):313-320.
[8] LIN R P, XIE T Z, LUO S, et al. Energy-efficient computation offloading in collaborative edge computing[J]. IEEE Internet of Things Journal, 2022,9(21):21305-21322.
[9] SONG S X. Construction of university online examination system based on cloud computing technology[J]. Scientific Programming, 2021,2021. DOI: 10.1155/2021/7849255.
[10] DENG C L, FANG X M, WANG X B, et al. Software orchestrated and hardware accelerated artificial intelligence: Toward low latency edge computing[J]. IEEE Wireless Communications, 2022,29(4):110-117.
[11] OMETOV A, MOLUA O L, KOMAROV M, et al. A survey of security in cloud, edge, and fog computing[J]. Sensors(Basel), 2022,22(3). DOI: 10.3390/s22030927.
[12] 肖国亮,李汉才,程煜. 大规模考试信息化监考系统的设计与应用 [J]. 中国考试, 2019,324(4):41-45.
[13] 熊宗杨,薛学斌,王欣,等. 基于过程化考核的在线考试系统的研究与实现[J]. 重庆师范大学学报(自然科学版), 2018,35(6):75-81.
[14] SPARKS J. Enabling Docker for HPC [J]. Concurrency and Computation: Practice and Experience, 2019,31(16):e5018.
[15] DENG S G, ZHAO H L, FANG W J, et al. Edge intelligence: The confluence of edge computing and artificial intelligence [J]. IEEE Internet of Things Journal, 2020,7(8):7457-7469.
[16] OROCEO P P, KIM J I, CALIWAG E M F, et al. Optimizing face recognition inference with a collaborative edge-cloud network[J]. Sensors (Basel), 2022,22(21). DOI: 10.3390/s22218371.
[17] DENG J K, GUO J, YANG J, et al. ArcFace: Additive angular margin loss for deep face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022,44(10):5962-5979.
[18] JIAO J C, LIU W L, MO Y K, et al. Dyn-arcFace: Dynamic additive angular margin loss for deep face recognition[J]. Multimedia Tools and Applications, 2021,80(17):25741-25756.
[19] ROBERTO M D, HORMANN K. Histogram equalization using a selective filter[J]. The Visual Computer, 2023,39(12):6221-6235.
[20] IBRAHIM M H, SAYAGH M, HASSAN A E. A study of how Docker compose is used to compose multi-component systems[J]. Empirical Software Engineering, 2021,26(6). DOI: 10.1007/S10664-021-10025-1.
[21] 陈轶阳,王小宁,卢莎莎,等. 面向高性能计算系统的容器技术综述[J]. 计算机科学, 2023,50(2):353-363.
[22] DEMIDOVSKIJ A, GORBACHEV Y, FEDOROV M, et al. OpenVINO deep learning workbench: Comprehensive analysis and tuning of neural networks inference[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision Workshops. IEEE, 2019:783-787.
[23] 吴逸文,张洋,王涛,等. 从Docker容器看容器技术的发展:一种系统文献综述的视角[J]. 软件学报, 2023,34(12):5527-5551.
[24] MENG Q, ZHAO S C, HUANG Z D, et al. MagFace: A universal representation for face recognition and quality assessment[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2021:14225-14234.
[25] HUANG Y G, WANG Y H, TAI Y, et al. CurricularFace: Adaptive curriculum learning loss for deep face recognition[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE， 2020:5901-5910.
[26] JAISWAL S K, AGRAWAL R. A comprehensive review of YOLOv5: Advances in real-time object detection[J]. International Journal of Innovative Research in Computer Science and Technology, 2024,12(3):75-80.