A Web-Based Smart Campus Identification Framework with YOLOv8n and Quality-Adaptive Temporal Face Fusion
Main Article Content
Abstract
Automated student identification in smart-campus environments requires dependable person localization, robust
facial matching, rejection of non-enrolled individuals, and practical web-based monitoring. Single-frame recognition can become
unreliable when surveillance imagery is affected by blur, low illumination, contrast variation, or over-exposure. This study
presents a web-based smart-campus identification framework that combines the nano configuration of You Only Look Once
version 8 person detection, FaceNet512 facial representation, and a training-free quality-temporal adaptive fusion mechanism
for open-set recognition. The proposed method evaluates consecutive face observations using sharpness, brightness suitability,
and contrast, retains the most informative frames, and combines their embeddings using quality-dependent softmax weights.
A sequence-quality score also controls an adaptive acceptance threshold for distinguishing enrolled students from unknown
individuals. Person detection was evaluated independently on the Common Objects in Context 128 subset, while open-set
recognition was assessed using a controlled Labeled Faces in the Wild protocol containing 15 enrolled and 10 unknown
identities. Under mixed image-quality conditions, the proposed configuration achieved 100 percent open-set identification
accuracy, compared with 90.00 percent for a randomly observed single-frame baseline, 98.33 percent for best-quality single
frame selection, and 93.33 percent for unweighted five-frame averaging. Unknown-person rejection increased from 86.67
percent to 100 percent relative to the random single-frame baseline. The detector obtained a mean average precision at 0.5
intersection-over-union of 0.7606 with approximately 3.73 milliseconds inference time per image in the recorded accelerator
experiment. These pilot results indicate that quality-aware temporal fusion can improve recognition robustness without retraining
the facial embedding model.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
IJCERT Policy:
The published work presented in this paper is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means that the content of this paper can be shared, copied, and redistributed in any medium or format, as long as the original author is properly attributed. Additionally, any derivative works based on this paper must also be licensed under the same terms. This licensing agreement allows for broad dissemination and use of the work while maintaining the author's rights and recognition.
By submitting this paper to IJCERT, the author(s) agree to these licensing terms and confirm that the work is original and does not infringe on any third-party copyright or intellectual property rights.
References
Mei Wang and Weihong Deng, “Deep face recognition: A survey,” Neurocomputing, vol. 429, pp. 215–244, 2021. DOI: 10.1016/j.neucom.2020.10.081.
Chuanxing Geng, Sheng-Jun Huang, and Songcan Chen, “Recent advances in open set recognition: A survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 10, pp. 3614–3631, 2021. DOI: 10.1109/TPAMI.2020.2981604.
Lacey Best-Rowden and Anil K. Jain, “Learning face image quality from human assessments,” IEEE Transactions on Information Forensics and Security, vol. 13, no. 12, pp. 3064–3077, 2018. DOI: 10.1109/TIFS.2018.2799585.
Shaolin Su, Hanhe Lin, Vlad Hosu, Oliver Wiedemann, Jinqiu Sun, Yu Zhu, Hantao Liu, Yanning Zhang, and Dietmar Saupe, “Going the extra mile in face image quality assessment: A novel database and model,” IEEE Transactions on Multimedia, vol. 26, pp. 2671–2685, 2024. DOI: 10.1109/TMM.2023.3301276.
Eric Lopez-Lopez, Xose M. Pardo, and Carlos V. Regueiro, “Incremental learning from low-labelled stream data in open-set video face recognition,” Pattern Recognition, vol. 131, Art. no. 108885, 2022. DOI: 10.1016/j.patcog.2022.108885.
Xingbo Dong, Jiewen Yang, Andrew Beng Jin Teoh, Dahai Yu, Xiaomeng Li, and Zhe Jin, “Video-based face outline recognition,” Pattern Recognition, vol. 152, Art. no. 110482, 2024. DOI: 10.1016/j.patcog.2024.110482.
Mohsin Ullah, Imtiaz Ahmad Taj, and Rana Hammad Raza, “Degradation model and attention guided distillation approach for low resolution face recognition,” Expert Systems with Applications, vol. 243, Art. no. 122882, 2024. DOI: 10.1016/j.eswa.2023.122882.
Pietro Melzi, Ruben Tolosana, Ruben Vera-Rodriguez, Minchul Kim, Christian Rathgeb, Xiaoming Liu, Ivan DeAndres-Tame, Aythami Morales, Julian Fierrez, Javier Ortega-Garcia, et al., “FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems,” Information Fusion, vol. 107, Art. no. 102322, 2024. DOI: 10.1016/j.inffus.2024.102322.
Jiwon Jang and Chong O. Kim, “Teacher–Explorer–Student learning: A novel learning method for open set recognition,” IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 1, pp. 767–780, 2025. DOI: 10.1109/TNNLS.2023.3336799.
Ning Zhuang, Qiang Zhang, Chunhong Pan, Bo Ni, Yi Xu, Xiaokang Yang, and Wenjun Zhang, “Recognition oriented facial image quality assessment via deep convolutional neural network,” Neurocomputing, vol. 358, pp. 109–118, 2019. DOI: 10.1016/j.neucom.2019.04.057.
Rafael H. Vareto, Yao Linghu, Terrance E. Boult, William Robson Schwartz, and Marcel Günther, “Open-set face recognition with maximal entropy and Objectosphere loss,” Image and Vision Computing, vol. 141, Art. no. 104862, 2024. DOI: 10.1016/j.imavis.2023.104862.
S. Irene, A. John Prakash, and V. Rhymend Uthariaraj, “Person search over security video surveillance systems using deep learning methods: A review,” Image and Vision Computing, vol. 143, Art. no. 104930, 2024. DOI: 10.1016/j.imavis.2024.104930.
I. Pattnaik, A. Dev, and A. K. Mohapatra, “A face recognition taxonomy and review framework towards dimensionality, modality and feature quality,” Engineering Applications of Artificial Intelligence, vol. 126, Art. no. 107056, 2023. DOI: 10.1016/j.engappai.2023.107056.
Youssef Zennayi, Souad Benaissa, Hassane Derrouz, and Zakaria Guennoun, “Unauthorized access detection system to the equipments in a room based on the persons identification by face recognition,” Engineering Applications of Artificial Intelligence, vol. 124, Art. no. 106637, 2023. DOI: 10.1016/j.engappai.2023.106637.
Farah Wahida, M. A. P. Chamikara, Ibrahim Khalil, and Mohammed Atiquzzaman, “An adversarial machine learning based approach for privacy preserving face recognition in distributed smart city surveillance,” Computer Networks, vol. 254, Art. no. 110798, 2024. DOI: 10.1016/j.comnet.2024.110798.
Min Wang, Yifan Kang, Bailu Deng, and Xi Lan, “Exploring college students’ risk perception and acceptance intention of facial recognition technology in China,” Telematics and Informatics, vol. 95, Art. no. 102193, 2024. DOI: 10.1016/j.tele.2024.102193.
Shu Min Leong, Raphaël C. W. Phan, Vishnu Monn Baskaran, and Chee Pun Ooi, “Privacy-preserving facial recognition based on temporal features,” Applied Soft Computing, vol. 96, Art. no. 106662, 2020. DOI: 10.1016/j.asoc.2020.106662.
Jian Guo, Hengyu Mu, Xingli Liu, Hengyi Ren, and Chong Han, “Federated learning for biometric recognition: A survey,” Artificial Intelligence Review, vol. 57, Art. no. 208, 2024. DOI: 10.1007/s10462-024-10847-7.
Žiga Babnik, Peter Peer, and Vitomir Štruc, “eDifFIQA: Towards efficient face image quality assessment based on denoising diffusion probabilistic models,” IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 6, no. 4, pp. 458–474, 2024. DOI: 10.1109/TBIOM.2024.3376236.
Kshitij Kotwal and Sébastien Marcel, “Review of demographic fairness in face recognition,” IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 8, no. 1, pp. 20–45, 2026. DOI: 10.1109/TBIOM.2025.3601217.
Tao Wang, Wenying Wen, Xiangli Xiao, Zhongyun Hua, Yu-Shu Zhang, and Yuming Fang, “Beyond privacy: Generating privacy-preserving faces supporting robust image authentication,” IEEE Transactions on Information Forensics and Security, vol. 20, pp. 2564–2576, 2025. DOI: 10.1109/TIFS.2025.3541859.
Hao Gong, Mengqi Dong, Shiqing Ma, Seyit Camtepe, Surya Nepal, and Chang Xu, “Stealthy physical masked face recognition attack via adversarial style optimization,” IEEE Transactions on Multimedia, vol. 26, pp. 5014–5025, 2024. DOI: 10.1109/TMM.2023.3330089.
Ivan DeAndres-Tame, Ruben Tolosana, Pietro Melzi, Ruben Vera-Rodriguez, Minchul Kim, Christian Rathgeb, Xiaoming Liu, Luis F. Gomez, Aythami Morales, Julian Fierrez, Javier Ortega-Garcia, et al., “Second FRCSyn-onGoing: Winning solutions and post-challenge analysis to improve face recognition with synthetic data,” Information Fusion, vol. 120, Art. no. 103099, 2025. DOI: 10.1016/j.inffus.2025.103099.
Jialiang Peng, Huiting Sun, Dong Yang, Ahmed A. Abd El-Latif, and Joel J. P. C. Rodrigues, “PriSecFedFR: Privacy-secure face recognition model training via federated learning and random projection,” Expert Systems with Applications, vol. 297, Art. no. 129383, 2026. DOI: 10.1016/j.eswa.2025.129383.
Ali Ahmed Elmahmudi and Hassan Ugail, “Deep face recognition using imperfect facial data,” Future Generation Computer Systems, vol. 99, pp. 213–225, 2019. DOI: 10.1016/j.future.2019.04.025.
Reham Hosney, Fatma M. Talaat, Eman M. El-Gendy, and Mahmoud M. Saafan, “AutYOLO-ATT: An attention-based YOLOv8 algorithm for early autism diagnosis through facial expression recognition,” Neural Computing and Applications, vol. 36, pp. 17199–17219, 2024. DOI: 10.1007/s00521-024-09966-7.
Divya Nimma, Omaia Al-Omari, Rahul Pradhan, Zoirov Ulmas, R. V. V. Krishna, Ts. Yousef A. Baker El-Ebiary, and Vuda Sreenivasa Rao, “Object detection in real-time video surveillance using attention based transformer-YOLOv8 model,” Alexandria Engineering Journal, vol. 118, pp. 482–495, 2025. DOI: 10.1016/j.aej.2025.01.032.
L. Zhang, M. Wan, P. Huang, and G. Yang, “Adversarial compact wrapping classifier learning for open set recognition,” Information Sciences, vol. 680, Art. no. 121114, 2024. DOI: 10.1016/j.ins.2024.121114.
Z. Zheng, Z. Liu, Y.-W. Si, X. Yuan, J. Duan, X. Li, X. Zhang, and X. Gong, “Quality adaptive class center for lightweight large-scale face recognition,” Information Sciences, vol. 732, Art. no. 122944, 2026. DOI: 10.1016/j.ins.2025.122944.
Yihua Fan, Yongzhen Wang, Dong Liang, Yiping Chen, Hui Xie, Fu Lee Wang, Jianxin Li, and Mingqiang Wei, “Low-FaceNet: Face recognition-driven low-light image enhancement,” IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1–13, 2024. DOI: 10.1109/TIM.2024.3372230.
Mingjie He, Jie Zhang, Shiguang Shan, and Xilin Chen, “Enhancing face recognition with detachable self-supervised bypass networks,” IEEE Transactions on Image Processing, vol. 33, pp. 1588–1599, 2024. DOI: 10.1109/TIP.2024.3364067.
Yang Xin, Xiang Zhong, Yu Zhou, and Jianmin Jiang, “Robust face recognition via adaptive mining and margining of noise and hard samples,” IEEE Transactions on Image Processing, vol. 34, pp. 8114–8129, 2025. DOI: 10.1109/TIP.2025.3634979.
H. Martínez, F. J. Rodríguez-Lozano, F. León-García, J. M. Palomares, and J. Olivares, “Distributed Fog computing system for weapon detection and face recognition,” Journal of Network and Computer Applications, vol. 232, Art. no. 104026, 2024. DOI: 10.1016/j.jnca.2024.104026.
Y. Tao, Y. Li, F. Kong, Y. Shi, M. Yang, J. Yu, and H. Zhang, “Privacy-preserving outsourcing scheme of face recognition based on locally linear embedding,” Computers & Security, vol. 144, Art. no. 103931, 2024. DOI: 10.1016/j.cose.2024.103931.
Yuling Luo, Tinghua Hu, Tao Hu, Xue Ouyang, Junxiu Liu, Qiang Fu, Qin Sheng, Shengfeng Qin, Zhen Min, and XiaoGuang Lin, “DPO-Face: Differential privacy obfuscation for facial sensitive regions,” Computers & Security, vol. 154, Art. no. 104434, 2025. DOI: 10.1016/j.cose.2025.104434.