2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 17 , Issue 1 , PP: 325-341, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Mohammed Ahmed Talab 1 * , Mustafa A. Feath 2 , Ahmed Hadi Ali AL-Jumaili 3 * , Mohammed A. Al-shibl 4 , Ravie Chandren Muniyandi 5
Doi: https://doi.org/10.54216/JISIoT.170123
This paper introduces an advanced method for face recognition in video surveillance systems, leveraging only a single reference image per individual. The challenge of recognizing faces in video is addressed, considering issues like pose variations, occlusions, and lighting changes. The proposed approach utilizes 3D Morphable Models (3DMM) to generate a 3D face mesh from the reference image, facilitating robust face alignment and recognition across video frames. A Convolutional Neural Network based pipeline is employed for face detection, pose estimation, and extraction of invariant features, while an optimization framework refines landmark positions and depth maps for accurate 3D reconstruction. The system performs exceptionally well on the CASIA-WebFace Dataset, with 97.00% pAUC (20%) in surveillance mode and 98.69% in identification mode for frontal views. With an efficiency of 16.72 FPS on modest hardware, the system proves its practicality for real-world deployment. The method incorporates synthetic data augmentation and Random Subspace Methods to enhance adaptability to domain-specific conditions. Compared to existing methods like Eoe-SVM and CCM-CNN, the proposed system demonstrates a superior balance between accuracy and computational efficiency, particularly in Single Sample Per Person (SSPP) scenarios. By focusing on single-reference image recognition, the system offers a promising solution for large-scale surveillance applications, where video footage typically contains multiple poses, expressions, and lighting variations. The results highlight the system's effectiveness and efficiency, making it an excellent alternative for real-time face recognition in complex and dynamic surveillance environments.
Face recognition , video surveillance , 3D morphable models , single reference image , domain adaptation , Deep learning
[1] D. Gorodnichy and G. Bessens, “From recognition in brain to recognition in perceptual vision systems. Case study: Face in video. Example: Identifying computer users with low-resolution webcams,” in Proc. 3rd Int. Conf. Vision, Video Graph., 2005.
[2] R. K. K. Reddy, S. J. K. S. Reddy, and K. P. R. Reddy, “A survey on face recognition techniques: Challenges and solutions,” Int. J. Comput. Appl., vol. 975, no. 14, pp. 1–7, 2020.
[3] M. Abdul-Al et al., “The evolution of biometric authentication: A deep dive into multi-modal facial recognition: A review case study,” IEEE Access, vol. 12, pp. 50689–50721, 2024.
[4] M. Zamir et al., “Face detection & recognition from images & videos based on CNN & Raspberry Pi,” Computation, vol. 10, no. 9, p. 148, 2022.
[5] Tvoroshenko and V. Kukharchuk, “Current state of development of applications for recognition of faces in the image and frames of video captures,” in Proc. IEEE 16th Int. Conf. Adv. Trends Radioelectron., Telecommun. Comput. Eng. (TCSET), 2021, pp. 682–686.
[6] M. Latif et al., “Face recognition from video by matching images using deep learning-based models,” VAWKUM Trans. Comput. Sci., vol. 12, no. 2, pp. 50–64, 2024.
[7] H. L. Gururaj et al., “A comprehensive review of face recognition techniques, trends and challenges,” IEEE Access, vol. 12, pp. 31114–31151, 2024.
[8] Anil et al., “Literature survey on face recognition of occluded faces,” in Proc. 7th Int. Conf. Circuit, Power Comput. Technol. (ICCPCT), 2024, pp. 1930–1937.
[9] H. Castañeda Rincón and O. Santos Ariza, “Estrategia para la implementación de herramientas con reconocimiento facial en los Sistemas Integrados de Emergencias y Seguridad (SIES),” M.S. thesis, Univ. Dist. Francisco José de Caldas, Bogotá, Colombia, 2021.
[10] H. Du, H. Shi, D. Zeng, X.-P. Zhang, and T. Mei, “The elements of end-to-end deep face recognition: A survey of recent advances,” ACM Comput. Surv., vol. 54, no. 10s, pp. 1–42, 2022.
[11] F. X. Gaya-Morey et al., “Deep learning-based facial expression recognition for the elderly: A systematic review,” arXiv Prepr., arXiv:2502.02618, 2025.
[12] Y. Mi et al., “Duetface: Collaborative privacy-preserving face recognition via channel splitting in the frequency domain,” in Proc. 30th ACM Int. Conf. Multimedia, 2022, pp. 6755–6764.
[13] S. Hangaragi and T. Singh, “Face detection and recognition using face mesh and deep neural network,” Procedia Comput. Sci., vol. 218, pp. 741–749, 2023.
[14] B. Amirgaliyev et al., “A review of machine learning and deep learning methods for person detection, tracking and identification, and face recognition with applications,” Sensors, vol. 25, no. 5, p. 1410, 2025.
[15] O. Elharrouss, N. Almaadeed, and S. Al-Maadeed, “A review of video surveillance systems,” J. Vis. Commun. Image Represent., vol. 77, p. 103116, 2021.
[16] C. Jiang et al., “Object detection from UAV thermal infrared images and videos using YOLO models,” Int. J. Appl. Earth Obs. Geoinf., vol. 112, p. 102912, 2022.
[17] D. Cozzolino et al., “Raising the bar of AI-generated image detection with CLIP,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2024, pp. 4356–4366.
[18] M. Faraki, X. Yu, Y.-H. Tsai, Y. Suh, and M. Chandraker, “Cross-domain similarity learning for face recognition in unseen domains,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 15292–15301.
[19] T. Liu et al., “Cross-domain facial expression recognition via disentangling identity representation,” in Proc. 32nd Int. Joint Conf. Artif. Intell. (IJCAI), 2023, pp. 1213–1221.
[20] G. Wang, H. Han, S. Shan, and X. Chen, “Cross-domain face presentation attack detection via multi-domain disentangled representation learning,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2020, pp. 6678–6687.
[21] Y. Gao et al., “Cross-domain facial expression recognition through reliable global–local representation learning and dynamic label weighting,” Electronics, vol. 12, no. 21, p. 4553, 2023.
[22] H. Wang, C. Liu, and X. Ding, “Still-to-video face recognition in unconstrained environments,” in Proc. SPIE 9405, Image Process.: Mach. Vis. Appl. VIII, 2015, p. 94050H.
[23] M. Shafiq and Z. Gu, “Deep residual learning for image recognition: A survey,” Appl. Sci., vol. 12, no. 18, p. 8972, 2022.
[24] E. S. Leif et al., “A systematic review of social-validity assessments in the Journal of Applied Behavior Analysis: 2010–2020,” J. Appl. Behav. Anal., vol. 57, no. 3, pp. 542–559, 2024.
[25] G. Petmezas et al., “Automated lung sound classification using a hybrid CNN-LSTM network and focal loss function,” Sensors, vol. 22, no. 3, p. 1232, 2022.
[26] R. Sheela and R. Suchithra, “Unmasking the masked: Face recognition and its challenges using the periocular region–A review,” in Handbook of Research on Technical, Privacy, and Security Challenges in a Modern World. IGI Global, 2022, pp. 62–81.
[27] D. Wang, Y. Gu, L. Luo, and F. Ren, “Occlusion-aware visual-language model for occluded facial expression recognition,” in Proc. Int. Joint Conf. Neural Netw. (IJCNN), 2024, pp. 1–8.
[28] S. Bashbaghi, E. Granger, R. Sabourin, and G.-A. Bilodeau, “Robust watch-list screening using dynamic ensembles of SVMs based on multiple face representations,” Mach. Vis. Appl., vol. 28, no. 2, pp. 219–241, 2017.
[29] Z. Yu et al., “Hybrid incremental ensemble learning for noisy real-world data classification,” IEEE Trans. Cybern., vol. 49, no. 2, pp. 403–416, 2017.
[30] F. Nourbakhsh, E. Granger, and G. Fumera, “An extended sparse classification framework for domain adaptation in video surveillance,” in Proc. Asian Conf. Comput. Vis. Workshops, 2016, pp. 360–376.
[31] M. Parchami, S. Bashbaghi, and E. Granger, “CNNs with cross-correlation matching for face recognition in video surveillance using a single training sample per person,” in Proc. 14th IEEE Int. Conf. Adv. Video Signal Based Surveill. (AVSS), 2017, pp. 1–6.
[32] N. K. Mishra and S. K. Singh, “Face recognition using 3D CNN and Hardmining loss function,” SN Comput. Sci., vol. 3, no. 2, p. 155, 2022.
[33] N. A. M. Ariffin, U. A. Gimba, and A. Musa, “Face detection based on Haar cascade and convolution neural network (CNN),” J. Adv. Res. Comput. Appl., vol. 38, no. 1, pp. 1–11, 2025.
[34] F. Roli and G. L. Marcialis, “Semi-supervised PCA-based face recognition using self-training,” in Proc. Struct., Syntactic, Stat. Pattern Recognit., 2006, pp. 560–568.
[35] S. Bashbaghi, E. Granger, R. Sabourin, and G.-A. Bilodeau, “Watch-list screening using ensembles based on multiple face representations,” in Proc. 22nd Int. Conf. Pattern Recognit., 2014, pp. 4489–4494.
[36] M. Yang, L. Van Gool, and L. Zhang, “Sparse variation dictionary learning for face recognition with a single training sample per person,” in Proc. IEEE Int. Conf. Comput. Vis., 2013, pp. 689–696.
