AI-Based Live Face Recognition and Target Person Detection System

AI and computer vision support automated person detection and real-time tracking. However, occlusion, lighting changes, tracking errors, and limited computing resources remain challenges. This paper proposes comparing tracking methods using FPS, identity switches, track fragmentation, and recovery time to evaluate tracking consistency and processing efficiency. Final conclusions will be based on experimental results.

[1] B. Amirgaliyev, M. Mussabek, T. Rakhimzhanova, and A. Zhumadillayeva, “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, Art. no. 1410, 2025, doi: 10.3390/s25051410. [2] C.-Y. Chang et al., “Design and implementation of a real-time face recognition system based on artificial intelligence techniques,” Multimedia Systems, vol. 30, Art. no. 114, 2024, doi: 10.1007/s00530-024-01306-y. [3] Y. Zhang, P. Sun, Y. Jiang, D. Yu, F. Weng, Z. Yuan, P. Luo, W. Liu, and X. Wang, “ByteTrack: Multi-Object Tracking by Associating Every Detection Box,” in Proc. European Conference on Computer Vision (ECCV), 2022, pp. 1–21, doi: 10.1007/978-3-031-20047-2_1. [4] W. Wang et al., “Towards Occlusion-Aware Multi-Pedestrian Tracking,” Applied Sciences, vol. 15, no. 24, Art. no. 13045, 2025. doi: 10.3390/app152413045. [5] D. Rodriguez Garcia, A. Aparicio Serna, D. Sancho Crespo, X. Yu, and J. Saniie, “AI Smart Security Camera for Person Detection, Face Recognition, Tracking and Logging.” Publication details and DOI to be verified from the supplied paper before final submission.