Citation

Umrao, Sanjana and Sharma, Shamneesh and Sharma, Ajay and Gochhait, Saikat and Alandoli, Mohammed Nasser (2025) Real-Time Face and Person Detection Using YOLOv5 and OpenCV: A Performance-Optimized Approach with Benchmarking and Tracking. In: 2025 Multimedia University Engineering Conference (MECON), 21-23 July 2025, Cyberjaya, Malaysia.

Text 465.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

In recent years, face and person detection have emerged as critical applications in computer vision, enabling advancements in surveillance, biometric authentication, and real-time monitoring systems. This paper describes a comprehensive face and person detection system based on YOLOv5 for person detection and OpenCV’s deep learning models for frontal and profile face detection. The proposed system receives video footage, performs detection, and tracks targets throughout the frames while measuring performance indicators such as frame per second (FPS), CPU, and memory consumption. In contrast to traditional methods, multiple detection approaches were applied, which makes the system more accurate and robust in dynamic conditions. The full-scale implementation validation of the system was performed using real-life video footage where finding the balance among the models’ accuracy, efficiency, and real-time processing speed posed challenges. This approach designs a framework based on the requirements of real-time systems which can be improved by integrating multi-angle face recognition, optimizing on edge devices, and tailoring to specific domains. This work assists the further development of face and person detection systems using deep learning models with real-time tracking and benchmarking, promoting future innovations in intelligent surveillance and biometric security systems.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Face Detection, Person Tracking, YOLOv5, OpenCV, Deep Learning, Real-Time Detection, Computer Vision, Benchmarking, Biometric Security.
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	19 Mar 2026 00:16
Last Modified:	19 Mar 2026 00:16
URII:	http://shdl.mmu.edu.my/id/eprint/15505

Downloads

Edit (login required)