Real-Time Facial Recognition and Behaviour Analysis for Workplace Monitoring

Facial recognition systems have become increasingly valuable in workplace environments where real-time identity verification and behavioural monitoring are essential for ensuring safety, security, and operational efficiency. This paper presents a lightweight and cost-effective facial recognition system designed specifically for workplace monitoring, integrating both identity recognition and behaviour analysis using classical computer vision techniques. The system employs Haar Cascade classifiers for real-time face detection, utilizing OpenCV for image processing and Flask as the backend framework. A live video feed from a camera is processed to recognize individuals and monitor their activity. In addition to identifying faces, the system is capable of detecting specific behavioural patterns, such as inattention or improper handling of materials. When such events are identified, the system logs the behaviour and can issue an alert through a speaker or dashboard notification. A custom-built web dashboard, developed using Dash and Bootstrap, provides real-time visualization of detections, system logs, and analytical charts for better decision-making. The dashboard is responsive, user-friendly, and suitable for deployment in a variety of workplace settings. The proposed solution offers a practical alternative to complex deep learning models, requiring minimal computational resources while still achieving reliable performance. The modular nature of the system also allows for future extensions such as integration with biometric attendance, advanced pose estimation, or cloud-based monitoring.