Published Paper Details:

This research presents the design and implementation of a Real-Time Face Recognition System for CCTV Surveillance using deep learning techniques to enhance public safety and surveillance efficiency. The system automatically detects and identifies individuals from live video streams, enabling reliable recognition of suspects or missing persons in real time. It integrates face detection, feature extraction, and similarity matching to achieve high recognition accuracy while handling variations in pose, lighting, and orientation. Additionally, the system supports dual-mode surveillance by incorporating vehicle detection and license plate recognition, allowing comprehensive monitoring of both individuals and vehicles. The proposed approach is capable of processing multiple camera feeds simultaneously while maintaining low latency and real-time performance. It generates instant alerts upon successful identification, ensuring quick response and decision-making. Overall, the system reduces dependence on manual monitoring, minimizes human error, and provides an efficient, scalable solution for modern intelligent surveillance applications.