Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195834,
        author = {SIRIKONDA MAHESH and SOMAROWTHU ANIL KUMAR and SOMAROUTHU MANIKANTA and SHAIK NAYABRASOOL and MAHA LAKSHMI G},
        title = {Surveillance System for Real-Time High-Precision Recognition of Criminal Faces from wild videos Using R-CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1284-1294},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195834},
        abstract = {The rapid growth of urban surveillance infrastructure has generated vast amounts of video data, creating a critical need for intelligent systems capable of accurately identifying criminal suspects in real time. This project presents a surveillance system for high-precision recognition of criminal faces from unconstrained (“wild”) video streams using Region-based Convolutional Neural Networks (R-CNN). The proposed system is designed to operate under real-world conditions, including variations in illumination, pose, occlusion, facial expressions, and low-resolution imagery commonly encountered in public surveillance footage. The framework integrates face detection, feature extraction, and face recognition into a unified deep learning pipeline. R-CNN is employed to localize facial regions with high accuracy, while a deep convolutional network extracts discriminative facial features for identity matching against a criminal database. The system supports real-time processing by optimizing detection and classification stages, enabling prompt alerts when a match is detected. Experimental evaluations demonstrate that the proposed approach achieves high recognition accuracy and robustness compared to traditional face recognition techniques, even in challenging environments. This surveillance solution offers a scalable and effective tool for enhancing public safety and assisting law enforcement agencies in crime prevention and investigation},
        keywords = {},
        month = {April},
        }