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{177863,
        author = {Syed Aatif Ali and Kumar Telang and Syed Adnan Ahmed and Prof. S.R Gangane},
        title = {Weapon Detection in Real-Time CCTV Videos Using AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {1660-1670},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177863},
        abstract = {With the increasing incidence of criminal activities, there is a growing need for security forces to integrate automated command systems. This study introduces an innovative deep learning model designed to classify seven distinct types of weapons. The proposed model is based on the VGGNet architecture and implemented using Keras, which operates on the TensorFlow framework. It is trained to accurately identify various weapons, including assault rifles, bazookas, grenades, hunting rifles, knives, handguns, and revolvers. The training process involves designing layers, executing computational procedures, saving training data, evaluating performance, and testing the model. A carefully curated dataset, comprising images from these seven weapon categories, is utilized to enhance the model’s learning capability. To assess its efficiency, a comparative analysis is conducted against well-known models such as VGG-16, ResNet-50, and ResNet-101. The results demonstrate that the proposed model achieves outstanding classification accuracy of 98.40%, significantly outperforming VGG-16 (89.75%), ResNet-50 (93.70%), and ResNet-101 (83.33%). These findings underscore the potential of this deep learning approach in strengthening security operations and assisting law enforcement in identifying and addressing threats more effectively.},
        keywords = {Deep learning, armed weapon detection, machine learning, object detection, convolutional neural networks},
        month = {May},
        }