• Jillidimudi Dileep Kumar
• Dr. B. Sreenivasa Rao
• Panigrahi Asish Kumar

The weapon detection is a key area of computer vision with the aim of enhancing safety and security systems. This project compares the efficiency of various deep learning approaches such as YOLOv4, YOLOv6, InceptionV3, InceptionResNetV2, VGG16, and ResNet + Faster R-CNN (FRCNN) in automating the process of weapon spotting in images and videos. The performance of each algorithm is evaluated in terms of relevant metrics such as precision, recall, F1 score, enabling comparative study. Among other algorithms applied for this study, YOLOv6 exhibits the highest real time accuracy and therefore can be applied in real time applications as well. This study also indicates the weakness of certain models or configurations and recommends the best for particular use in video surveillance systems. The proposed framework improves both accuracy and performance efficiency for quick weapons detection in a number of diversified settings.

VGG16, YOLOv6, Weapon

"HYBRID ALGORITHMS FOR REAL-TIME WEAPON IDENTIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 1, page no.b261-b266, January-2025, Available :http://www.jetir.org/papers/JETIR2501155.pdf

"HYBRID ALGORITHMS FOR REAL-TIME WEAPON IDENTIFICATION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 1, page no. ppb261-b266, January-2025, Available at : http://www.jetir.org/papers/JETIR2501155.pdf