• Aastha Sakshi
• Girija Chiddarwar
• Aritra Ghosh
• Bhakti Barve
• Vasudha Agrawal

Based on the current situation of gun violence around the world, there is a need for automated surveillance for the detection of handguns the objective of this proposed technique is to visually detect the handgun in images captured in video surveillances. The proposed method is to conduct a comparative study between the available object recognition algorithms and choosing an optimal algorithm for a video surveillances system. A dataset of images of guns and knives is used. The data will be trained using the most optimal algorithm. There are available surveys that show that YOLO-V3 (You Only Look Once version 3) can be used as an alternative of Faster RCNN (Region Based Convolutional Neural Networks), but there are no available papers or surveys assessing the function of YOLO-V4 (You Only Look Once version 4) so that will be tested by this paper.

Object recognition, Comparative Study

"Comparative Study Of Object Recognition Algorithms To Find The Optimal Algorithm For Weapons Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 7, page no.g181-g189, July-2021, Available :http://www.jetir.org/papers/JETIR2107756.pdf

"Comparative Study Of Object Recognition Algorithms To Find The Optimal Algorithm For Weapons Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 7, page no. ppg181-g189, July-2021, Available at : http://www.jetir.org/papers/JETIR2107756.pdf