Abstract:
"This project aims to develop a video and image violence detection system using machine learning and image processing techniques. With the growing trend of recording and distributing violent events across multiple platforms, the need for effective violence detection systems has increased significantly. The Intelligent Violence Video Detection project addresses the growing need for effective violence detection systems. Unfortunately, in the busy and stressful lifestyle of today's society, instances of frustration and hurtful emotional behavior are commonplace. This can lead to violations of rules and regulations and even violence, and such events are often difficult to detect and control. The proposed solution involves the use of A Convolutional Neural Network (CNN)
that has undergone training using a substantial dataset of annotated images and videos, with an architecture consisting of multiple layers responsible for learning features and making predictions. The effectiveness of the violence detection system is assessed by utilizing metrics such as accuracy, validity, and recall. The findings demonstrate that the proposed solution achieves exceptional accuracy and effectively identifies instances of violence within videos and images. In conclusion, the proposed solution is a promising approach to detect violent events in videos and images using machine learning and image processing techniques. Future work can be done to further improve the accuracy and efficiency of the system."
