Paper Title
Helmet Detection on Two-Wheeler Riders using Machine Learning

Road safety is often neglected by riders worldwide leading to accidents and deaths. To address this issue, most countries have laws which mandate the use of helmets for two-wheeler riders. In addition to the law, there is a significant proportion of the police force that discourages this behavior by issuing a traffic violation ticket. As of now, this process is manual and tedious. This project aims to solve this problem by automating the process of detecting the riders who are riding without helmets. Furthermore, the system also extracts the license plate so that it could be used to issue traffic violation tickets. The system implements machine learning and image processing techniques to detect riders, riding two-wheelers, who are not wearing helmets. The system takes a video of traffic on public roads as the input and detects moving objects in the scene. A machine learning classifier is applied to the moving object to identify if the moving object is a two-wheeler. If it is a two-wheeler, then another classifier is used to detect whether the rider is wearing a helmet. The license plate is provided as the output in case the rider is not wearing a helmet. Keywords - Machine Learning, Supervised Learning, Feature Extraction, Background Subtraction, MATLAB Functions