International Journal of Scientific Research and Engineering Development

Automatic number plate detection and traffic violation monitoring are critical aspects of modern intelligent transportation systems. This study presents a real-time system that leverages deep learning techniques — specifically the YOLO (You Only Look Once) object detection algorithm — combined with Optical Character Recognition (OCR) and a full-stack web application to detect traffic violations, extract license plate numbers, and generate automated fines. The system processes real-time video and image feeds from surveillance cameras, identifies violations such as riding without a helmet and triple riding, extracts the offending vehicle's number plate using EasyOCR, and stores the violation record in a MySQL database. A React.js frontend and Python Flask backend provide an interactive interface for law enforcement authorities. The proposed system achieves high detection accuracy under varying lighting and environmental conditions and demonstrates the potential of AI-driven automation to enhance road safety and reduce dependency on manual traffic enforcement.

Pratik Govind Chakane, Shubhangi Kamble, "Automatic Number Plate Detection and Traffic Violation Using Deep Learning " International Journal of Scientific Research and Engineering Development, V9(2): Page(20-23) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.