• Medarametla Sathwika
• Koneti Harsha Vardhan
• Racharla Pranay Raj
• A Prashanth Rao

In the current situation, we are confronted with a variety of traffic control issues in India, which can be addressed using a variety of approaches. Riding a motorcycle without a helmet is a traffic offence in India that has resulted in an increase in the number of accidents and fatalities. What if there was a system that would scan for traffic violations such as not wearing a helmet while riding a motorcycle and, if found, would retrieve the vehicle's licence plate number automatically? Recent research has successfully completed this task using CNN, R-CNN, LBP, HoG, HaaR, and other characteristics. However, these efforts are limited in terms of efficiency, precision, and the speed with which objects are detected and classified. Object detection using Deep Learning at three layers is the basic principle involved. At the first level, YOLOv2 detects a person, a motorcycle/moped, and a helmet at the second level, YOLOv3, and a licence plate at the third level, YOLOv2. After that, OCR is used to retrieve the licence plate registration number (Optical Character Recognition). The speed with which this task is completed is critical because it uses photographs as its input. We built a comprehensive solution for both helmet detection and licence plate number extraction using the approaches mentioned above.

License Plate Extraction, CNN, Tesseract OCR, Helmet Detection

"HELMET DETECTION AND LICENSE PLATE RECOGNITION USING CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 6, page no.b210-b213, June-2022, Available :http://www.jetir.org/papers/JETIR2206129.pdf

"HELMET DETECTION AND LICENSE PLATE RECOGNITION USING CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 6, page no. ppb210-b213, June-2022, Available at : http://www.jetir.org/papers/JETIR2206129.pdf