• Shally Gupta
• Rajesh S. Singh
• Ratnesh Srivastava
• H. L. Mandoria

An automated system for recognizing vehicles’ license plates is a growing need in order to improve security and for traffic control applications, particularly in major urban areas. Automatic Number Plate Recognition (ANPR) is a type of an Intelligent Transport System. While numerous studies on plate identification, character segmentation and character recognition have been performed, several challenges still remain. An efficient Vehicle Detection System is necessary to ensure traffic monitoring. In the last 4-5 years, several image processing and learning methods have been developed such as Optical Character Recognition (OCR) technique. The aspect of object detection, though, hasn’t been exploited for ANPR framework in the previous researches focused on object detection. This research uses deep learning to leverage these object detection algorithms. You-Only-Look-Once (YOLO) and Convolutional Neural Network (CNN) have shown themselves to be the most efficient methods with regard to both supervised and unsupervised learning. This work studies several algorithms for object detection and deep learning, and compares their performance. The custom dataset was used to identify and recognize the license plate to ensure successful traffic management. We studied Deep Learning algorithms based on Image Segmentation using object detection algorithm through YOLO object detection technique in darkflow frameworks and character recognition based on CNN and also trained a model as base learner. This study establishes a method for real-time detection and identification of license plate, and drawing useful conclusions. The results of the simulation show that the deep learning methodology is more effective when detecting vehicle plates.

Automatic Number Plate Recognition, Convolution Neural Network, Image Processing, Optical Character Recognition, License Plate, Deep Learning

"Detection of Vehicular Number Plate System using Deep Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 3, page no.1627-1636, March-2021, Available :http://www.jetir.org/papers/JETIR2103207.pdf

"Detection of Vehicular Number Plate System using Deep Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 3, page no. pp1627-1636, March-2021, Available at : http://www.jetir.org/papers/JETIR2103207.pdf