The Vehicle License Plate Recognition System Based On Bp Neural Network Research And Realization

The License Plate Recognition (LPR) system becomes an important part of Intelligent Traffic System (ITS) with the rapid development of computer science and digital image processing. LPR technology can used in many fields to improve management's automation grade, such as electron charging, pass controlling and automobile stream supervising etc. More and more people are attaching importance to its interrelated technology study.The essential technology of LPR system lies in the digital image pretreatment technology, the plate location technology and the plate character recognition technology. This paper discussed a LPR system which applies the computer image processing technology, the license location technology, the character division technology, the license character recognition technology based on BP Neural Network networks.Vehicle license plate location (LPL) and character segmentation techniques are key technologies of the vehicle license plate recognition system. In this paper a new arithmetic of perpendicular edge detection works on license plate location, according to geometrical features of perpendicular edge which belong to license plate characteristics. From the image, it can confirm the likelihood license plate inquire electoral district with edge detection. Think about the characters geometrical shape, we filter the license plate inquire electoral district, and locate the license plate location. Finally, the character angles are corrected by Hough transformation, and the character is segmented by segmentation algorithm. Location and segmentation problems are solved effectively under complex scenes.This paper discuss the neural network and related theories, which focuses on analysis of the neural networks in Character Recognition application, the design of BP neural network classifiers and extraction of the license plate characters. All the characteristics of the char image are input to BP network and the output of BP network is coded by binary code. Hidden layer nodes are identified by the initial use of hidden nodes in empirical formula. All of this greatly reduce the number of iterations and the size of the network and enhance the speed of the LPR. The study shows that the proposed edge detection arithmetic can detect image edge rapidly, and the LP area's contour is very clear. The results report that LP characters are segmented accurately by the proposed location and segmentation arithmetic that have high accuracy and robustness. The BP network has satisfying performance in character recognition. It is satisfied with the requirement of real-time LP recognition and has some theoretical and practical significance.