基于BP神经网络的车牌识别技术研究(英文版).docVIP

Research on license plate recognition technology based on BP neural network With the continuous development of science and technology, means of traffic management is from manual management gradually transformed into automatically or semi automatically, license plate recognition as one of the key and hot issues in the research field of modern traffic engineering by more and more peoples attention. In recent years, neural networks have been applied in many fields, and the characteristics of neural networks are used to make the character recognition based on BP neural network. This article through to in license plate recognition system image pre processing, four key steps: license plate location, character segmentation and character recognition of proposed a kind of license plate characters based on neural network recognition algorithm. Used this method of license plate image experiments were conducted to extract the feature of the license plate character sample, and under the environment of MATLAB on the license plate character recognition was simulated. The results showed that this algorithm the characters on the license plate location and segmentation has good effect, the license plate character recognition with certain accuracy. Key words: BP neural network; license plate location; license plate recognition; character segmentation; character recognition 1 Introduction With the increase of the number of cars, there are traffic congestion in the world. In order to solve this problem, many cities will be widened lane, but still far from solving the problem. Not to increase the existing road facilities, how to improve the efficiency of transportation has become the focus of research in the world. Intelligent transportation system (Intelligent - Transportation System ITS) is the main development trend of the future traffic regulation system. Vehicle license plate recognition technology (License - Plate Recognition LPR) is one of the core technologies in ITS. Therefore,