【作者】 马月涛；

【导师】 张向东；

【作者基本信息】 西安电子科技大学 ， 交通信息工程及控制， 2007， 硕士

【摘要】 随着我国经济的发展、汽车拥有量的急剧增加,公路交通成为我国重要的交通运输途径,是国家大力发展的基础设施,而传统的人工管理方式已越来越不能满足实际工作的需要,日益拥堵的城市交通需要用更先进、更有效的交通管理、控制。以计算机图像处理技术,通信技术为核心的智能化道路交通监控和管理系统ITS己成为当前交通管理发展的主要方向。车辆牌照的自动识别LPR是计算机视觉与模式识别技术在智能交通领域应用的重要研究课题之一,也是智能交通中关键技术之一。本文应用图像处理技术、车牌定位技术、车牌分割技术、字符特征提取方法、神经网络识别技术等来解决车辆牌照识别问题,首先将图像进行灰度化、灰度拉伸、中值滤波的预处理方法,很好地消除了图像的噪音,强化了纵向纹理区;通过对车牌特征和定位技术的深入研究,提出了基于水平扫描和垂直投影法的车牌定位方法,能够很准确地搜索到车牌区域;基于车辆牌照的一些结构特点及先验知识,完成了基于投影直方图的车牌字符分割域;最后对神经网络的构成以及相关的理论进行了讨论,着重分析了神经网络的理论原理和在字符识别中的应用方法。由实验所得的结果,本系统能较准确定位、分割车牌并进行识别,系统的性能良好。从中可看出:多种预处理与识别技术有机结合能提高系统识别能力,在有效、实用的原则下将神经网络与人工智能技术相结合将成为模式识别研究的两个重要发展趋势。更多还原

【Abstract】 With the fantastic spur in economy and rapid development of the owning amount of automobile, the highway communication becomes one of the most important communications and transportation ways in our country , but the traditional transportation practical demands nowadays,also crowded traffic needs more advanced and more effective traffic administration and system. So Intelligent Transportation Systems(ITS) which makes use of image preprocessing technology and communication technology becomes main direction of traffic administration.License Plate Recognition(LPR) is one of the critical techniques and the key of ITS. The paper is based on image preprocessing technology、license plate location technology、character segmentation technology and BP neural network technology to study LPR. First, through gray equalization、median filter and so on, the noise will be reduced well and the lengthways-texture area can be strengthened; through deeply study in license plate character and license plate location, a license plate location algorithm based on horizontal scan and vertical projection is put forward that can search the license plate area accurately; based on structure-characteristic and transcendent information of license plate, character segmentation will be done well; last, the paper analyzes the structure of the neural network with relevant theories and emphatically discusses the theory principle of the neural network and the application method in character recognition with it.As the test result, it proves that this recognition system can relatively accurate to locate license plate and recognize characters and system’s performance is good. It shows that combined pretreatments and recognition techniques can improve the ability of recognition, and the combination of neural network and artificial intelligence under the principle of efficiency and practicality will be two major development tendencies of pattern recognition.更多还原