西安工业大学1 摘要汽车牌照自动识别系统是近几年发展起来的计算机视觉和模式识别技术在智能交通领域应用的重要研究课题之一。在车牌自动识别系统中, 首先要将车牌从所获得的图像中分割出来, 这是进行车牌字符识别的重要步骤,定位准确与否直接影响车牌识别率。本次毕业设计首先对车牌识别系统的现状和已有的技术进行深入的研究,在研究的基础上开发出一个基于MATLAB 的车牌识别系统,通过编写M文件,对各种车辆图像处理方法进行分析、比较,提出了车牌预处理、 车牌粗定位何静定位的方法。本次设计采取的是基于边缘检测,先从经过边缘提取后的车辆图像中提取车牌特征,进行分析处理, 从而初步定出车牌的区域, 再利用车牌的先验知识和分布特征对车牌区域二值化图像进行处理,从而得到车牌的精确区域, 并且取得了较好的定位结果。矚慫润厲钐瘗睞枥庑赖。关键词 :识别率车牌定位二值化边缘检测西安工业大学2 Abstract The subject of the automatic recognition of the most significant subiects that are improved from the connection of computer vision and pattren recognition .In LPSR ,the first step is for locating the license plate in the captured image which is very important for character recognition .The recognition correction rate of license plate is goverment by accurate degree of license plate location .聞創沟燴鐺險爱氇谴净。The graduation project first in-depth study on the status of the license plate recognition systems and existing technology, on the basis of the study developed a matlab-based license plate recognition system, a variety of vehicles, image processing, through the preparation of the M-fileanalysis of the proposed license plate pretreatment, the positioning of the coarse license plate positioning Jing. The design is taken based on edge detection, start to extract the license plate characteristics after the vehicle image edge extraction, analysis and processing, which initially identified the license plate area, then use the prior knowledge and d...