毕业设计大论文重点.doc

兰州理工大学毕业设计 LANZHOU UNIVERSITY OF TECHNOLOGY 毕业设计 题 目 基于特征的车牌定位方法设计及实现 学生姓名 ***** 学 号 ***** 专业班级 通***班 指导教师 *** 学 院 计算机与通信学院 答辩日期 *年*月16号  基于特征的车牌定位方法及实现 License Plate Location Method Based on the Characteristics of the Design and Implementation ** ** **[键入文字]  PAGE \* MERGEFORMAT II 摘要 智能交通系统（ITS）是交通管理在当前发展的重要方向，其中车辆牌照识别（LPR）系统在智能交通系统中起着举足轻重的作用。车牌识别系统包括图像提取、图像预处理、车牌定位、字符识别四个主要方面，而车牌的定位更是LPR系统的关键之一。车牌区域精确的定位会对车牌识别的准确性产生直接影响，是影响车牌识别系统整体性能的关键所在。 本文主要研究车牌区域定位的设计与实现，对车牌区域的固有特征和当前车牌定位技术进行简介，着重介绍了几种常用的车牌定位方法。然后在此基础上通过采集到彩色车牌照图像进行灰度化，利用中值滤波去掉图像中的干扰噪声，改善图像质量，对图像二值化后通过数学形态学的开、闭运算对车牌进行处理以获得车牌可能的候选区域，然后通过边缘检测对图像中的车牌进行定位。实验表明通过上述方法处理后，基本上就可以定位出像素区域中车牌的位置。 关键词：图像预处理；数学形态学；车牌定位 Abstract Intelligent transportation system (ITS) is the important direction of traffic management in the current development, the vehicle license plate recognition (LPR) system plays an important role in intelligent transportation system. License plate recognition system includes the following four main aspects :image extraction, image preprocessing, license plate locating, character recognition. And license plate location is one of the key of LPR system. Accurate positioning of license plate area can directly influence on the accuracy of license plate recognition, and it is the key to the license plate recognition system overall performance. This paper mainly studies the design and implementation of license plate localization, the inherent characteristics of the license plate region and the current license plate location technology to carry on the introduction, introduced several kinds of commonly used method of license plate location. Then on this basis, through collecting color license plate images to gray scale, by using median filter to remove the interference noise of the image and improve image quality. After image binarization by the opening and closing mathematical morphology