文档介绍：华中科技大学
硕士学位论文
车牌识别系统中车牌定位与字符分割的研究
姓名:蒋传伟
申请学位级别:硕士
专业:计算数学
指导教师:卢力
20061029
华中科技大学硕士学位论文
摘要
随着我国国民经济的高速发展,国内高速公路、城市道路、停车场的建设越来越
多,人们对交通控制、安全管理的要求也日益提高,智能交通系统(ITS)己成为当前交
通管理发展的重要方向,而车辆牌照识别(LPR)系统作为智能交通系统的一部分起着举
足轻重的作用,它在高速公路、城市道路和停车场等项目管理占有无可替代的重要地
位,它的广泛应用必将有助于我国交通管理自动化的进程。
本文对车牌识别系统中的车牌定位和车牌字符分割这两个主要问题,开展了部分
研究工作。
针对车牌定位问题,提出了一种基于数学形态学的定位方法。首先对车牌进行预
处理,确定候选区域队列,然后排除候选车牌区域中的干扰区域,最后来定位真正的
车牌区域,并给出了相应的算法和程序实现。
针对车牌字符分割问题,首先利用张量投票技术对获得的车牌图片进行预处理,
然后引入基于连通域的字符分割方法进行分割,提出了相应的算法并程序实现。
本文算法对牌照在图像中的位置没有限制,对牌照的倾斜、变形、字符的污染、
模糊有较强的抗干扰能力,对于外界光线强度和图像对比度的变化有较强的适应能力。

关键词:车牌识别,车牌定位,数学形态学,车牌字符分割,张量投票
I
华中科技大学硕士学位论文
Abstract
With the high-speed development of our national economy, there are more and more
construct in the domestic expressway, urban road, and parking area, etc. The requisition on
the traffic control, safety management improves day by day. The intelligent traffic system
(ITS) has already e the main direction of present traffic administration development,
and vehicle license plate recognition (LPR) system as core of ITS, plays a very important
role. It occupies important role in the project management of expressway, urban road and
parking area, etc. Its wide application will contribute to the process of the traffic
management automation of our country.
The thesis aims at researching the following two aspects in the License Plate
Recognition System: license plate location and character segmentation.
Concerning the license plate location problem, a location method based on
Mathematical Morphology is brought up. First, the license plate image is preprocessed and
candidate district is determined. Secondly, the interfered district is excluded. At last, the real
license plate region is located. Besides that, the corresponding algorithm is provided.
Concerning the character segmentation issue, the method is as follows: First, the license
plate location image is preprocessed using tensor voting te