摘要
车牌识别系统是智能交通系统的重要组成部分。本文研究了进行车牌识别的各项关键技术,在分析了近年来一些典型的车牌识别算法的基础上,最终确定一系列有效的算法对车牌进行识别。车牌定位是汽车牌照识别系统的重要环节,定位的准确性直接影响车牌识别的准确率。在车牌定位(车牌检测)阶段,本文提出了基于数学形态学与多特征组合分析相结合的快速汽车车牌定位方法。对于字符分割,主要借助相关的投影信息和先验知识来确定每个字符的分割位置。字符识别,本文给出了改进算法的BP神经网络。实验表明,本文算法可以有效提高识别速度和准确率。
The Car License Plate Recognition System was an important component of Intelligent Transportation System. It was proposed a new method for car license plate location by combining morphology and multiple features. Algorithms of all modules related to LPRS were deeply studied and analyzed. An improved BP neural network was used to carry out the recognition of letters and numbers in the license plate.
出处
《交通建设与管理》
2009年第11期94-97,共4页
Transport Construction & Management
关键词
车牌识别系统
车牌定位
字符分割
字符识别
Car License Plate Recognition System
license plate location
character segmentation
character recognition
