基于多特征和加权模式相似性测度的车牌字符识别方法  

A Method for License Plate Recognition Based on Multiple Features and Weighted Pattern Similarity Measurement

作　　者：谢剑斌[1] 刘通[1] 文特[1] 闫玮[1] 

机构地区：[1]国防科技大学电子科学与工程学院,湖南长沙410073

出　　处：《计算机工程与科学》2008年第8期36-38,共3页Computer Engineering & Science

基　　金："十一五"国防重点预研项目(102010201)

摘　　要：针对嵌入式环境下车牌识别的问题,本文提出了一种基于多特征和加权模式相似性测度的车牌字符识别方法。首先获取车牌字符的结构、轮廓与笔划等多特征信息,建立车牌字符编码表;然后利用加权模式相似性测度进行特征匹配,完成字符识别。该方法不需要样本和模板,占用资源少,运算效率高,可以满足嵌入式环境下车牌识别对资源和效率的要求。实验表明,该方法鲁棒性好、识别率高。A method for license plate recognition based on multiple features and weighted pattern similar：ty measurement is proposed for the embedded environment. Firstly, the multi-feature information including structure, profile and stroke is detected and the license plate code table is set up. Secondly,by weighted pattern similarity measurement,license plate recognition is realized. This method does not need samples and templates,costs little resources and has high computing efficiency, and can meet the needs of resources and efficiency for license plate recognition in the embedded environment. The experiments show that the method has good robustness and high recognition rate.

关 键 词：车牌字符识别 多特征 相似性测度 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]