基于SVM混合网络的车牌字符识别研究  

Vehicle License Plate Characters Recognition Using Support Vector Machines

作　　者：王润民[1] 钱盛友[1] 邹永星[1] 

机构地区：[1]湖南长沙湖南师范大学物理与信息科学学院,湖南410081

出　　处：《微计算机信息》2007年第34期222-223,259,共3页Control & Automation

基　　金：湖南省自然科学基金资助项目(02JJY2059)

摘　　要：本文提出了一种基于SVM混合网络的车牌字符识别方法。首先根据国内车牌字符的排列特点依次构造汉字识别子网、英文识别子网、英文与数字识别子网以及数字识别子网。然后针对英文字符和阿拉伯数字的字体结构具有连通性这一特点,采用形态学方法进行滤波处理,以减少噪声干扰。预处理后提取字符的小波包系数和矩做为特征量,最后在各个识别子网中采用SVM识别方法对车牌中的汉字、英文字符以及阿拉伯数字进行了识别。实验结果表明,该方法效果良好。A kind of character recognition method of the vehicle license plate based on support vector machines is presented in this paper. Firstly, A Chinese character recognition sub-network,A English character recognition sub-network,A Chinese character and English character recognition sub-network and a digital character recognition sub-network are constructed for Chinese vehicle license plate characters＇ properties.Then, the English characters and digital characters are processed by mathematics morphology to decrease the noise for their special typeface structure,and the characters＇ wavelet packet coefficients and the Zemike moments are distilled to make up the feature space after preprocessed.Finally, The characters of the vehicle license plate are recognized by support vector machines in every recognition sub-network. The experimental results demonstrate the efficiency of the proposed approach.

关 键 词：字符识别 支持向量机 矩 神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]