一种轻量级的车牌字符识别算法

详细信息    查看全文 | 推荐本文 |

英文篇名：Light-weight Recognition Algorithm of Vehicle License Plate Characters 作者：马李昕 ; 李凤坤 英文作者：MA Li-xin;LI Feng-kun;Dalian Neusoft University of Information; 关键词：车牌识别 ; 字符识别 ; 形状特征向量 英文关键词：Vehicle license plate recognition;;Character recognition;;Shape feature vector 中文刊名：JSJA 英文刊名：Computer Science 机构：大连东软信息学院; 出版日期：2019-06-15 出版单位：计算机科学 年：2019 期：v.46 基金：辽宁省博士启动基金(20170520398);; 辽宁省教育厅科学技术一般项目(L2015041)资助 语种：中文; 页：JSJA2019S1050 页数：4 CN：S1 ISSN：50-1075/TP 分类号：249-251+268

摘要

字符识别是车牌识别的一个关键环节。在对车牌字符集进行深入分析的基础上,提出了形状特征向量等概念,从理论上分析并证明了形状特征向量用于车牌字符识别的可行性。文中提出了一种基于形状特征向量的车牌字符识别算法,并进行了仿真实验。实验结果表明,形状特征向量能够用作车牌字符识别,基于形状特征向量的车牌识别算法具有97.31%的正确率;此外,该算法没有复杂的训练过程,不需要大量数据来记录训练结果,实现简单,是一种轻量级的车牌字符识别算法。
        Character recognition is the key step of vehicle license plate recognition(VLPR).Some concepts,such as shape feature vector(SFV),were proposed after examining the character set used by vehicle license plate and the feasibility of using SFV to recognize vehicle license plate characters was proven theoretically.Then,a character recognition algorithm of vehicle license plate was proposed and evaluated by simulation.The result of the simulation shows that SFVcan be used as license plate character recognition,and the license plate recognition algorithm based on SFV has an accuracy rate of 97.31%.Besides,this algorithm has no complex training process and does not require large amounts of data to record the training results.It is simple to implement and is a lightweight license plate character recognition algorithm.

引文

[1] LETS,TRAN V N,Hamamoto K.A robust and flexible license plate detection method[C]//Proceedings of International Conference on Advanced Technologies for Communications (ATC).Hanoi:IEEE Press,2014:326-331.
    [2] DU S,IBRAHIM M,SHEHATA M.Automatic License Plate Recognition (ALPR):A State-of-the-Art Review [J].IEEE Transactions on Circuits and Systems for Video Technology,2013,23(2):311-325.
    [3] 钟菲,杨斌.基于主成分分析网络的车牌检测方法[J].计算机科学,2018,45(3):270-275.
    [4] 李彦,张洪博,石莲英.基于SIFT特征匹配的车牌识别方法[J].计算机工程与应用,2016,52(12):194-200.
    [5] 瞿中,常庆丽,王永昆,等.改进的车牌相似字符分级分类识别算法研究[J].计算机工程与设计,2013,34(4):1336-1340.
    [6] 罗辉武,唐远炎,王翊等.基于结构特征和灰度特征的车牌字符识别方法[J].计算机科学,2011,38(11):267-302.
    [7] 焦娜.基于软K段主曲线的LPR字符特征的提取方法[J].计算机科学,2017,44(9):49-52.
    [8] 贾文其,李明,朱美强等.基于栈式降噪自编码神经网络的车牌字符识别[J].计算机工程与设计,2016,37(3):750-756.
    [9] 施隆照,强书连.基于组合支持向量机的车牌字符识别[J].计算机工程与设计,2017,38(6):1619-1623.
    [10] 平源,李慧娜.快速精确识别车牌字符的方法[J].计算机工程与设计,2008,29(9):2410-2412.
    [11] 何兆成,佘锡伟,余文进,等.字符多特征提取方法及其在车牌识别中的应用[J].计算机工程与应用,2011,47(23):228-231.