基于HAAR特征与BP神经网络的车牌识别技术研究

详细信息    查看全文 | 推荐本文 |

英文篇名：Research on vehicle license plate recognition technology based on HAAR feature and BP neural network 作者：刘伍丰 ; 何前磊 ; 郑维 英文作者：Liu Wufeng;He Qianlei;Zheng Wei;College of Electrical Engineering, Henan University of Technology; 关键词：OpenCV ; 车牌识别 ; HAAR特征 ; SVM算法 ; BP神经网络 英文关键词：OpenCV;;license plate recognition;;HAAR features;;support vector machine(SVM) algorithm;;BP neural network 中文刊名：DZCL 英文刊名：Electronic Measurement Technology 机构：河南工业大学电气工程学院; 出版日期：2019-04-23 出版单位：电子测量技术 年：2019 期：v.42;No.316 基金：河南省教育厅科技攻关项目(172102210028);; 河南省高等学校重点科研项目(17A490001);; 河南省高等学校青年骨干教师项目(2016GGJS-066);; 校青年骨干教师培养计划(2018008);; 国家粮食局公益性行业科研项目(201513003)资助 语种：中文; 页：DZCL201908031 页数：7 CN：08 ISSN：11-2175/TN 分类号：67-73

摘要

车牌识别技术运用OpenCV计算机开源机器视觉库,对图像进行处理提取出图像中蕴含的车牌信息,达到车牌识别的目的。通过运用HAAR特征,训练出AdaBoost分类器查找图片中的车牌区域,同时运用Sobel算子进行边缘检测等操作查找车牌区域,最终运用支持向量机(SVM)算法进行两种定位的疑似车牌区域的最终确认;确认后的车牌区域进行字符分割等操作进行字符的分离;最后运用训练的反向传播(BP)神经网络进行字符的识别并最终输出车牌信息。研究结果显示,车牌识别的效率很高,拥有一定的使用价值。
        License plate recognition technology uses OpenCV(open source computer vision library) computer open source machine vision library to process the image to extract the license plate information contained in the image to achieve the purpose of license plate recognition. By using the HAAR feature, the AdaBoost(Adaptive Boosting) classifier is trained to find the license plate area in the picture; At the same time, the Sobel operator is used for edge detection and other operations to find the license plate area; Finally, the SVM(Support Vector Machine) algorithm is used to finalize the two suspected license plate areas; After the confirmation of the license plate area, character division and other operations are performed to separate characters; The trained back propagation(BP) neural network is used to identify the characters and finally output the license plate information. The research results show that it can effectively identify license plate information and has great practical value.

引文

[1] 曾超,陈雨.车牌超分辨率重建与识别[J].计算机测量与控制,2018,26(3):244-249.
    [2] 牛进才,徐建立,李梦君.车辆牌照识别算法的研究与实现[J].电子测量技术,2018,41(6):45-49.
    [3] 鹿琛,王姗珊.基于BP神经网络的车牌字符识别方法[J].山东农业大学学报(自然科学版),2017,48(1):113-116.
    [4] PAPAGEORGIOU C,POGGIO T.A trainable system for object detection[J].International Journal of Computer Vision,2000,38(1):15-33.
    [5] PAPAPEORGIOU C,OREN M,POGGIO T,A general framework for object detection [C].IEEE International Conference on Computer Vision,1998:555-562.
    [6] VIOLA P,JONES M.Robust real-time object detection[J].International Journal of Computer Vision,2001,4:34-47.
    [7] VIOLA P,JONES M.Rapid object detection using a boosted cascade of simple features[C].Proceeding of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001:511-518.
    [8] LIENHART R,MAYDT J.An extended set of Haar-like features for rapid object detection[C].Proceedings of 2002 International Conference on Image Processing,1998:555-562.
    [9] LIENHART R,KURANOV A,PISAREVSKY V.Empirical analysis of detection cascades of boosted classifiers for rapid object detection[C].Proceedings of the 25th German Pattern Recognition Symposium,2003:297-304.
    [10] FREUND Y,SCHAPIRE R E.Experiments with a new boosting algorithm[C].Proceedings of the 13th Conference on Machine Learning,1996:148-156.
    [11] 刘然.支持向量机在嵌入式控制系统的实现研究[D].杭州:杭州电子科技大学,2011.
    [12] HSU C W,CHANG CC,LIN C J.A practical guide to support vector classification[EB/OL].2010-04-15.http://www.csie,ntu.edu.tw/～cjlin.
    [13] TSAI C M,LEE H J.Binarzation of color document images via Iuminance and saturation color features[J].IEEE Transtation on Image Processing,2002,4(11):434-451.
    [14] WANG S,LEE H.Detection and recognition of license plate characters with different appearances [C].Shanghai:IEEE International Conference on Intelligent Transportation System,2003,979-984.
    [15] 廖作斌.车牌识别处理中的关键技术及核心算法研究[J].哈尔滨师范大学自然科学学报,2015,31(4):58-61.
    [16] 谭勇,朱斌.基于改进特征提取的BP神经网络车牌识别[J].重庆文理学院学报(自然科学版),2009,28(3):42-45.