Please wait a minute...
浙江大学学报(工学版)
计算机技术﹑电信技术     
基于R-ELM的实时车牌字符识别技术
柯海丰1,2,应晶1,2
1. 浙江大学城市学院 计算机科学与工程学系,浙江 杭州 310015;2.浙江大学 计算机科学与技术学院,浙江 杭州 310027
Real-time license character recognition technology based on R-ELM
KE Hai-feng1,2, YING Jing1,2
1. Department of Computer Science and Engineering, Zhejiang University City College, Hangzhou 310015, China;2. College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
 全文: PDF(1799 KB)   HTML
摘要:

提出新的实时车牌字符识别技术.该技术对分割后的字符图像进行灰度化,归一到固定像素大小,采用R-ELM算法进行训练.该技术的优点在于能够采用较小的样本集,快速达到理想的识别率.实验数据显示,与传统的BP算法相比,效率能够提高2~3个数量级.为了有效地挖掘GPU的运算能力,系统采用弹性队列与动态符合调整方法,将字符数据组合成数据包,保证在使用图形处理器(GPU)进行识别的过程中,运算效率最大化.实验显示,与CPU相比,能够得到近2个数量级的速度提升.通过对大量实际样本图像的测试,采用该方法获得了良好的识别及加速效果.

Abstract:

A new real-time recognition technology was provided for license plate character. Character image segmentation was normalized to a fixed pixel size after gray processing, and then R-ELM algorithm for training was applied. The desired recognition accuracy was rapidly achieved by using comparatively smaller sample sets.  Experimental results show that recognition efficiency can be improved from 100 to 1000 times compared with the traditional BP algorithm. To apply the GPU technology more effectively, the system assembles the character data into packets by using elastic queue and dynamic compliance adjustment method which can acquire maximum efficiency in the recognition process. Experiments indicated that recognition accuracy was raised nearly 100 times compared with CPU. By testing of a large number of practical sample images, the method can obtain a good recognition and accelerated result.

出版日期: 2014-08-04
:  TP 311  
通讯作者: 应晶,男,教授,博导     E-mail: yingj@zucc.edu.cn
作者简介: 柯海丰(1977—),男,博士生,从事GPU、模式识别的研究. E-mail: kehf@zucc.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

柯海丰,应晶. 基于R-ELM的实时车牌字符识别技术[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2014.07.010.

KE Hai-feng, YING Jing. Real-time license character recognition technology based on R-ELM. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2014.07.010.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2014.07.010        http://www.zjujournals.com/eng/CN/Y2014/V48/I7/1209

1] 路小波,凌小静,黄卫. 一种基于模板匹配的汽车牌照识别方法[J]. 交通与计算机, 2004, 22(6): 79-82.
LU Xiao-bo, LING Xiao-jing, HUANG Wei. A method of vehicle number plate recognition based on template matching [J]. Computer and Communications, 2004, 22(6): 79-82.
[2] 植俊文,戴青云,黄雪贤. 一种基于径向基神经网络的车牌字符识别方法[J]. 计算机应用, 2005, 25(增1): 311-313.
ZHI Jun-wen, DAI Qing-yun, HUANG Xue-xian. License character recognition technology based on RBF neural network [J]. Journal of Computer Applications, 2005, 25(supp.1): 311-313.
[3] ZHENG L, HE X. Number plate recognition based on support vector machines [C]∥IEEE International Conference on Video and Signal Based Surveillance. [S.l.]: IEEE, 2006: 13.
[4] 魏武,黄心汉,张起森,等. 基于模板匹配和神经网络的车牌字符识别方法[J]. 模式识别与人工智能, 2001, 14(1): 123-127.
WEI Wu,HUANG Xin-han,ZHANG Qi-sen, et al. A method of recognizing characters in vehicle license-plates using pattern match and neural networks [J]. Pattern Recognition and Artificial Intelligence, 2001, 14(1): 123-127.
[5] 侯海滨,沈希忠,孙林. 基于多分类器的牌照字符识别算法[J]. 华东理工大学学报: 自然科学版, 2010(2): 290-294.
HOU Hai-bin, SHEN Xi-zhong, SUN Lin. Novel license plate character recognition algorithm based on multi-classifier [J]. Journal of East China University of Science and Technology: Natural Science Edition, 2010(2): 290-294.
[6] HAYKIN S. Neural networks and learning machines [M]. New York: Prentice Hall, 2009.
[7] HUANG G B, WANG D H, LAN Y. Extreme learning machines: a survey [J]. International Journal of Machine Learning and Cybernetics, 2011, 2(2): 107-122.
[8] HUANG G B, ZHOU H M, DING X J, et al. Extreme learning machine for regression and multiclass classification [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2012, 42(2): 513-529.
[9] RUMELHART D E, MCCLELLAND J L, GROUP P R. Parallel distributed processing: explorations in the microstructure of cognition [J]. Computational models of cognition and perception, 1988, 1(1): 354-362.
[10] ZHANG G P. Neural networks for classification: a survey [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2000, 30(4): 451-462.
[11] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: theory and applications [J]. Neurocomputing, 2006, 70(1): 489-501.
[12] HUANG G B, CHEN L. Enhanced random search based incremental extreme learning machine [J]. Neurocomputing, 2008, 71(16): 3460-3468.
[13] ZHANG B L, FU M Y, YAN H. A nonlinear neural network model of mixture of local principal component analysis: application to handwritten digits recognition [J]. Pattern Recognition, 2001, 34(2): 203-214.
[14] KUSSUL E, BAIDYK T. Improved method of handwritten digit recognition tested on MNIST database [J]. Image and Vision Computing, 2004, 22(12): 971-981.
[15] 邓万宇,郑庆华,陈琳,等. 神经网络极速学习方法研究[J]. 计算机学报, 2010, 33(2): 279-287.
DENG Wan-yu, ZHENG Qing-hua, CHEN Lin, et al. Research on extreme learning of neural networks [J]. Chinese Journal of Computers, 2010, 33(2): 279-287.
[16] XUE G Z. Introduction to statistical learning theory and support vector machines [J]. Acta Automatica Sinica, 2000, 26(1): 32-42.
[17] 郑永凯,张凌,董守斌. 图像灰度分布标准化算法研究[J]. 小型微型计算机系统, 2002, 23(10): 1218-1221.
ZHENG Yong-kai, ZHANG Ling, DONG Shou-bin. Algorithm on greyscale distribution normalization of face image [J]. Mini-micro Systems, 2002, 23(10): 1218-1221.
[18] LU C B, GU C Q. The computation of the inverse of block-wise centrosymmetric matrices [J]. Publicationes Mathematicae Debrecen, 2013, 82(2): 379-397.
[19] LU C B, GU C Q. The computation of the square roots of circulant matrices [J]. Applied Mathematics and Computation, 2011, 217(16): 6819-6829.
[20] 刘进锋,郭雷. CPU 与 GPU 上几种矩阵乘法的比较与分析[J]. 计算机工程与应用, 2011, 47(19): 911.
LIU Jin-feng, GUO Lei. Comparison and analysis of matrix multiplications on GPU and CPU [J]. Computer Engineering and Applications, 2011, 47(19): 911.

[1] 王海艳, 程严. 基于离散系数的双向服务选择方法[J]. 浙江大学学报(工学版), 2017, 51(6): 1197-1204.
[2] 袁友伟, 余佳, 郑宏升, 王娇娇. 基于新颖性排名和多服务质量的云工作流调度算法[J]. 浙江大学学报(工学版), 2017, 51(6): 1190-1196.
[3] 许荣斌, 石军, 张鹏飞, 谢莹. Petri网的映射变迁关系相似性度量[J]. 浙江大学学报(工学版), 2017, 51(6): 1205-1213.
[4] 常超, 刘克胜, 谭龙丹, 贾文超. 基于图模型的C程序数据流分析[J]. 浙江大学学报(工学版), 2017, 51(5): 1007-1015.
[5] 王继奎. 贝叶斯冲突Web数据可信度算法[J]. 浙江大学学报(工学版), 2016, 50(12): 2380-2385.
[6] 涂鼎, 陈岭, 陈根才, 吴勇, 王敬昌. 基于在线层次化非负矩阵分解的文本流主题检测[J]. 浙江大学学报(工学版), 2016, 50(8): 1618-1626.
[7] 杨莎, 叶振宇, 王淑刚, 陶海, 李石坚, 潘纲, 朱斌. 感认知增强的智能机械手系统[J]. 浙江大学学报(工学版), 2016, 50(6): 1155-1159.
[8] 罗林, 苏宏业, 班岚. Dirichlet过程混合模型在非线性过程监控中的应用[J]. 浙江大学学报(工学版), 2015, 49(11): 2230-2236.
[9] 汪宏浩, 王慧泉, 金仲和. 基于增量链接的可回滚星载软件在轨更新方法[J]. 浙江大学学报(工学版), 2015, 49(4): 724-731.
[10] 王继奎, 李少波. 基于真值发现的冲突数据源质量评价算法[J]. 浙江大学学报(工学版), 2015, 49(2): 303-318.
[11] 蔡华林,陈刚,陈珂. 多类别复合资源的空间匹配[J]. 浙江大学学报(工学版), 2015, 49(1): 69-78.
[12] 俞东进,殷昱煜,吴萌萌,刘愉. 基于混合协同过滤的Web服务QoS预测方法[J]. 浙江大学学报(工学版), 2014, 48(11): 2039-2045.
[13] 刘智慧, 张泉灵. 大数据技术研究综述[J]. 浙江大学学报(工学版), 2014, 48(6): 957-972.
[14] 田甜,巩敦卫. 基于覆盖难度选择路径的测试数据进化生成[J]. 浙江大学学报(工学版), 2014, 48(5): 948-994.
[15] 柯海丰,应晶. 基于R-ELM的实时车牌字符识别技术[J]. J4, 2014, 48(2): 0-0.