一种有效的提高车牌首字符识别率的方法

计算机科学 ›› 2013, Vol. 40 ›› Issue (Z6): 176-179.

一种有效的提高车牌首字符识别率的方法

吕文强,杨健

南京理工大学计算机科学与技术学院南京210094;南京理工大学计算机科学与技术学院南京210094

出版日期:2018-11-16 发布日期:2018-11-16

Effective Way of Improving the Recognition Rate of License Plate’s First Character

LV Wen-qiang and YANG Jian

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 针对车牌识别系统中由于低质车牌首字符特征提取困难而导致车牌首字符识别率不高的问题,提出了一种新的车牌汉字特征提取方法。该方法首先对车牌首字符的二值图像进行网格化处理,并对每一块网格区域提取字符笔画所在像素的占空比、散度和质心3个特征分量,接着将提取到的所有的特征向量用支持向量机分类器进行训练,最终可以得到一组鲁棒性很强的分类器。实验结果表明,该特征提取方法与支持向量机分类器结合可以较大地提高车牌首字符的识别率。

关键词: 车牌识别,支持向量机,字符识别,形状参数

Abstract: This paper offers a new method of extracting feature for solving the problem of the low Chinese character recognition rate resulted from the poor quality of the Chinese character image in the license plate recognition system．Firstly,the binary Chinese character image that has been segmented is divided into many blocks．Secondly,this paper extracts three stroke pixel’s feature components that include the proportion of stroke pixels in the block,the divergence and the centroid for each block．Thirdly,this paper combines the new feature extraction method with the SVM classifier．At last,a group of robust classifiers are obtained．The experimental results show that the Chinese character recognition rate can be improved greatly.

Key words: License plate recognition,Support vector machine,Character recognition,Shape parameter

吕文强,杨健. 一种有效的提高车牌首字符识别率的方法[J]. 计算机科学, 2013, 40(Z6): 176-179. https://doi.org/

LV Wen-qiang and YANG Jian. Effective Way of Improving the Recognition Rate of License Plate’s First Character[J]. Computer Science, 2013, 40(Z6): 176-179. https://doi.org/

参考文献

[1] 韩立明,王波涛.车牌识别中关键技术的研究与实现[J].计算机工程与设计,2010,1(17):3919-3923
[2] Comelli P,Ferragina P,Graninri M,et al．Optical recognition of motor vehicle license plates[J].IEEE Transactions on Vehicular Technology,1995,4(4):790-799
[3] Ko M,Kim Y．License plate surveillance system using weighted template matching[C]∥Proceeding of the 32nd Applied ImageryPattern Recognition Workshop．2003:269-274
[4] Huang Y,Lai S,Chuang W．A template-based model for license plate recognition[C]∥IEEE International Conference on Networking,Sensing and Control．2004,2:737
[5] Mori S,Suen C,Yamamoto K．Historical review of OCR re-search and development[J]．Proceedings of the IEEE,1992,80(7):1029
[6] Glauberman M.Character recognition for business machines[J]．Electronics,1956,29(2):132-136
[7] Bokser M,inc C,Sunnyvale C．Omnidocument technologies[J]．Proceedings of the IEEE,1992,80(7):1066-1078
[8] Due T,Jain A,Taxt T．Feature extraction methods for character recognition-a survey [J]．Pattern Recognition,1996,9(4):641-662
[9] Koval V,Turchenko V,Kochan V,et al．Smart license plate reco-gnition system based on image processing using neural network[C]∥IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing System．2003(8):125-128
[10] Pan X,Ye X,Zhang S．A hybrid method for robust ear platecharacter recognition[J]．Engineering Applications of Artificial Intelligence,2005,18(8):963-972
[11] Wang W．License plate recognition algorithm based on radial basis function neural networks[C]∥Proceedings of the 2009International Symposium on Intelligent Ubiquitous Computing and Education．2009:38-41
[12] Chi X,Dong J,Liu A,et al．A simple method for Chinese license plate recognition based on support vector machine[C]∥Proc of International Conference Communication,Circuits and Systems Proceeding．2006:2141-2145
[13] 薛磊,杨晓敏,吴炜,等．一种基于KNN与改进SVM的车牌字符识别算法[J].四川大学学报:自然科学版,2006,3(5):1031-1036
[14] 边肇祺,张学工.模式识别(第二版)[M].北京:清华大学出版社,2000
[15] Theodoridis S,Koutroumbas K．Pattern Recognition[M]．北京:电子工业出版社,2010
[16] 奉国和．SVM分类核函数及参数选择比较[J].计算机工程与应用,2011,7(3):123-124
[17] 刘健,刘忠,熊鹰．改进的二叉树支持向量机多类分类算法研究[J].计算机工程与应用,2010,6(33):117-120
[18] 何婕．SVM及其在车牌字符识别中的应用[D]．成都:四川大学,2005

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed