[1]方承志,周品,付世清. 基于小波核LS-SVM的车牌字符识别算法研究[J].计算机技术与发展,2015,25(03):86-90.
　FANG Cheng-zhi,ZHOU Pin,FU Shi-qing. Research on Plate Character Recognition Based on Wavelet Kernel LS-SVM[J].,2015,25(03):86-90.
点击复制

 基于小波核LS-SVM的车牌字符识别算法研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
25
期数:
2015年03期
页码:
86-90
栏目:
智能、算法、系统工程
出版日期:
2015-03-10

文章信息/Info

Title:
 Research on Plate Character Recognition Based on Wavelet Kernel LS-SVM
文章编号:
1673-629X（2015)03-0086-05
作者:
 方承志; 周品; 付世清
 南京邮电大学 电子科学与工程学院
Author(s):
 FANG Cheng-zhi; ZHOU Pin; FU Shi-qing
关键词:
 ; 字符识别; LS-SVM; 小波核函数; 多级分类器
Keywords:
 ; character recognition; LS-SVM; wavelet kernel function; multi-classifier
分类号:
TP391.4
文献标志码:
A
摘要:
 字符识别是整个车牌识别系统至关重要的一步，决定着系统最终的识别率。文中不同于传统的SVM识别方法，而是采用了LS-SVM为基础的新颖方法，从而简化了SVM优化问题的求解。鉴于车牌字符的独特性，将小波函数作为LS-SVM的核函数。结合字符和字符识别的特征，分析小波核函数的可行性，最后通过实验结果横向、纵向对比，得出小波核函数的优势。实验结果表明，相比于传统的神经网络和模板匹配等字符识别算法，提高了车牌系统的识别率；与传统SVM识别算法相比，亦减少了车牌的识别时间。
Abstract:
 Plate character recognition is a most important step of the whole plate recognition system,which determines the final system recognition rate. The method LS-SVM used in this paper is different from the traditional SVM,which simplifies the SVM optimization. In view of the specialty of plate character,take the wavelet function as the kernel function for LS-SVM. Combined with the feature of character and character recognition,analyze the feasibility of this wavelet kernel function,finally through the experimental results of verti-cal and horizontal comparison,the advantage of wavelet kernel function is obtained. Compared with other algorithms such as Neural Net-work and Template Matching,this method has improved the recognition rate while the recognition time is reduced.

相似文献/References:

[1]安然 张少军 陈华 喻振华.字符识别中毛刺的去除方法[J].计算机技术与发展,2007,(09):136.
　AN Ran,ZHANG Shao-jun,CHEN Hua,et al.Method for Removing Burr to Optical Character Recognition[J].,2007,(03):136.
[2]张庆丰 岑豫皖 杜培明.数显数字字符图像特征提取算法的研究与实现[J].计算机技术与发展,2007,(11):39.
　ZHANG Qing-feng,CEN Yu-wan,DU Pei-ming.Study and Realization for Numeral Instrument Image Feature Extraction Method[J].,2007,(03):39.
[3]陈卿 袁保社 李晓 任宏宇 张建华[].基于模板匹配的印刷维吾尔文字符识别研究[J].计算机技术与发展,2012,(04):119.
　CHEN Qing,YUAN Bao-she,LI Xiao,et al.Printed Uyghur Character Recognition Based on Template Matching[J].,2012,(03):119.
[4]王鹏 杜卫东 汪立新 张峰 韩伟 吕志刚.基于连通域特征的射线胶片信息识别技术研究[J].计算机技术与发展,2012,(12):119.
　WANG Peng,DU Wei-dong,WANG Li-xin,et al.Ray Film Character Recognition Technology Research Based on Connected Domain Characteristic[J].,2012,(03):119.
[5]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(03):1.
[6]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(03):5.
[7]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
　HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(03):13.
[8]侯善江[],张代远[][][]. 基于样条权函数神经网络P2P流量识别方法[J].计算机技术与发展,2014,24(07):21.
　HOU Shan-jiang[],ZHANG Dai-yuan[][][]. P2P Traffic Identification Based on Spline Weight Function Neural Network[J].,2014,24(03):21.
[9]李璨,耿国华,李康,等. 一种基于三维模型的文物碎片线图生成方法[J].计算机技术与发展,2014,24(07):25.
　LI Can,GENG Guo-hua,LI Kang,et al. A Method of Obtaining Cultural Debris’ s Line Chart Based on Three-dimensional Model[J].,2014,24(03):25.
[10]翁鹤,皮德常. 混沌RBF神经网络异常检测算法[J].计算机技术与发展,2014,24(07):29.
　WENG He,PI De-chang. Chaotic RBF Neural Network Anomaly Detection Algorithm[J].,2014,24(03):29.

更新日期/Last Update: 2015-05-04