车牌识别系统关键技术研究
|
摘要
车牌识别系统作为智能交通系统的重要组成部分,它在违章抓拍、停车场管理、智能小区交通管理和重要关卡车辆登记等方面有重要作用。本文从实际应用角度出发,针对城市道路以及高速公路等室外背景,对车牌识别系统中车牌定位、字符分割、字符识别等算法系统地进行了研究,论文主要工作如下：
在对现有的车牌定位算法进行研究比较的基础上,采用基于边缘检测和形态学处理的车牌定位算法,对Sobel边缘检测进行了改进,通过设定阈值来降低周围背景中细小边缘的干扰；并利用基于形态学处理的连通域分析,完成车牌定位。
在字符分割方面,采用基于最小二乘和最小投影距离相结合的车牌倾斜校正法方,在水平校正时,利用最小二乘拟合直线的方法求取倾斜角；在垂直校正时,利用了改进的最小投影距离法,降低了算法的执行次数,提高了执行效率。对校正后的车牌又利用投影法进行分割,并对存在粘连和分裂情况的字符进行了特殊处理。
在特征提取方面,采用基于小波变换和Zernike矩的组合特征,小波变换系数提取了字符的细节特征,Zernike矩提取了字符的全局特征,二者的组合特征更全面的区分了每个字符,并利用主元分析法对小波变换系数进行降维,去除相关性较大的量,降低了算法的运算量。最后对神经网络字符识别和支持向量机字符识别进行了分析,利用支持向量机设计车牌字符分类器,不仅识别率高、测试误差小,而且具有较强的泛化能力。
最后,在Matlab仿真平台上,对大量车牌图像进行了测试,结果表明,所改进的算法具有较高的有效性和实际应用价值。
As an important part of intelligent transportation systems, the license plate recognition system has an important role in violation enforcement, parking management, intelligent traffic management and the important points of vehicle registration. From the view of practical application, some researches have been done on license plate location, license plate segmentation and character recognition against the outdoor background of urban roads and highways. The main work is as follows:
On the basis of studying the existing vehicle license plate location algorithms, An License plate location based on edge detection and mathematical morphology has been presented.The Sobel edge detection has been improved, by setting the threshold to reduce the small edges'disturbance around the background, through using connected domain analyses based on morphological processing to complete the license plate location.
In terms of character segmentation, first, a tilt correction of license plate based on least squares and minimum projection distance has been put forwarded, on level correction, using least square to fit a straight line for obtaining the slope angle, on vertical correction, using an improved minimum projection distance method, it has reduced the number of execution and improved the execution efficiency. To the licenses which have been corrected has been segmented using modified projection method. Also the characters which are adhesion and fragmentation have been given special treatment.
In terms of extraction, a feature extraction based on Wavelet transform and Zernike has been presented.wavelet transform has extract the details of character features, Zernike moments has extract the global character features, the combination of those has distincted the character between each other. And using principal component analysis to reduce some features which have large correlation with others, the number of the operation of algorithm also has been reduced.Last, based on the analysis of the neural networks and support vector machine(SVM), using SVM to design the network of license plate characters, it has not only high recognition rate, small measurement error, but also a strong generalization.
Finally, on the Matlab simulation platform, a large number of plate images has been tested. Results show that the improvement algorithms have high effectiveness and the value of practical application.
在对现有的车牌定位算法进行研究比较的基础上,采用基于边缘检测和形态学处理的车牌定位算法,对Sobel边缘检测进行了改进,通过设定阈值来降低周围背景中细小边缘的干扰；并利用基于形态学处理的连通域分析,完成车牌定位。
在字符分割方面,采用基于最小二乘和最小投影距离相结合的车牌倾斜校正法方,在水平校正时,利用最小二乘拟合直线的方法求取倾斜角；在垂直校正时,利用了改进的最小投影距离法,降低了算法的执行次数,提高了执行效率。对校正后的车牌又利用投影法进行分割,并对存在粘连和分裂情况的字符进行了特殊处理。
在特征提取方面,采用基于小波变换和Zernike矩的组合特征,小波变换系数提取了字符的细节特征,Zernike矩提取了字符的全局特征,二者的组合特征更全面的区分了每个字符,并利用主元分析法对小波变换系数进行降维,去除相关性较大的量,降低了算法的运算量。最后对神经网络字符识别和支持向量机字符识别进行了分析,利用支持向量机设计车牌字符分类器,不仅识别率高、测试误差小,而且具有较强的泛化能力。
最后,在Matlab仿真平台上,对大量车牌图像进行了测试,结果表明,所改进的算法具有较高的有效性和实际应用价值。
As an important part of intelligent transportation systems, the license plate recognition system has an important role in violation enforcement, parking management, intelligent traffic management and the important points of vehicle registration. From the view of practical application, some researches have been done on license plate location, license plate segmentation and character recognition against the outdoor background of urban roads and highways. The main work is as follows:
On the basis of studying the existing vehicle license plate location algorithms, An License plate location based on edge detection and mathematical morphology has been presented.The Sobel edge detection has been improved, by setting the threshold to reduce the small edges'disturbance around the background, through using connected domain analyses based on morphological processing to complete the license plate location.
In terms of character segmentation, first, a tilt correction of license plate based on least squares and minimum projection distance has been put forwarded, on level correction, using least square to fit a straight line for obtaining the slope angle, on vertical correction, using an improved minimum projection distance method, it has reduced the number of execution and improved the execution efficiency. To the licenses which have been corrected has been segmented using modified projection method. Also the characters which are adhesion and fragmentation have been given special treatment.
In terms of extraction, a feature extraction based on Wavelet transform and Zernike has been presented.wavelet transform has extract the details of character features, Zernike moments has extract the global character features, the combination of those has distincted the character between each other. And using principal component analysis to reduce some features which have large correlation with others, the number of the operation of algorithm also has been reduced.Last, based on the analysis of the neural networks and support vector machine(SVM), using SVM to design the network of license plate characters, it has not only high recognition rate, small measurement error, but also a strong generalization.
Finally, on the Matlab simulation platform, a large number of plate images has been tested. Results show that the improvement algorithms have high effectiveness and the value of practical application.
引文
1.任殿波,张京明,崔胜民等.智能交通系统车道保持纵横向耦合控制[J].控制理论与应用,2010,27(12)：1661-1668
2.单家凌.基于无线网络车牌识别系统识别算法的研究[J].计算机测量与控制,2011,19(1)：124-126
3. 陆尚平,文友先,葛维等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10)：190-194
4. 张宇.基于神经网络信息融合的印刷体字符识别研究[J].微型机与应用,2009,28(21)：22-28
5.温雯,高歌.基于RFID射频识别技术的道路交通管理系统设计与开发[J].制造业自动化,2011,33(8)：151-153
6.许伦辉,陈衍平,修科鼎.基于图像处理的静态车牌识别技术[J],江西理工大学学报,2011,32(1)：47-50
7. 杨治明,王晓蓉,彭军等.BP人工神经网络在图像分割中的应用[J].计算机科学,2007,34(3)：234-236
8.余春琴,张浩然,李广林.车牌识别系统技术的研究与应用[J].电子技术,2010,37(12)：49-50
9. Kim K I, Jung K, Kim J H. Fast Color Texture-Based Object Detection in Images Application to License Plate Localization[J]. Lecture Notes on Computer Science,2005, 177:295-320
10. Broumandnia A, Fathy M. Application of Pattern Recognition for Farsi License Plate Recognition[OL]. http://www.icgst.com/gvip/v2/Pl 150439001.pdf,2005
11. Chang S L, Chen L S, Chung Y C etc. Automatic License Plate Recognition[J]. IEEE Trans. Intell. Transp. Syst.2004,5(1):42-53
12. Brugge M H, Stevens J H, Nijhuis J A etc. License Plate Recognition Using DTCNNs[J]. Workshop Cellular Neural Netw.1998,212-217
13. Chacon M I, Zimmerman A.License Plate Location Based on a Dynamic PCNN Scheme[J]. Neural Netw.2003,2:1195-1200
14. Kim K K, Kim K I, Kim J B etc. Learning-based Approach on License Plate Recognition[J]. Signal Process.2000,2:614-623
15. Nomura S, Yamanaka K, Katai O etc. A Novel Adaptive Morphological Approach for Degraded Character Image Segmentation[J]. Pattern Recognit.2005,38(11):1961-1975
16. Cui Y, Huang Q. Extracting Characters of License Plates from Video Sequences[J]. Mach. Vis. Appl.1998,10(5/6):308-320
17.安勇,张高伟.基于灰度图像的车牌识别系统[J].计算机工程与科学,2006,28,(2)：61-65
18.吴一全,张金矿.基于投影坐标p次方差及粒子群的车牌倾斜检测[J].计算机辅助设计与图形学学报,2010,22(1)：114-120
19.尚赵伟,国庆,马尚君等.基于二进小波变换的多车牌定位算法[J].计算机工程, 2011,37(3)：16-18
20.高全华,王晋国,孙锋利.基于Pseudo-Zernike不变矩的PNN车牌汉字识别[J].计算机工程,2009,35(4)：196-198
21.徐应涛,陆福宏,张莹.基于填充函数法训练BP神经网络的车牌字符识别算法[J].计算机工程与科学,2009,31(5)：59-61
22.曾飞.基于置信度分析和特征融合的车牌识别研究[J].湘潭师范学院学报(自然科学版),2009,31(4)：44-47
23.杨晓敏,何小海,吴炜等.基于高斯混合模型的车辆字符识别算法[J].光电子激光,2007,18(4)：487-490
24.马胜前,张光南,杨金龙等.基于二维直方图的Qtsu图像分割算法改进[J].西北师范大学学报(自然科学版),2009,45(1)：57-61
25.李字成,王目树.一种快速的车牌定位与提取算法[J].计算机工程与科学,2010,32(12)：42-45
26.王建,刘立,王天慧.基于四元数特定颜色对边缘检测的车牌定位[J].计算机应用,2011,31(3)：729-732
27.郑成勇.一种RGB颜色空间中的车牌定位新方法[J].中国图象图形学报,2010,15(11)：1623-1628
28.张浩鹏,王宗义.基于灰度方差和边缘密度的车牌定位算法[J].仪器仪表学报,2011,32(5)：1095-1102
29.张立国,杨瑾,李晶等.基于小波包和数学形态学结合的图像特征提取方法[J].仪器仪表学报,2010,31(10)：2285-2290
30.王成,黎绍发,何凯.基于简化PCNN的车牌定位算法[J].计算机工程,2010,36(24)：178-182
31.章品正,王健弘.一种应用机器学习的车牌定位方法[J].应用科学学报,2011,29,(2)：147-152
32.潘巍,刘宏宇,安荣等.一种梯度特征与区域合并的车牌定位方法[J].计算机工程与应用,2011,47(18)：204-206
33.阮秋奇.数字图像处理学[M].北京：电子工业出版社,2001
34.严国萍,戴若愚,潘晴等.基于LOG算子的自适应图像边缘检测方法[J].华中科技大学学报(自然科学版),2008,36(3)：85-87
35.宋锟,万燕,姚砺.基于Canny算子和轮廓方向图的异形纤维轮廓增强算法[J].东华大学学报(自然科学版),2011,37(2)：187-192
36.唐常青,吕红伯.数学形态学方法及其应用[M].北京：科学出版社,1990
37. Li Guihui, Li Yuanjin, Li Lanyou. Study on the Vehicle License Plate Tilt Correction[J]. Chines Journal of Scientific Instrument,2006,27(26):715-717
38.王枚,王国宏.基于字符投影最小距离的车牌校正方法[J].计算机工程,2008,34(6)：216-218
39.张云刚,张长水.利用Hough变换和先验知识的车牌字符分割算法[J].计算机学报2004, 27(1)：130-134
40.宋万里,张鸰.车牌识别中的倾斜车牌校正算法[J].科技信息,2011,(14)：43-44
41.朱程辉,吴德会.基于主元分析的倾斜车牌图像校正方法研究[J].微电子学与计算机,2006,23(1)：177-180
42.吴一全,丁坚.基于K-L展开式的车牌倾斜校正方法[J].仪器仪表学报,2008,29(8)：1690-1694
43.夏勇,戴汝为,肖柏华等.基于OCR与词形状编码的英文扫描文档检索[J].模式识别与人工智能,2009,22(3)：151-156
44.何东健.数字图像处理[M].西安：西安电子科技大学出版社,2008
45. HUANG Wei, LU Xiaobo, LING Xiaojing.Wavelet Packet Based Feature Extraction and Recognition of License Plate Characters[J].Chinese Science Bulletin,2005,50(2):97-100
46.潘梅森,郭国强.基于图像矩的车牌号码倾斜校正[J].计算机辅助设计与图形学学报,2007,19(8)：1041-1045
47.常淑英,臧永杰,戴士杰.基于字符间隙和垂直投影特征的铁路货车编码分割算法研究[J].河北工业大学学报,2011,40(2)：59-61
48.古辉,王益义.一种基于模板匹配的船铭牌字符分割方法[J].浙江工业大学学报,2010,38(1)：33-35
49.甘玲,林小晶.基于连通域提取的车牌字符分割算法[J].计算机仿真,2011,28(4)：336-339
50.姬光荣,乔小燕,郑海等.基于骨架的角毛藻显微图像特征提取[J].中国海洋大学学报(自然科学版),2010,40(11)：129-133
51.杨明,刘强,尹忠科等.基于轮廓追踪的字符识别特征提取[J].计算机工程与应用,2007,43(20)：207-209
52.董玲娇.车牌自动识别中的字符特征提取[J].机电工程,2008,25(9)：106-108
53.马北河,陈丽,雷亮等.实时联合傅立叶变换相关识别在车牌字符识别中的应用[J].广东工业大学学报,2009,26(3)：68-71
54.赵先锋.离散K-L变换在汽车车牌字符识别中的应用一例[J].仪器仪表学报,2004,25(3)
55.李建美,路长厚,李国平.基于Gabor变换的凹凸字符图像特征抽取新方法[].系统仿真学报,2008,20(8)：2133-21236
56.曹建海,路长厚.基于小波变换和DCT的字符图像特征抽取新方法.光电子·激光,2004,15(4)：79-85
57.郭招球,赵跃龙,高敬欣.基于小波和神经网络的车牌字符识别新方法[J].计算机测量与控制,2006,14(9)：1257-1259
58. Lazaridis G, Petrou M. Image Registration Using the Walsh Transform [J]. IEEE Transactions on Image Processing,2006,15(8):2343-2357
59.何通能,贾志勇.基于小波矩的车牌字符识别研究[J].浙江工业大学学报,2005,33,(2)：170-172
60. Duda Richard O, Hart Peter E, Stork David G. Pattern Classification, Second Edition[M]. America:John Wiley & Sons,2001
61.单宝忠,王淑岩,牛憨笨等.多项式拟合方法及应用[J],光学精密工程,2002,10(3)：318-322
62.田代军,周泽华,杨奇.仿Kronecker符号及其应用[J].数学的实践与认识,2007,37(19)：161-167
63.文传军,詹永照.基于自调节分类面SVM的平衡不平衡数据分类[J].系统工程,2009,37(3)：110-113
64.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),2010,36(2)：290-294
65.王歌,谢松云,党正.基于双神经网络分类器的脱机手写体汉字识别[J].西北工业大学学报,2010,28(4)：574-577
66.王润民,钱盛友,姚畅.一种基于GA和支持向量机的车牌字符识别方法[J].计算机工程与应用,2008,44(17)：231-233
2.单家凌.基于无线网络车牌识别系统识别算法的研究[J].计算机测量与控制,2011,19(1)：124-126
3. 陆尚平,文友先,葛维等.基于机器视觉的甘蔗茎节特征提取与识别[J].农业机械学报,2010,41(10)：190-194
4. 张宇.基于神经网络信息融合的印刷体字符识别研究[J].微型机与应用,2009,28(21)：22-28
5.温雯,高歌.基于RFID射频识别技术的道路交通管理系统设计与开发[J].制造业自动化,2011,33(8)：151-153
6.许伦辉,陈衍平,修科鼎.基于图像处理的静态车牌识别技术[J],江西理工大学学报,2011,32(1)：47-50
7. 杨治明,王晓蓉,彭军等.BP人工神经网络在图像分割中的应用[J].计算机科学,2007,34(3)：234-236
8.余春琴,张浩然,李广林.车牌识别系统技术的研究与应用[J].电子技术,2010,37(12)：49-50
9. Kim K I, Jung K, Kim J H. Fast Color Texture-Based Object Detection in Images Application to License Plate Localization[J]. Lecture Notes on Computer Science,2005, 177:295-320
10. Broumandnia A, Fathy M. Application of Pattern Recognition for Farsi License Plate Recognition[OL]. http://www.icgst.com/gvip/v2/Pl 150439001.pdf,2005
11. Chang S L, Chen L S, Chung Y C etc. Automatic License Plate Recognition[J]. IEEE Trans. Intell. Transp. Syst.2004,5(1):42-53
12. Brugge M H, Stevens J H, Nijhuis J A etc. License Plate Recognition Using DTCNNs[J]. Workshop Cellular Neural Netw.1998,212-217
13. Chacon M I, Zimmerman A.License Plate Location Based on a Dynamic PCNN Scheme[J]. Neural Netw.2003,2:1195-1200
14. Kim K K, Kim K I, Kim J B etc. Learning-based Approach on License Plate Recognition[J]. Signal Process.2000,2:614-623
15. Nomura S, Yamanaka K, Katai O etc. A Novel Adaptive Morphological Approach for Degraded Character Image Segmentation[J]. Pattern Recognit.2005,38(11):1961-1975
16. Cui Y, Huang Q. Extracting Characters of License Plates from Video Sequences[J]. Mach. Vis. Appl.1998,10(5/6):308-320
17.安勇,张高伟.基于灰度图像的车牌识别系统[J].计算机工程与科学,2006,28,(2)：61-65
18.吴一全,张金矿.基于投影坐标p次方差及粒子群的车牌倾斜检测[J].计算机辅助设计与图形学学报,2010,22(1)：114-120
19.尚赵伟,国庆,马尚君等.基于二进小波变换的多车牌定位算法[J].计算机工程, 2011,37(3)：16-18
20.高全华,王晋国,孙锋利.基于Pseudo-Zernike不变矩的PNN车牌汉字识别[J].计算机工程,2009,35(4)：196-198
21.徐应涛,陆福宏,张莹.基于填充函数法训练BP神经网络的车牌字符识别算法[J].计算机工程与科学,2009,31(5)：59-61
22.曾飞.基于置信度分析和特征融合的车牌识别研究[J].湘潭师范学院学报(自然科学版),2009,31(4)：44-47
23.杨晓敏,何小海,吴炜等.基于高斯混合模型的车辆字符识别算法[J].光电子激光,2007,18(4)：487-490
24.马胜前,张光南,杨金龙等.基于二维直方图的Qtsu图像分割算法改进[J].西北师范大学学报(自然科学版),2009,45(1)：57-61
25.李字成,王目树.一种快速的车牌定位与提取算法[J].计算机工程与科学,2010,32(12)：42-45
26.王建,刘立,王天慧.基于四元数特定颜色对边缘检测的车牌定位[J].计算机应用,2011,31(3)：729-732
27.郑成勇.一种RGB颜色空间中的车牌定位新方法[J].中国图象图形学报,2010,15(11)：1623-1628
28.张浩鹏,王宗义.基于灰度方差和边缘密度的车牌定位算法[J].仪器仪表学报,2011,32(5)：1095-1102
29.张立国,杨瑾,李晶等.基于小波包和数学形态学结合的图像特征提取方法[J].仪器仪表学报,2010,31(10)：2285-2290
30.王成,黎绍发,何凯.基于简化PCNN的车牌定位算法[J].计算机工程,2010,36(24)：178-182
31.章品正,王健弘.一种应用机器学习的车牌定位方法[J].应用科学学报,2011,29,(2)：147-152
32.潘巍,刘宏宇,安荣等.一种梯度特征与区域合并的车牌定位方法[J].计算机工程与应用,2011,47(18)：204-206
33.阮秋奇.数字图像处理学[M].北京：电子工业出版社,2001
34.严国萍,戴若愚,潘晴等.基于LOG算子的自适应图像边缘检测方法[J].华中科技大学学报(自然科学版),2008,36(3)：85-87
35.宋锟,万燕,姚砺.基于Canny算子和轮廓方向图的异形纤维轮廓增强算法[J].东华大学学报(自然科学版),2011,37(2)：187-192
36.唐常青,吕红伯.数学形态学方法及其应用[M].北京：科学出版社,1990
37. Li Guihui, Li Yuanjin, Li Lanyou. Study on the Vehicle License Plate Tilt Correction[J]. Chines Journal of Scientific Instrument,2006,27(26):715-717
38.王枚,王国宏.基于字符投影最小距离的车牌校正方法[J].计算机工程,2008,34(6)：216-218
39.张云刚,张长水.利用Hough变换和先验知识的车牌字符分割算法[J].计算机学报2004, 27(1)：130-134
40.宋万里,张鸰.车牌识别中的倾斜车牌校正算法[J].科技信息,2011,(14)：43-44
41.朱程辉,吴德会.基于主元分析的倾斜车牌图像校正方法研究[J].微电子学与计算机,2006,23(1)：177-180
42.吴一全,丁坚.基于K-L展开式的车牌倾斜校正方法[J].仪器仪表学报,2008,29(8)：1690-1694
43.夏勇,戴汝为,肖柏华等.基于OCR与词形状编码的英文扫描文档检索[J].模式识别与人工智能,2009,22(3)：151-156
44.何东健.数字图像处理[M].西安：西安电子科技大学出版社,2008
45. HUANG Wei, LU Xiaobo, LING Xiaojing.Wavelet Packet Based Feature Extraction and Recognition of License Plate Characters[J].Chinese Science Bulletin,2005,50(2):97-100
46.潘梅森,郭国强.基于图像矩的车牌号码倾斜校正[J].计算机辅助设计与图形学学报,2007,19(8)：1041-1045
47.常淑英,臧永杰,戴士杰.基于字符间隙和垂直投影特征的铁路货车编码分割算法研究[J].河北工业大学学报,2011,40(2)：59-61
48.古辉,王益义.一种基于模板匹配的船铭牌字符分割方法[J].浙江工业大学学报,2010,38(1)：33-35
49.甘玲,林小晶.基于连通域提取的车牌字符分割算法[J].计算机仿真,2011,28(4)：336-339
50.姬光荣,乔小燕,郑海等.基于骨架的角毛藻显微图像特征提取[J].中国海洋大学学报(自然科学版),2010,40(11)：129-133
51.杨明,刘强,尹忠科等.基于轮廓追踪的字符识别特征提取[J].计算机工程与应用,2007,43(20)：207-209
52.董玲娇.车牌自动识别中的字符特征提取[J].机电工程,2008,25(9)：106-108
53.马北河,陈丽,雷亮等.实时联合傅立叶变换相关识别在车牌字符识别中的应用[J].广东工业大学学报,2009,26(3)：68-71
54.赵先锋.离散K-L变换在汽车车牌字符识别中的应用一例[J].仪器仪表学报,2004,25(3)
55.李建美,路长厚,李国平.基于Gabor变换的凹凸字符图像特征抽取新方法[].系统仿真学报,2008,20(8)：2133-21236
56.曹建海,路长厚.基于小波变换和DCT的字符图像特征抽取新方法.光电子·激光,2004,15(4)：79-85
57.郭招球,赵跃龙,高敬欣.基于小波和神经网络的车牌字符识别新方法[J].计算机测量与控制,2006,14(9)：1257-1259
58. Lazaridis G, Petrou M. Image Registration Using the Walsh Transform [J]. IEEE Transactions on Image Processing,2006,15(8):2343-2357
59.何通能,贾志勇.基于小波矩的车牌字符识别研究[J].浙江工业大学学报,2005,33,(2)：170-172
60. Duda Richard O, Hart Peter E, Stork David G. Pattern Classification, Second Edition[M]. America:John Wiley & Sons,2001
61.单宝忠,王淑岩,牛憨笨等.多项式拟合方法及应用[J],光学精密工程,2002,10(3)：318-322
62.田代军,周泽华,杨奇.仿Kronecker符号及其应用[J].数学的实践与认识,2007,37(19)：161-167
63.文传军,詹永照.基于自调节分类面SVM的平衡不平衡数据分类[J].系统工程,2009,37(3)：110-113
64.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),2010,36(2)：290-294
65.王歌,谢松云,党正.基于双神经网络分类器的脱机手写体汉字识别[J].西北工业大学学报,2010,28(4)：574-577
66.王润民,钱盛友,姚畅.一种基于GA和支持向量机的车牌字符识别方法[J].计算机工程与应用,2008,44(17)：231-233