机动车车牌自动识别系统的算法研究
|
摘要
机动车车牌识别(Vehicle License Plate Recognition)系统是智能交通系统的一个重要组成部分,在缓解和管理日益拥堵的城市交通和公路交通中有着举足轻重的作用。目前车牌自动识别系统不仅应用在停车场、高速公路出入口收费、小区车辆管理等简单卡口场景中,也应用在了路况繁杂、交通拥堵的城市十字路口等复杂场景中。
本论文根据数字图像处理、模式识别技术以及统计学习理论,主要针对简单卡口和十字路口两种场景提出车牌自动识别系统中相应的车牌定位和字符识别算法。论文的主要研究工作如下:
1.车牌定位,即从包含车牌的车辆图像中提取出感兴趣的号牌。本文提出了基于投影和密度的车牌定位方法。在对车辆图像进行灰度化、灰度拉伸等一些预处理后,计算水平区域的一阶差分并进行投影得到其一阶差分图,再经过波峰合并和中值滤波定位出车牌的水平位置;然后利用Sobel垂直算子进行边缘检测,通过密度法定位出车牌的左右边界。最后采用Hough变换对定位后的倾斜车牌进行矫正,为字符分割提供更好的数据源。
2.车牌字符识别,即从分割出来的字符图像识别出对应的字符,并以文本形式输出。本文针对两种不同场景分别采用不同的字符识别算法,即针对卡口场景的One-against-One多分类支持向量机算法以及针对十字路口场景的基于Adaboost与多分类支持向量机的组合分类算法。并根据现有车牌标准GA36-2007和GA36-1992结合车牌字符特征的先验知识,将车牌字符分为四大类分别训练,来进一步提高算法的识别率。
本文提出的所有算法都经过Matlab7.0仿真验证,并用C语言实现。实验证明针对卡口场景和十字路口场景的车牌定位算法的准确率分别是97.5%和95.9%,字符识别准确率分别是97.65%和91.48%。
Automatic Vehicle License Plate Recognition System is an important component of the Intelligent Transportation System. It plays an important role in mitigating and managing the increasing congestion in urban traffic and road transport. At present, the Automatic Vehicle License Plate Recognition System is not only used in car parks, highway tolls, residential vehicle management and other simple gate scenes, and also is used in some complex scenes such as urban crossroads which has a complex road conditions and a heavy traffic.
In this paper, according to Digital Image Processing, Pattern Recognition and Statistical Learning Theory, the algorithms of license plate location and character recognition for simple gate scenes and urban crossroads in automatic Vehicle License Plate Recognition System are proposed. Major researches in this paper are as follows:
1. Vehicle license plate location is to extract the license plate from which the vehicles images contain. In this paper, an algorithm for the license plate location based on the density and projection is put forward. After the image preprocessing, such as transformation from color images to gray images and gray stretch, calculate the first-order differential of the whole level region to get the first-order image, and then, the level position of plate can be located through the algorithm of wave merging and the median filtering. Next, using the vertical Sobel edge detection operator, the left and right boundary of plate can be located through the density. Finally, using the Hough transform to correct the located inclined plate for a better data source for character segmentation.
2. License plate character recognition is to identify the corresponding characters from the character images which are from the character segmentation, and give the results in text form. In this paper, two algorithms of character recognition for two different scenes are used respectively, that is the One-against-One multi-class support vector machine algorithm for the gate scenes and the Adaboost algorithm combined with the One-against-One multi-class SVM for the crossroads. And in accordance with standards of China’s existing license plate GA36-2007 and GA36-1992, combining the features of license plate characters, the license characters are divided into four classes, and trained respectively for a better recognition rate.
All algorithms proposed in this paper have been simulated by MATLAB 7.0, and programmed with C. The results show that the accuracy rate of location algorithm for the gate scenes and the crossroads is 97.5% and 95.9%, the accuracy rate of character recognition is 97.65% and 91.48%.
本论文根据数字图像处理、模式识别技术以及统计学习理论,主要针对简单卡口和十字路口两种场景提出车牌自动识别系统中相应的车牌定位和字符识别算法。论文的主要研究工作如下:
1.车牌定位,即从包含车牌的车辆图像中提取出感兴趣的号牌。本文提出了基于投影和密度的车牌定位方法。在对车辆图像进行灰度化、灰度拉伸等一些预处理后,计算水平区域的一阶差分并进行投影得到其一阶差分图,再经过波峰合并和中值滤波定位出车牌的水平位置;然后利用Sobel垂直算子进行边缘检测,通过密度法定位出车牌的左右边界。最后采用Hough变换对定位后的倾斜车牌进行矫正,为字符分割提供更好的数据源。
2.车牌字符识别,即从分割出来的字符图像识别出对应的字符,并以文本形式输出。本文针对两种不同场景分别采用不同的字符识别算法,即针对卡口场景的One-against-One多分类支持向量机算法以及针对十字路口场景的基于Adaboost与多分类支持向量机的组合分类算法。并根据现有车牌标准GA36-2007和GA36-1992结合车牌字符特征的先验知识,将车牌字符分为四大类分别训练,来进一步提高算法的识别率。
本文提出的所有算法都经过Matlab7.0仿真验证,并用C语言实现。实验证明针对卡口场景和十字路口场景的车牌定位算法的准确率分别是97.5%和95.9%,字符识别准确率分别是97.65%和91.48%。
Automatic Vehicle License Plate Recognition System is an important component of the Intelligent Transportation System. It plays an important role in mitigating and managing the increasing congestion in urban traffic and road transport. At present, the Automatic Vehicle License Plate Recognition System is not only used in car parks, highway tolls, residential vehicle management and other simple gate scenes, and also is used in some complex scenes such as urban crossroads which has a complex road conditions and a heavy traffic.
In this paper, according to Digital Image Processing, Pattern Recognition and Statistical Learning Theory, the algorithms of license plate location and character recognition for simple gate scenes and urban crossroads in automatic Vehicle License Plate Recognition System are proposed. Major researches in this paper are as follows:
1. Vehicle license plate location is to extract the license plate from which the vehicles images contain. In this paper, an algorithm for the license plate location based on the density and projection is put forward. After the image preprocessing, such as transformation from color images to gray images and gray stretch, calculate the first-order differential of the whole level region to get the first-order image, and then, the level position of plate can be located through the algorithm of wave merging and the median filtering. Next, using the vertical Sobel edge detection operator, the left and right boundary of plate can be located through the density. Finally, using the Hough transform to correct the located inclined plate for a better data source for character segmentation.
2. License plate character recognition is to identify the corresponding characters from the character images which are from the character segmentation, and give the results in text form. In this paper, two algorithms of character recognition for two different scenes are used respectively, that is the One-against-One multi-class support vector machine algorithm for the gate scenes and the Adaboost algorithm combined with the One-against-One multi-class SVM for the crossroads. And in accordance with standards of China’s existing license plate GA36-2007 and GA36-1992, combining the features of license plate characters, the license characters are divided into four classes, and trained respectively for a better recognition rate.
All algorithms proposed in this paper have been simulated by MATLAB 7.0, and programmed with C. The results show that the accuracy rate of location algorithm for the gate scenes and the crossroads is 97.5% and 95.9%, the accuracy rate of character recognition is 97.65% and 91.48%.
引文
[1]韩居舒.闯红灯车牌的识别:[硕士学位论文].上海:上海交通大学,2007
[2]莫海宁.自然条件下车牌字符识别方法的研究:[硕士学位论文].哈尔滨:哈尔滨工业大学,2006
[3]刘文峰,吴学毅,刘长富.基于RGB色度空间的车牌定位及矫正算法.武汉大学学报, 2006, Vol.31,No.9
[4]李庆庆,张燕平.基于模糊边缘检测算法的车牌定位.计算机技术与发展, 2006, Vol.16,No.12
[5]张引,潘云鹤.彩色汽车图像牌照定位新方法.中国图像图形学报,2001. Vol.6,No.4
[6]许礼武,许伦辉,黄艳国.基于小波分解的车牌定位算法.计算机工程,2006, Vol.32,No.21
[7]张玲,刘勇,何伟.自适应遗传算法在车牌定位中的应用.计算机应用,2008, Vol.28,No.1
[8]边肇祺,张学工等.模式识别[M].第二版.北京:清华大学出版社, 2006
[9]章毓晋.图像分割.北京:科学出版社,2001,26-30
[10] (美)冈萨雷斯(Gonzalez, R. C. )等著;阮秋琦等译.数字图像处理(第二版).北京:电子工业出版社, 2003.3
[11]王润生.图像理解.长沙:国防科技大学出版,1995
[12] Cheng Zhangfan, Chen Rongbao, License Plate Location Method Based on Modified HIS Model of Color Image. Proceedings of 9th International Conference on Electronic Measurement and Instruments, 2009, p 4197-4201
[13] Sun Guangmin, Li Gang, Xu Lei, Wang Jing. A New Method of Vehicle Lecense Plate Location Based on Mathmatical Morphology and Texture Characteristic. 2008 3rd IEEE Conference on Industrial Electronics and Applications, 2008, p 985-988
[14] Bai Hongliang, Liu Changping. A hybrid License Plate Extraction Method Based on Edge Statistics and Morphology. Proceedings - International Conference on Pattern Recognition, 2004, v 2, p 831-834
[15] Wang Jianxia, Gao Guilong, Yang Huili. Research and Implementation of License Plate Location Based on Histogram Division Method. Proceedings of 9th International Conference on Electronic Measurement and Instruments, 2009, p 1230-1233
[16] Cheng Zhang, Guangmin Sun, Deming Chen, Tianxue Zhao. A Rapid Locating Method ofVehicle License Plate Based on Chraacteristics of Characters’Connerction and Projection. 2007 Second IEEE Conference on Industrial Electronics and Applications, 2007, p 2546-2549
[17] Weijuan Wen, Xianglin Huang, Lifang Yang, Zhao Yang, Pengju Zhang. The Vehicle License Plate Location Method Based-on Wavelet Transform. Proceedings of the 2009 International Joint Conference on Computational Sciences and Optimization, 2009, v 2, p 381-384
[18] Haibin Huang, Guangfu Ma, Yufei Zhuang. Vehicle License Plate Location Based on Harris Corner Detection. Proceedings of the International Joint Conference on Neural Networks, 2008, p 352-355
[19] Zhang Pinzheng, Wang Jianhong. A hybrid vehicle license plate location method based on Gentle AdaBoost and corner validation. Proceedings of SPIE - The International Society for Optical Engineering, 2009, v 7495
[20]中华人民共和国公安部.闯红灯自动记录系统通用技术条件. GA/T 496-2004行业标准
[21]中华人民共和国公安部.公路车辆智能监测记录系统通用技术条件. GA/T 497-2004行业标准
[22]中华人民共和国公安部.中华人民共和国机动车号牌. GA36-2007行业标准
[23]中华人民共和国公安部.中华人民共和国机动车号牌. GA36-2007行业标准
[24] Haijiao Wang, Xinnian Wang, Wenju Li, Xiaodan Jia, Color Prior Knowledge-Based License Plate Location Algorithm. 2nd Workshop on Digital Media and its Application in Museum and Heritage, 2007, p 47-52
[25] Zeng Ruili, Li Gang, Xiao Yunkui, Wang mengjun. Algorithm of car license plates location based on multi-feature fusion. Proceedings of the World Congress on Intelligent Control and Automation (WCICA), 2008, p 8465-8470
[26] Haiqi Huang, Ming Gu, Hongyang Chao. An Efficient Method of License Plate Location in Natural-scence Image. 5th International Conference on Fuzzy Systems and Knowledge Discovery, 2008, v 4, p 15-19
[27]刘兴,蒋天发.车牌字符图像分割技术的研究与应用.武汉大学学报,Dec,2006, Vol.39,No.6
[28]周开军.复杂环境下的车牌识别研究:[硕士学位论文].武汉:武汉理工大学,2006
[29] Varsha Kamat, Subramaniam Ganesan. An Efficient Implementation of the Hough Transform for Detecting Vehicle License Plates Using DSP’S. Real-Time Technology and Applications - Proceedings, 1995, p 58-59
[30]别致,周俊生,陈家俊.基于SVM-Adaboost的中文组块分析.计算机工程与应用,2008, 44(21), 171-173
[31]马腾飞,郑永果,赵卫东.基于边缘检测与Hough变换的车牌字符分割算法.系统仿真学报, 2006, Vol. 18, Suppl.1, 391-392
[32]李鸿林,张忠民,羿宗琪.中值滤波技术在图像处理中的应用.信息技术,2004, Vol.28, NO.7
[33]高浩军,杜宇人.中值滤波在图像处理中的应用.电子工程师,2004, Vol.30 No.8
[34] Pan Xiang, Ye Xiuzi, Zhang Sanyuan. A Hybrid Method for Robust Car Plate Character Recognition. Engineering Applications of Artificial Intelligence, December 2005, v 18, n 8, p 963-972,
[35] K.Crammer and Y. Singer. On the learnability and design of output codes for multiclass problems. Computational Learing Theory, 2000, p 35-46
[36] J. Weston and C. Watkins. Multi-class support vector machines. Proceedings of ESANN99, Brussels, 1999
[37]余华.基于快速最近特征线(NFL)的车牌字符识别方法.语音、通信及信号处理. 2007,Vol.26,No.4
[38] Xuchun Li, Lei Wang, Eric Sung. A Study of AdaBoost with SVM Based Weak Learners. Proceedings of the International Joint Conference on Neural Networks, 2005, v 1, p 196-201
[39]王晓丹,孙东延,郑春颖,张宏达,赵学军.一种基于AdaBoost的SVM分类器.空军工程大学学报,2006, Vol.7, No.6
[40]琚旭,王浩,姚宏亮.基于Boosting的支持向量机组合分类器.合肥工业大学学报,2006, Vol.29, No.10, p 1220-1222
[41]张晓龙,任芳.支持向量机与AdaBoost的结合算法研究.计算机应用与研究,2009, Vol.26, No.1, 77-78/110
[42]李亚军,刘晓霞,陈平.改进的AdaBoost算法与SVM的组合分类器.计算机工程与应用, 2008,44(32), 140-142
[43] Xiaolong Zhang, Fang Ren. Improving Svm Learning Accuracy with Adaboost. 4th International Conference on Natural Computation, 2008, v 3, p 221-225
[44] Freund Y. and Schapre R. E. A Decision-theoretical Generalization of On-line Learning and an Application to Boosting. Jouranl of Computer and System Sciences, August 1997, 55(1):119-139,
[45]蒋焰,丁晓青.基于多步校正的改进AdaBoost算法.清华大学学报(自然科学版), 2008,Vol 48,No.10:1613-1616
[46] Hua-jun SONG, Mei-li SHEN, Wei-feng LIU. Target Track System Design Based on SVM and AdaBoost. 1st International Congress on Image and Signal Processing, 2008, v 4, p 652-656
[47] Qingchuan Tao, Xiaohai He, Daishen Luo, Wei Wu. A New Car Plate Recognition Method Based on Fuzzy Entropy. Proceedings of the World Congress on Intelligent Control and Automation (WCICA), 2004, v 5, p 4054-4056
[48] Lihong Zheng, Xiangjian He, Qiang Wu, Wenjing Jia. A Hierarchically Combined Classifier for License Plate Recognition. Proceedings of 8th International Conference on Computer and Information Technology, 2008, p 372-377
[49] Xiaojun Chi, Junyu Dong,, Aihua Liu, Huiyu Zhou. A Simple Method for Chinese License Plate Recognition Based on Support Vector Machine. 2006 International Conference on Communications, Circuits and Systems, 2006, v 3, p 2141-2145
[50] Santanu Das, Ashok N.Srivastava, Aaditi Chattopadhyay. Classification of Damage Signatures in Composite Plates using One-Class SVMs. IEEE Aerospace Conference Proceedings, 2007
[51]周奇.基于支持向量机的脱机手写字符识别研究:[硕士学位论文].重庆:重庆大学,2007
[52]王润民,钱盛友,邹永星.基于SVM混合网络的车牌字符识别研究.微计算机信息, 2007.23.12-1
[53]张永.基于模糊支持向量机的多类分类算法研究:[博士学位论文].大连:大连理工大学,2008
[54]黄文杰.基于聚类分析的车牌字符识别方法与应用.中国测试技术,2008,Vol.34,No.4
[55]刘泓,方敏,梁朝军.基于Rough集的车牌字符识别方法.合肥工业大学学报, 2004,Vol.27,No.10
[56] Vapnik. Statistical Learning Theory. Springer, N.Y., 1998.
[57] Vapnik. The Nature of Statistical Learning Theory. Springer, N.Y., 1995
[58] J.Smola and B. Scholkopf. On a kernel-based method for pattern recognition regression, approximation and operator inversion. Algrithmica, 1998, 22:211-231
[59] J.C. Platt, N. Cristianini, and J. Shawe-Taylor. Large margin DAGs for multiclass classification. Advances in Neural Information Processing Systems, 2000, vol. 12, p 547-553
[2]莫海宁.自然条件下车牌字符识别方法的研究:[硕士学位论文].哈尔滨:哈尔滨工业大学,2006
[3]刘文峰,吴学毅,刘长富.基于RGB色度空间的车牌定位及矫正算法.武汉大学学报, 2006, Vol.31,No.9
[4]李庆庆,张燕平.基于模糊边缘检测算法的车牌定位.计算机技术与发展, 2006, Vol.16,No.12
[5]张引,潘云鹤.彩色汽车图像牌照定位新方法.中国图像图形学报,2001. Vol.6,No.4
[6]许礼武,许伦辉,黄艳国.基于小波分解的车牌定位算法.计算机工程,2006, Vol.32,No.21
[7]张玲,刘勇,何伟.自适应遗传算法在车牌定位中的应用.计算机应用,2008, Vol.28,No.1
[8]边肇祺,张学工等.模式识别[M].第二版.北京:清华大学出版社, 2006
[9]章毓晋.图像分割.北京:科学出版社,2001,26-30
[10] (美)冈萨雷斯(Gonzalez, R. C. )等著;阮秋琦等译.数字图像处理(第二版).北京:电子工业出版社, 2003.3
[11]王润生.图像理解.长沙:国防科技大学出版,1995
[12] Cheng Zhangfan, Chen Rongbao, License Plate Location Method Based on Modified HIS Model of Color Image. Proceedings of 9th International Conference on Electronic Measurement and Instruments, 2009, p 4197-4201
[13] Sun Guangmin, Li Gang, Xu Lei, Wang Jing. A New Method of Vehicle Lecense Plate Location Based on Mathmatical Morphology and Texture Characteristic. 2008 3rd IEEE Conference on Industrial Electronics and Applications, 2008, p 985-988
[14] Bai Hongliang, Liu Changping. A hybrid License Plate Extraction Method Based on Edge Statistics and Morphology. Proceedings - International Conference on Pattern Recognition, 2004, v 2, p 831-834
[15] Wang Jianxia, Gao Guilong, Yang Huili. Research and Implementation of License Plate Location Based on Histogram Division Method. Proceedings of 9th International Conference on Electronic Measurement and Instruments, 2009, p 1230-1233
[16] Cheng Zhang, Guangmin Sun, Deming Chen, Tianxue Zhao. A Rapid Locating Method ofVehicle License Plate Based on Chraacteristics of Characters’Connerction and Projection. 2007 Second IEEE Conference on Industrial Electronics and Applications, 2007, p 2546-2549
[17] Weijuan Wen, Xianglin Huang, Lifang Yang, Zhao Yang, Pengju Zhang. The Vehicle License Plate Location Method Based-on Wavelet Transform. Proceedings of the 2009 International Joint Conference on Computational Sciences and Optimization, 2009, v 2, p 381-384
[18] Haibin Huang, Guangfu Ma, Yufei Zhuang. Vehicle License Plate Location Based on Harris Corner Detection. Proceedings of the International Joint Conference on Neural Networks, 2008, p 352-355
[19] Zhang Pinzheng, Wang Jianhong. A hybrid vehicle license plate location method based on Gentle AdaBoost and corner validation. Proceedings of SPIE - The International Society for Optical Engineering, 2009, v 7495
[20]中华人民共和国公安部.闯红灯自动记录系统通用技术条件. GA/T 496-2004行业标准
[21]中华人民共和国公安部.公路车辆智能监测记录系统通用技术条件. GA/T 497-2004行业标准
[22]中华人民共和国公安部.中华人民共和国机动车号牌. GA36-2007行业标准
[23]中华人民共和国公安部.中华人民共和国机动车号牌. GA36-2007行业标准
[24] Haijiao Wang, Xinnian Wang, Wenju Li, Xiaodan Jia, Color Prior Knowledge-Based License Plate Location Algorithm. 2nd Workshop on Digital Media and its Application in Museum and Heritage, 2007, p 47-52
[25] Zeng Ruili, Li Gang, Xiao Yunkui, Wang mengjun. Algorithm of car license plates location based on multi-feature fusion. Proceedings of the World Congress on Intelligent Control and Automation (WCICA), 2008, p 8465-8470
[26] Haiqi Huang, Ming Gu, Hongyang Chao. An Efficient Method of License Plate Location in Natural-scence Image. 5th International Conference on Fuzzy Systems and Knowledge Discovery, 2008, v 4, p 15-19
[27]刘兴,蒋天发.车牌字符图像分割技术的研究与应用.武汉大学学报,Dec,2006, Vol.39,No.6
[28]周开军.复杂环境下的车牌识别研究:[硕士学位论文].武汉:武汉理工大学,2006
[29] Varsha Kamat, Subramaniam Ganesan. An Efficient Implementation of the Hough Transform for Detecting Vehicle License Plates Using DSP’S. Real-Time Technology and Applications - Proceedings, 1995, p 58-59
[30]别致,周俊生,陈家俊.基于SVM-Adaboost的中文组块分析.计算机工程与应用,2008, 44(21), 171-173
[31]马腾飞,郑永果,赵卫东.基于边缘检测与Hough变换的车牌字符分割算法.系统仿真学报, 2006, Vol. 18, Suppl.1, 391-392
[32]李鸿林,张忠民,羿宗琪.中值滤波技术在图像处理中的应用.信息技术,2004, Vol.28, NO.7
[33]高浩军,杜宇人.中值滤波在图像处理中的应用.电子工程师,2004, Vol.30 No.8
[34] Pan Xiang, Ye Xiuzi, Zhang Sanyuan. A Hybrid Method for Robust Car Plate Character Recognition. Engineering Applications of Artificial Intelligence, December 2005, v 18, n 8, p 963-972,
[35] K.Crammer and Y. Singer. On the learnability and design of output codes for multiclass problems. Computational Learing Theory, 2000, p 35-46
[36] J. Weston and C. Watkins. Multi-class support vector machines. Proceedings of ESANN99, Brussels, 1999
[37]余华.基于快速最近特征线(NFL)的车牌字符识别方法.语音、通信及信号处理. 2007,Vol.26,No.4
[38] Xuchun Li, Lei Wang, Eric Sung. A Study of AdaBoost with SVM Based Weak Learners. Proceedings of the International Joint Conference on Neural Networks, 2005, v 1, p 196-201
[39]王晓丹,孙东延,郑春颖,张宏达,赵学军.一种基于AdaBoost的SVM分类器.空军工程大学学报,2006, Vol.7, No.6
[40]琚旭,王浩,姚宏亮.基于Boosting的支持向量机组合分类器.合肥工业大学学报,2006, Vol.29, No.10, p 1220-1222
[41]张晓龙,任芳.支持向量机与AdaBoost的结合算法研究.计算机应用与研究,2009, Vol.26, No.1, 77-78/110
[42]李亚军,刘晓霞,陈平.改进的AdaBoost算法与SVM的组合分类器.计算机工程与应用, 2008,44(32), 140-142
[43] Xiaolong Zhang, Fang Ren. Improving Svm Learning Accuracy with Adaboost. 4th International Conference on Natural Computation, 2008, v 3, p 221-225
[44] Freund Y. and Schapre R. E. A Decision-theoretical Generalization of On-line Learning and an Application to Boosting. Jouranl of Computer and System Sciences, August 1997, 55(1):119-139,
[45]蒋焰,丁晓青.基于多步校正的改进AdaBoost算法.清华大学学报(自然科学版), 2008,Vol 48,No.10:1613-1616
[46] Hua-jun SONG, Mei-li SHEN, Wei-feng LIU. Target Track System Design Based on SVM and AdaBoost. 1st International Congress on Image and Signal Processing, 2008, v 4, p 652-656
[47] Qingchuan Tao, Xiaohai He, Daishen Luo, Wei Wu. A New Car Plate Recognition Method Based on Fuzzy Entropy. Proceedings of the World Congress on Intelligent Control and Automation (WCICA), 2004, v 5, p 4054-4056
[48] Lihong Zheng, Xiangjian He, Qiang Wu, Wenjing Jia. A Hierarchically Combined Classifier for License Plate Recognition. Proceedings of 8th International Conference on Computer and Information Technology, 2008, p 372-377
[49] Xiaojun Chi, Junyu Dong,, Aihua Liu, Huiyu Zhou. A Simple Method for Chinese License Plate Recognition Based on Support Vector Machine. 2006 International Conference on Communications, Circuits and Systems, 2006, v 3, p 2141-2145
[50] Santanu Das, Ashok N.Srivastava, Aaditi Chattopadhyay. Classification of Damage Signatures in Composite Plates using One-Class SVMs. IEEE Aerospace Conference Proceedings, 2007
[51]周奇.基于支持向量机的脱机手写字符识别研究:[硕士学位论文].重庆:重庆大学,2007
[52]王润民,钱盛友,邹永星.基于SVM混合网络的车牌字符识别研究.微计算机信息, 2007.23.12-1
[53]张永.基于模糊支持向量机的多类分类算法研究:[博士学位论文].大连:大连理工大学,2008
[54]黄文杰.基于聚类分析的车牌字符识别方法与应用.中国测试技术,2008,Vol.34,No.4
[55]刘泓,方敏,梁朝军.基于Rough集的车牌字符识别方法.合肥工业大学学报, 2004,Vol.27,No.10
[56] Vapnik. Statistical Learning Theory. Springer, N.Y., 1998.
[57] Vapnik. The Nature of Statistical Learning Theory. Springer, N.Y., 1995
[58] J.Smola and B. Scholkopf. On a kernel-based method for pattern recognition regression, approximation and operator inversion. Algrithmica, 1998, 22:211-231
[59] J.C. Platt, N. Cristianini, and J. Shawe-Taylor. Large margin DAGs for multiclass classification. Advances in Neural Information Processing Systems, 2000, vol. 12, p 547-553