基于神经网络的车牌识别系统的研究与设计
|
摘要
随着我国经济的发展、汽车拥有量的急剧增加，公路交通成为我国重要的交通运输途径，是国家大力发展的基础设施。日益拥堵的城市交通需要用更先进、更有效的交通管理、控制。利用电子信息技术来提高管理效率、交通效率和安全的智能交通系统ITS已成为当前交通管理发展的主要方向。
车牌识别LPR是智能交通中关键技术之一。以自动的车牌号码识别为基础，可以对车辆进行自动登记、验证、监视、报警，进而可以应用在多种场合，如高速公路收费系统：道路、卡口监控系统；小区、停车场收费、监控系统；车流统计、引导系统等。
本论文是基于图像处理的相关理论，将计算机视觉与模式识别技术相结合，对车辆牌照识别系统进行了较深入的研究和分析。第一章论述了汽车牌照识别的主要几种应用技术和现阶段的发展动向。在第二章中，分别对车牌识别系统的硬件设计和软件设计进行了简要的介绍。第三章对图像分割的各种方法及特点进行了讨论。第四章分析了字符识别中特征量的提取方法，并对神经网络的构成以及相关的理论进行了讨论，着重分析了神经网络的理论原理和在字符识别中的应用方法。第五章是在前两章的理论基础上，详细介绍了车牌识别系统软件设计的实现方法和实验结果，应用图像分割的理论对车牌进行边缘检测和提取，利用轮廓和投影的方法提取字符的特征，最后用神经网络的方法对所得字符进行识别。
由试验所得的结果，本系统能较准确定位、分割车牌并进行识别，系统的性能良好。从中可看出：多种预处理与识别技术有机结合能提高系统识别能力，在有效、实用的原则下将神经网络与人工智能技术相结合将成为模式识别研究的两个重要发展趋势。
With the fantastic spur in economy and rapid development of the owning amount of automobile, the highway communication becomes one of the most important communications and transportation ways in our country. And now it is infrastructures that the country developed energetically. Also crowded urban traffic needs more advanced and more effective traffic administration and control system. So Intelligent Transportation Systems (ITS) which makes use of electronic information technology to raise management efficiency, traffic efficiency and traffic security becomes main direction of traffic administration.
License Plate Recognition (LPS) is one of the critical techniques for the intelligent transportation system. The system can automatically register, verily. monitor vehicle or report to the police with automatic recognition for vehicle license plates. So it can be used in many kinds of occasions ,such as the charges system of expressway, monitoring system at road and roll-gate, charge and monitoring system at the district, parking area, guide system, the system counting the quantity of vehicle passing in a certain period time, etc..
Based on image procession technology, computer vision technology and artificial neural network technology, the paper deeply researches and analyses an automobile license plate identification system. Chapter 1 gives a full introduction of the present situation of technologies in automatic number-plate recognition all around the world. It analyzes that the development tendency of technologies of automatic number-plate recognition on the basis of discussing the specialization of automatic number-plate recognition in our country. In chapter 2, there are some brief introduces of software design and hardware design of an automobile license plate identification system. Chapter 3 discusses some basic principles of image segmentation. Chapter 4 introduces some characteristic extracting methods of character recognition, analyzes the structure of the neural network with relevant theories and emphatically discusses the theory principle of the neural
network and the application method in character recognition with it. Based on the theories of the first two chapters, chapter 5 introduces the theoretical foundation and method of the software design of the license plate recognition system in detail. In this system, a license plate is fixed in a position and cut apart by verge examination based on the differential operator and threshold algorithm. Then outline method and projection method are used as methods of characteristic extracting, lastly neural network is used as a method to recognition the single character.
As the test result, it proves that this recognition system can relatively accurate to locate license plate and recognize characters and system's performance is good. It shows that combined pretreatments and recognition techniques can improve the ability of recognition, and the combination of neural network and artificial intelligence under the principle of efficiency and practicality will be two major development tendencies of pattern recognition.
车牌识别LPR是智能交通中关键技术之一。以自动的车牌号码识别为基础，可以对车辆进行自动登记、验证、监视、报警，进而可以应用在多种场合，如高速公路收费系统：道路、卡口监控系统；小区、停车场收费、监控系统；车流统计、引导系统等。
本论文是基于图像处理的相关理论，将计算机视觉与模式识别技术相结合，对车辆牌照识别系统进行了较深入的研究和分析。第一章论述了汽车牌照识别的主要几种应用技术和现阶段的发展动向。在第二章中，分别对车牌识别系统的硬件设计和软件设计进行了简要的介绍。第三章对图像分割的各种方法及特点进行了讨论。第四章分析了字符识别中特征量的提取方法，并对神经网络的构成以及相关的理论进行了讨论，着重分析了神经网络的理论原理和在字符识别中的应用方法。第五章是在前两章的理论基础上，详细介绍了车牌识别系统软件设计的实现方法和实验结果，应用图像分割的理论对车牌进行边缘检测和提取，利用轮廓和投影的方法提取字符的特征，最后用神经网络的方法对所得字符进行识别。
由试验所得的结果，本系统能较准确定位、分割车牌并进行识别，系统的性能良好。从中可看出：多种预处理与识别技术有机结合能提高系统识别能力，在有效、实用的原则下将神经网络与人工智能技术相结合将成为模式识别研究的两个重要发展趋势。
With the fantastic spur in economy and rapid development of the owning amount of automobile, the highway communication becomes one of the most important communications and transportation ways in our country. And now it is infrastructures that the country developed energetically. Also crowded urban traffic needs more advanced and more effective traffic administration and control system. So Intelligent Transportation Systems (ITS) which makes use of electronic information technology to raise management efficiency, traffic efficiency and traffic security becomes main direction of traffic administration.
License Plate Recognition (LPS) is one of the critical techniques for the intelligent transportation system. The system can automatically register, verily. monitor vehicle or report to the police with automatic recognition for vehicle license plates. So it can be used in many kinds of occasions ,such as the charges system of expressway, monitoring system at road and roll-gate, charge and monitoring system at the district, parking area, guide system, the system counting the quantity of vehicle passing in a certain period time, etc..
Based on image procession technology, computer vision technology and artificial neural network technology, the paper deeply researches and analyses an automobile license plate identification system. Chapter 1 gives a full introduction of the present situation of technologies in automatic number-plate recognition all around the world. It analyzes that the development tendency of technologies of automatic number-plate recognition on the basis of discussing the specialization of automatic number-plate recognition in our country. In chapter 2, there are some brief introduces of software design and hardware design of an automobile license plate identification system. Chapter 3 discusses some basic principles of image segmentation. Chapter 4 introduces some characteristic extracting methods of character recognition, analyzes the structure of the neural network with relevant theories and emphatically discusses the theory principle of the neural
network and the application method in character recognition with it. Based on the theories of the first two chapters, chapter 5 introduces the theoretical foundation and method of the software design of the license plate recognition system in detail. In this system, a license plate is fixed in a position and cut apart by verge examination based on the differential operator and threshold algorithm. Then outline method and projection method are used as methods of characteristic extracting, lastly neural network is used as a method to recognition the single character.
As the test result, it proves that this recognition system can relatively accurate to locate license plate and recognize characters and system's performance is good. It shows that combined pretreatments and recognition techniques can improve the ability of recognition, and the combination of neural network and artificial intelligence under the principle of efficiency and practicality will be two major development tendencies of pattern recognition.
引文
[1] 黄志建，古向阳，戴均陶．条形码技术及应用[M]．北京：机械工业出版社，1992．
[2] 高一凡，王选仓．条形码在交通管理中的应用[J]．交通与计算机，1996，14(2)：53～58
[3] 边肇祺等．模式识别[M]．北京：清华大学出版社，1988：250～257
[4] Johnson A S, Bird B M, Number-plate matching for automatic vehicle identification. Electronic Image and Image Processing in Security and Forensic Science [C]. IEE Colloquium, 1990(4): 1～8.
[5] Lotufo R A,Morgan A D, Johnson A S. Automatic number-plate recognition. Image Analysis for Transport Application [C]. IEE Colloquium, 1990 (6):1～6.
[6] 胡守仁．神经网络应用技术[M]．北京：国防科技大学出版社，1993．
[7] 章毓晋．图像处理和分析(图像工程 上册)．北京：清华大学出版社，1999：1～217
[8] 章毓晋．图像分割．北京：科学出版社，2001．
[9] K.R.Castleman 著，朱志刚等译，数字图像处理．北京：电子工业出版社，1998：378～422
[10] 邓炜，王军安，杨永生．计算机图像识别系统的设计与实现．计算机应用研究．2000，6：79～80
[11] 李小平，林学言，曲大成等．车辆牌照识别系统可靠性问题的研究．北京理工大学学报．2001，21(1)：11～14
[12] 王广宇．车辆牌照识别系统综述．郑州轻工业学院学报(自然科学报)．2001，16(2)：47～50
[13] 赵荣春等．数字图像处理导论．西安：西北工业大学出版社，1996：192～227
[14] Lam L, Lee S W, Suen C Y. Thinning Methodologies-a Comprehensive Survey. IEEE Trans Patt Anal Math Intell, 1992,14:869-885
[15] Kai Huang,Hong Yah. Off-Line Signature Verification Based on Geometric Feature Extraction and Neural Network Classification. Pattern Recognition, 1997,30(1):9-17
[16] Brows R M, Foy T H, Handprinted Symbol Recognition System. Pattern Recognition, 1988,21(2): 98-118
[17] Smith R W. Computer Processing of Line Images: A Survey Pattern Recognition. 1987 20:7-15
[18] Hu M K,Visual Pattern Recognition by Moment Invariant. IRE Tran Inf Theory. 1992, 8: 179-187
[19] Garris M D, Wilson C L. Neural Network-Based Systems for Handprinted OCR Applications. IEEE Tran Image Processing, 1998,7(8): 1097-1112
[20] 焦李成 著．神经网络系统理论．西安：西安电子科技大学出版社，1996：1～50
[21] 王永骥，涂健．神经元网络控制．北京：机械工业出版社，1998
[22] 张乃尧，阎平凡．神经网络与模糊控制．北京：清华大学出版社，1998
[23] 郑南宁，张西宁，戴莹等．行驶车辆牌照自动识别系统．西安交通大学学报，1991，25(1)：43～54
[24] 郁梅，郁伯康．基于视觉的车辆牌照检测．计算机应用研究，1999，5：65～67
[25] 袁志伟，潘晓露，陈艾等．车辆牌照定位的算法研究．昆明理工大学学报，2001，26(2)：56～60
[26] 富煜清，沈魏，黄心华．汽车牌照的提取方法研究．模式识别与人工智能，2000，13(3)：345～348
[27] 吕凤军著．数字图像处理编程入门—做一个自己的Photoshop北京，清华大学出版社，1999
[28] 杨杰，厉旭，郭伟．基于数学形态学和神经网络的车牌识别．武汉理工大学学报(交通科学与工程版)2001，25：371～374
[29] 叶晨洲，杨杰，宣国荣．车辆牌照字符识别．上海交通大学学报．2000，34(5)：672～675
[30] 张引，潘云鹤．面向车辆牌照字符识别的预处理算法．计算机应用研究．1999，7：85～87
[31] 曹迪铭，宣国荣．牌照字符分割中的区域分裂与合并．计算机工程．2000，26(10)：18～20
[32] 曹迪铭．神经网络在车辆牌照字符识别中的应用．微型电脑应用．2000，16(6)：5～9
[33] 厉旭，杨杰．基于神经网络的多识别器在字符识别中的应用．交通与计算机．2001，增刊，19：89～91
[34] 施阳等著．MATLAB语言工具箱—TOOLBOX实用指南．西安，西北工业大学出版社．1999：124～257
[35] 楼顺天等著．基于MATLAB的系统分析与设计—神经网络．西安，西安电子科技大学出版社，1998
[36] 楼顺天等著．基于MATLAB的系统分析与设计—信号处理．西安，西安电子科技大学出版社，1998
[37] 陈桂明等著．应用MATLAB语言处理数字信号与数字图像．北京，科学出版社，2000．
[38] 张宜华著．精通MATLAB 5．北京，清华大学出版社，1999
[39] 高俊斌著．MATLAB 5.0 语言与程序设计．武汉，华中理工大学出版社，1998
[40] Battiti R, Colla A. Democracy in Neural Nets Voting Schemes for Classification. Neural NetWorks, 1994,7(4): 691～707
[41] 郝红卫，戴汝为．人机结合的集成方法及其在字符识别中的应用．模式识别与人工智能，1996，11(3)：311～317
[42] Song Wang, Xiaoyan Zhu. Multiple Experts Recognition System Based on Neural Network. In Proc Conf on Pattern Recognition's 96, Vienna, Austria, 545～548
[43] Elliman D G, Lancaster I T. Review of Segmentation Contextual Analysis Techniques for Text Recognition. Pattern Recognition Society, 19990,23(3-4): 337～346
[44] Yuntao Cui, Qian Huang, Character Extraction of License Plates from Video. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997:502～507
[45] Luis Salgado, Jose M. Memendez, Enrique Rendon, Narciso Garcia. Automatic Car Plate Detection and Recognition through Intelligent Vision Engineering. IEEE Annual International Carnahan Conference on Security Technology, Proceedings, 1999: 71～76
[46] Mantas J. An overview of character recognition methodologies. Pattern Recognition, 1986(19): 425～430
[47] 王年，熊原，赵海峰等．基于神经网络的汽车牌照自动识别．安徽大学学报(自然科学版)，2000，24(1)：45～50
[48] Darw iche E, Pandya A S, Mandalia A D. Automated optical recognition of degraded characters [J]. SPIE, 1992, 1661:27～32
[49] M.Shridhar, J.W.V. Miller, G.Houle, L.Bijnag te. Recognition of License Plate Images: Issues and Perspectives. Proceedings of Fifth International Conference on Document Analysis and Recognition, 1997:17～20
[50] Paolo Ferragina, Mario Notturno Graieri, Flavio Stabile. Optical Recognition of Motor Vehicle License Plate. Paolo Comelli. IEEE Transactions On Vehicle Technology, 1995,44(4): 790～799
[51] J.Bernsen: Dynamic thresholding of grey-level images. Pro: 8th Int. Conf. On Pattern Recognition, Paris, 1986: 1251～1255
[2] 高一凡，王选仓．条形码在交通管理中的应用[J]．交通与计算机，1996，14(2)：53～58
[3] 边肇祺等．模式识别[M]．北京：清华大学出版社，1988：250～257
[4] Johnson A S, Bird B M, Number-plate matching for automatic vehicle identification. Electronic Image and Image Processing in Security and Forensic Science [C]. IEE Colloquium, 1990(4): 1～8.
[5] Lotufo R A,Morgan A D, Johnson A S. Automatic number-plate recognition. Image Analysis for Transport Application [C]. IEE Colloquium, 1990 (6):1～6.
[6] 胡守仁．神经网络应用技术[M]．北京：国防科技大学出版社，1993．
[7] 章毓晋．图像处理和分析(图像工程 上册)．北京：清华大学出版社，1999：1～217
[8] 章毓晋．图像分割．北京：科学出版社，2001．
[9] K.R.Castleman 著，朱志刚等译，数字图像处理．北京：电子工业出版社，1998：378～422
[10] 邓炜，王军安，杨永生．计算机图像识别系统的设计与实现．计算机应用研究．2000，6：79～80
[11] 李小平，林学言，曲大成等．车辆牌照识别系统可靠性问题的研究．北京理工大学学报．2001，21(1)：11～14
[12] 王广宇．车辆牌照识别系统综述．郑州轻工业学院学报(自然科学报)．2001，16(2)：47～50
[13] 赵荣春等．数字图像处理导论．西安：西北工业大学出版社，1996：192～227
[14] Lam L, Lee S W, Suen C Y. Thinning Methodologies-a Comprehensive Survey. IEEE Trans Patt Anal Math Intell, 1992,14:869-885
[15] Kai Huang,Hong Yah. Off-Line Signature Verification Based on Geometric Feature Extraction and Neural Network Classification. Pattern Recognition, 1997,30(1):9-17
[16] Brows R M, Foy T H, Handprinted Symbol Recognition System. Pattern Recognition, 1988,21(2): 98-118
[17] Smith R W. Computer Processing of Line Images: A Survey Pattern Recognition. 1987 20:7-15
[18] Hu M K,Visual Pattern Recognition by Moment Invariant. IRE Tran Inf Theory. 1992, 8: 179-187
[19] Garris M D, Wilson C L. Neural Network-Based Systems for Handprinted OCR Applications. IEEE Tran Image Processing, 1998,7(8): 1097-1112
[20] 焦李成 著．神经网络系统理论．西安：西安电子科技大学出版社，1996：1～50
[21] 王永骥，涂健．神经元网络控制．北京：机械工业出版社，1998
[22] 张乃尧，阎平凡．神经网络与模糊控制．北京：清华大学出版社，1998
[23] 郑南宁，张西宁，戴莹等．行驶车辆牌照自动识别系统．西安交通大学学报，1991，25(1)：43～54
[24] 郁梅，郁伯康．基于视觉的车辆牌照检测．计算机应用研究，1999，5：65～67
[25] 袁志伟，潘晓露，陈艾等．车辆牌照定位的算法研究．昆明理工大学学报，2001，26(2)：56～60
[26] 富煜清，沈魏，黄心华．汽车牌照的提取方法研究．模式识别与人工智能，2000，13(3)：345～348
[27] 吕凤军著．数字图像处理编程入门—做一个自己的Photoshop北京，清华大学出版社，1999
[28] 杨杰，厉旭，郭伟．基于数学形态学和神经网络的车牌识别．武汉理工大学学报(交通科学与工程版)2001，25：371～374
[29] 叶晨洲，杨杰，宣国荣．车辆牌照字符识别．上海交通大学学报．2000，34(5)：672～675
[30] 张引，潘云鹤．面向车辆牌照字符识别的预处理算法．计算机应用研究．1999，7：85～87
[31] 曹迪铭，宣国荣．牌照字符分割中的区域分裂与合并．计算机工程．2000，26(10)：18～20
[32] 曹迪铭．神经网络在车辆牌照字符识别中的应用．微型电脑应用．2000，16(6)：5～9
[33] 厉旭，杨杰．基于神经网络的多识别器在字符识别中的应用．交通与计算机．2001，增刊，19：89～91
[34] 施阳等著．MATLAB语言工具箱—TOOLBOX实用指南．西安，西北工业大学出版社．1999：124～257
[35] 楼顺天等著．基于MATLAB的系统分析与设计—神经网络．西安，西安电子科技大学出版社，1998
[36] 楼顺天等著．基于MATLAB的系统分析与设计—信号处理．西安，西安电子科技大学出版社，1998
[37] 陈桂明等著．应用MATLAB语言处理数字信号与数字图像．北京，科学出版社，2000．
[38] 张宜华著．精通MATLAB 5．北京，清华大学出版社，1999
[39] 高俊斌著．MATLAB 5.0 语言与程序设计．武汉，华中理工大学出版社，1998
[40] Battiti R, Colla A. Democracy in Neural Nets Voting Schemes for Classification. Neural NetWorks, 1994,7(4): 691～707
[41] 郝红卫，戴汝为．人机结合的集成方法及其在字符识别中的应用．模式识别与人工智能，1996，11(3)：311～317
[42] Song Wang, Xiaoyan Zhu. Multiple Experts Recognition System Based on Neural Network. In Proc Conf on Pattern Recognition's 96, Vienna, Austria, 545～548
[43] Elliman D G, Lancaster I T. Review of Segmentation Contextual Analysis Techniques for Text Recognition. Pattern Recognition Society, 19990,23(3-4): 337～346
[44] Yuntao Cui, Qian Huang, Character Extraction of License Plates from Video. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997:502～507
[45] Luis Salgado, Jose M. Memendez, Enrique Rendon, Narciso Garcia. Automatic Car Plate Detection and Recognition through Intelligent Vision Engineering. IEEE Annual International Carnahan Conference on Security Technology, Proceedings, 1999: 71～76
[46] Mantas J. An overview of character recognition methodologies. Pattern Recognition, 1986(19): 425～430
[47] 王年，熊原，赵海峰等．基于神经网络的汽车牌照自动识别．安徽大学学报(自然科学版)，2000，24(1)：45～50
[48] Darw iche E, Pandya A S, Mandalia A D. Automated optical recognition of degraded characters [J]. SPIE, 1992, 1661:27～32
[49] M.Shridhar, J.W.V. Miller, G.Houle, L.Bijnag te. Recognition of License Plate Images: Issues and Perspectives. Proceedings of Fifth International Conference on Document Analysis and Recognition, 1997:17～20
[50] Paolo Ferragina, Mario Notturno Graieri, Flavio Stabile. Optical Recognition of Motor Vehicle License Plate. Paolo Comelli. IEEE Transactions On Vehicle Technology, 1995,44(4): 790～799
[51] J.Bernsen: Dynamic thresholding of grey-level images. Pro: 8th Int. Conf. On Pattern Recognition, Paris, 1986: 1251～1255
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |