摘要
车牌识别是智能交通系统中最关键的研究课题,有着广泛的应用前景,如交通道路监控、高速公路自动收费、停车场管理等。随着经济社会发展,机动车辆日益增加,对车辆进行安全管理、交通流引导和控制的需求越来越明显,因此研究更为稳定、快速、有效的车牌识别系统具有巨大的社会意义和实用价值。
车牌识别关键技术由三部分组成：车牌定位、字符分割和字符识别。本文综合应用图像处理技术、模式识别、人工神经网络等方法,对这三大技术进行深入学习与研究,提出了有效的改进方法,并利用VC++6.0平台,编程实现了车牌识别系统。具体包括以下内容：
在综合分析了各种典型车牌定位算法后,提出一种基于水平垂直投影的车牌定位方法。该方法对预处理后的图像进行一次平滑处理去除噪声,然后阈值化,再对阈值化后的二值图像在水平垂直方向上进行投影运算,求得车牌区域上下左右边缘位置后,进行裁剪。该方法特征提取简单、计算量小、速度快,且易于理解操作,能有效地实现车牌定位。
在综合分析了基于投影、聚类、模板匹配等字符分割算法后,提出一种基于车牌先验知识的行列扫描字符分割方法。该方法结合我国车牌长宽、字符特征,先利用扫描行法获得车牌字符上下边界,再利用扫描列法依次获得各字符左右边界,以此分割各字符。实验证明,该方法执行速度快,能很好地处理由于车牌磨损、污染造成的字符粘连现象。
在综合分析了基于模板匹配、人工神经网络的字符识别方法,以及深入研究了传统BP神经网络缺陷后,提出一种改进了的分组BP神经网络字符识别方法。该方法结合现有车牌字符类型,将BP神经网络分成四个子网络进行学习识别,并在权值修改时加入动量系数,很好地解决了学习速率过大或过小所引起的网络易发散或收敛慢的问题。经大量实验证明,该方法能有效提高BP网络学习速度以及字符识别准确率。
License Plate Recognition is one of the most critical research topics in the Intelligent Transportation System. It has a broad application prospects, such as road traffic monitoring, automated highway toll collection, parking management, and so on. With the development of economic and society, the quantity of vehicles is increasing, and the demand of vehicle safety management, traffic guidance and control is more and more obviously. Therefore, it has great social significance and pratical value to make a research in more stable, fast and effective license plate recognition system.
License plate recognition technology consists of three key components, i.e. license plate location, character segmentation and character recognition. This article used image processing and artificial neural network technologies, proposed effective improvements, and used VC++6.0 platform programming of the license plat recognition system. It included contents as follows:
A new algorithm of license plate location based on horizontal and vertical projection is proposed. Firstly, after pre-processing, the image was smoothed to remove noise. Secondly, the image was projected in the horizontal and vertical direction after thresholding of binary image, when we got the upper and lower edge of the license plate area location, we could intercept the image. This method is simple, fast, and easy to understand, it can effectively locate the license plate.
This article proposed a new method of license plate character segmentation which based on prior knowledge of plate. The method useed the fixed features of our license plate. Firstly, the upper and lower boundary of license characters was obtained by scanning each line of the plate. Secondly, the left and right boundary of license characters was obtained by scanning each column. Experiment results show that this method performs fast, and can effectively deal with the uncleared characters that caused by wear and pollution phenomena.
Based on the analysis of template matching and artificial neural network character recognition methods. The article proposed a method of improved packet BP neural network character recognition. The method divided the BP neural network into four sub-networks, and added the momentum factor when weight changing. In the traditional BP network, when learning rate is too big or small, the network is easy to divergence or slow convergence. The packet BP network can slove this problem. Experiment results demonstrate that the method can effectively improve the speed of BP network training and character recognition accuracy.
引文
[1]C. Ramos, C. Frasson, and S. Ramachandran. Introduction to the Special Issue on Real World Applications of Intelligent Tutoring Systems. Proc IEEE Transactions on Learning Technologies[C].2009, April-June
[2]Tindall D W. Application of Neural Techniques to Automatic License Plate recognition. Proceedings of European Convention on Security and Detection, Brighton,1995:81-85
[3]姚德宏.基于神经网络的汽车牌照提取研究[J].计算机应用,2001,21(6):40-41
[4]赵雪春,戚飞虎.基于彩色分割的车牌自动识别技术[J].上海交通大学学报,1998,32(10):4-9
[5]陈黎,黄心汉,王敏,李炜.基于聚类分析的车牌字符分割方法[J].计算机工程与应用,2002,(6):221-256
[6]陈寅鹏,丁晓清.复杂车辆图像中的车牌定位与字符分割方法[J].红外与激光工程,2004,33(1):29-33
[7]Johnson A S, Bird B M, Number-plate matching for automatic vehicle identification. Proceeding of electronic image and image processing in security and fore science[C].IEE Colloquim,1990(4):1-8
[8]王鉴,黄山,严国莉,凌彤辉.车牌字符识别技术[J].中国测试技术,2005,31(2):45-46,84
[9]董镭.基于车牌识别技术的车辆管理系统的研发[D].广西:广西大学,2008:3-5
[10]R PARISI, et al. CarPlate Recognition by Neural Networks and Image Processing[A]. Proc IEEE International Symposium on Circuits and Systems[C], USA,1998, May31-June 3
[11]J BARROSO, A RAFAEL, et al. Number plate reading using computer vision[A]. Proc IEEE International Symposium on Industrial Electronics(ISIP)[C]. Portual, http://www.utad.pt/,1997
[12]Barroso J, Bulas-Cruz J&Dagless EL, Real-Time Number Plate Reading,4th IFAC Work shop on Algorithmsf or Real-Time Control
[13]容观澳.计算机图像处理[M].北京：清华大学出版社,2000
[14]Ostu N.A Threshold Selection Method from Gray-Level Histograms[J]. IEEE Transactions on Systems, Man and Cybernetics.1979,9(l):62-66
[15]罗希平,田捷,诸葛婴等.图像分割方法综述[J].模式识别与人工智能,1999,12(3):300-312
[16]陈丹,张峰,贺贵明.一种改进的文本图像二值化算法[J].计算机工程,2003,29(13):85-86
[17]阮秋琦.数字图像处理学[M].北京：电子工业出版社,2008
[18]胡旺,李志蜀,黄奇.基于双窗口和极值压缩的自适应中值滤波[J].中国图像图形学报,2007,1:43-50
[19]刘先莹,候德文.车牌定位常见方法介绍与分析[J].多媒体技术及其应用,2007:748-750
[20]冈萨雷斯.数字图像处理[M].北京：电子工业出版社,2004
[21]张引,潘云鹤.彩色汽车图像牌照定位新方法[J].中国图形图像学报,2001,6(4)
[22]郭大波,陈礼民,卢朝阳,韩丽萍.基于车牌底色识别的车牌定位方法[J].计算机工程与设计,2003,24(5)：81-87
[23]王晓华,赵为平,高庆吉等.采用基于结构性的统计法识别火车车号[J].东北电力学院学报,1998,8(3):79-83
[24]陈利.车牌识别系统中的字符分割技术研究[J].电脑知识与技术,2008:1693-1694,1699
[25]黄山,车牌识别技术的研究和实现[D].四川：四川大学,2005
[26]冼允廷,路小波,施毅等.基于投影二分法的车牌字符分割方法[J].交通与计算机,2007,25(5)：69-72
[27]王冠,敖志刚等.基于快速连通域标记的车牌字符分割[J].计算机与现代化,2007,6:55-57
[28]范玮琦,穆长江.一种基于汉字结构特征的车牌照字符分割方法[J].仪器仪表学报,2003,24(4):472-474
[29]Abhijit S.Pandya Robert B.Macy, Pattern Recognition with Neural Network sin C++, IEEE PRESS(神经网络模式识别及其实现,徐勇荆涛等译.电子工业出版社)：192-20
[30]黄德双.神经网络模式识别系统理论[M].北京：电子工业出版社,1996
[31]D. Rumelhart, G. Hinton, R. Willians, "Learning Internal Representations by Error Propagation", Parallel Distributed Processing: Foundations, Rumelhart, McClelland, eds, Vol.1, pp.318-362, MIT Press,1986
[32]虞和济,陈长征,张省,周建男.基于神经网络的智能诊断[M].北京：冶金工业出版社,2000
[33]陈杨,王茹,林辉Matlab6.0版本中神经网络工具箱学习算法的使用与比较[J].电脑与信息技术科技,2002(3)：1-6
[34]苏高利,邓芳萍.论基于贴TLAB语言的BP神经网络的改进算法[J].科技通报,2003(2)：130-136