汽车牌照自动识别技术的研究
|
摘要
在基于电子信息技术的智能交通系统(ITS)中，车牌识别(LPR)是最为关键的技术之一，它以车牌号码自动识别为基础，可以对车辆进行自动验证、监视和报警。然而，由于车牌识别系统通常工作在自然环境中，受外界因素影响较大，而且我国车牌中通常包含一些结构复杂的汉字，使得很多情况下系统的识别率很难令人满意，大大影响了智能交通系统的工作效率。
本文基于数字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为深入地分析和研究。重点对车牌区域定位算法和车牌字符识别算法进行了改进和创新。
首先，在车牌区域的定位和提取中，采用了对车牌区域进行粗、细两级定位的方法。在粗定位时采用一种改进的模糊匹配算法，克服了传统模板匹配算法计算量大、对背景复杂的图像难以准确分割的缺点；在精确定位时根据车牌区域行相邻像素之间变化频繁的特点，对车牌区域精细定位。
然后，在车牌字符的分割中，根据车牌本身提供的先验知识，采用了连通域分析法和灰度投影法相结合的算法，克服了目前常用算法中对部分汉字和数字字符不易准确分割的难点，使得字符分割更加精确。
最后，在车牌字符的识别中，讨论了人工神经网络的理论原理和在字符识别中的应用方法，着重分析了应用传统的神经网络算法进行字符识别时存在的不足，并提出了一些改进措施，针对由于光线不足或牌照污损所引起的字符模糊现象，利用字符外围轮廓和投影特征相结合的方法提取字符特征，并采用改进的BP神经网络算法对所得字符进行了识别。
通过仿真试验可以证明，本文提出的算法能比较准确地定位、分割车牌区域并进行字符识别，且系统的性能良好。从中可以看出多种图像预处理与模式识别技术的有机结合能有效地提高系统的识别能力。
In the Intelligent Transportation Systems (ITS) which bases on electronic information technology, License Plate Recognition (LPR) is one of the most critical technologies. The system can automatically verify, monitor vehicle or report to the police with automatic recognition for vehicle license plate. However, because License Plate Recognition system usually works in natural environment and our country's vehicle license plates include some complex Chinese characters, the recognition rate can't achieve satisfying effect in many conditions and work efficiency of the Intelligent Transportation Systems is influenced obviously.
Based on digital image processing technology, computer vision technology and pattern recognition technology, license plate identification system is deeply researches and analyses. Some improvements and innovation on license plate location and characters recognition can be made in this paper.
First, in the license plate location system, this paper proposes a method which makes two-level location. In primary location, using a improved blurry matching arithmetic, the defect of plentiful account in the traditional template matching arithmetic can be conquered. In precision location, based on high change frequency about 0 and 1 of license plate horizontal orientation, the accurate license plate district can be got.
Second, in the characters segmentation system, based on the transcendental knowledge which comes from license plate, this paper uses a method that combines district connectivity and gray projection to conquer some difficulties which come from come unreadable characters in the traditional arithmetic. The result displays that the characters can be more exactly segmented.
Finally, in the characters recognition system, this paper discusses the theory principle of the neural network and the application method in character recognition, emphatically analyses traditional Artificial Neural Network's defects and improvements measures. Aiming at character unclear phenomena, character figure means and projection method are used to extract character characteristic. Lastly improved BP neural network is used as a method to recognition the single character.
As the test result, this arithmetic can accurately locate to license plate and recognize characters. And the system's performance is good. It shows that combined pretreatments and pattern recognition techniques can improve the ability of recognition.
本文基于数字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为深入地分析和研究。重点对车牌区域定位算法和车牌字符识别算法进行了改进和创新。
首先，在车牌区域的定位和提取中，采用了对车牌区域进行粗、细两级定位的方法。在粗定位时采用一种改进的模糊匹配算法，克服了传统模板匹配算法计算量大、对背景复杂的图像难以准确分割的缺点；在精确定位时根据车牌区域行相邻像素之间变化频繁的特点，对车牌区域精细定位。
然后，在车牌字符的分割中，根据车牌本身提供的先验知识，采用了连通域分析法和灰度投影法相结合的算法，克服了目前常用算法中对部分汉字和数字字符不易准确分割的难点，使得字符分割更加精确。
最后，在车牌字符的识别中，讨论了人工神经网络的理论原理和在字符识别中的应用方法，着重分析了应用传统的神经网络算法进行字符识别时存在的不足，并提出了一些改进措施，针对由于光线不足或牌照污损所引起的字符模糊现象，利用字符外围轮廓和投影特征相结合的方法提取字符特征，并采用改进的BP神经网络算法对所得字符进行了识别。
通过仿真试验可以证明，本文提出的算法能比较准确地定位、分割车牌区域并进行字符识别，且系统的性能良好。从中可以看出多种图像预处理与模式识别技术的有机结合能有效地提高系统的识别能力。
In the Intelligent Transportation Systems (ITS) which bases on electronic information technology, License Plate Recognition (LPR) is one of the most critical technologies. The system can automatically verify, monitor vehicle or report to the police with automatic recognition for vehicle license plate. However, because License Plate Recognition system usually works in natural environment and our country's vehicle license plates include some complex Chinese characters, the recognition rate can't achieve satisfying effect in many conditions and work efficiency of the Intelligent Transportation Systems is influenced obviously.
Based on digital image processing technology, computer vision technology and pattern recognition technology, license plate identification system is deeply researches and analyses. Some improvements and innovation on license plate location and characters recognition can be made in this paper.
First, in the license plate location system, this paper proposes a method which makes two-level location. In primary location, using a improved blurry matching arithmetic, the defect of plentiful account in the traditional template matching arithmetic can be conquered. In precision location, based on high change frequency about 0 and 1 of license plate horizontal orientation, the accurate license plate district can be got.
Second, in the characters segmentation system, based on the transcendental knowledge which comes from license plate, this paper uses a method that combines district connectivity and gray projection to conquer some difficulties which come from come unreadable characters in the traditional arithmetic. The result displays that the characters can be more exactly segmented.
Finally, in the characters recognition system, this paper discusses the theory principle of the neural network and the application method in character recognition, emphatically analyses traditional Artificial Neural Network's defects and improvements measures. Aiming at character unclear phenomena, character figure means and projection method are used to extract character characteristic. Lastly improved BP neural network is used as a method to recognition the single character.
As the test result, this arithmetic can accurately locate to license plate and recognize characters. And the system's performance is good. It shows that combined pretreatments and pattern recognition techniques can improve the ability of recognition.
引文
1 Ichiro Masaki. A Brief History of ITS. USA: Massachusetts Institute of Technology, 1999:25-30
2 Kerry L.Clines. Intelligent Transportation Systems. Better Roads,2005,75(7):75-76
3 Brian L.Smith, William T.Scherer. Development of Integrated Intelligent Transportation Systems. Transportation Research Record, 1999,(1675):84-90
4 宋维明．国外智能交通系统建设模式综述及其启示．电子技术(上海)，2006，33(12)：19-22
5 廖翔云，许锦标，龚仕伟．车牌识别技术研究．微机发展，2003，13(a02)：31-32 35
6 唐汉征．车牌识别系统的工作原理及其应用．现代电子工程，2004，(2)：66-69
7 章毓晋．图象工程—图象处理和分析．北京：清华大学出版社，1999：100-106
8 Haiyuan Wu, Qian Chen, Masahiko Yachida. Face Detection from Color Images Using a Fuzzy Pattern Matching Method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999,21 (6):557-563
9 Yihong Xu,George Nagy. Prototype Extraction and Adaptive OCR. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999,21 (12): 1280-1296
10 Jonathan J.Hull, Sargur N.Srihari, Tin K.Ho. Regression Approach to Combination of Decisions by Multiple Character Recognition Algorithms. Proceedings of SPIE-The International Society for Optical Engineering, 1992,1661:137-145
11 C.Nadal, R.Legault, C.Y.Suen. Building A New Generation of Handwriting Recognition Systems. Pattern Recognition Letters, 1993,14(4):303
12 Masato Suzuki, Nei Kato. Handprinted Character Recognition System Using Image Transformation Based on Partial Inclination Detection. IEICE Transactions on Information and Systems, 1996,E79-D(5):504-509
13 崔屹．数字图像处理技术与应用．北京：电子工业出版社，1997：100-104
14 王泽华．车牌识别系统中倾斜车牌的一种定位方法．仪器仪表用户，2005，12(4)：86-88
15 Jun Cao, M.Ahmadi, M.Shridhar. Recognition of Handwritten Numerals with Multiple Feature and Multistage Classifier. Pattern Recognition, 1995,28(2): 153-160
16 Xu Lei. Methods of Combing Multiple Classifiers and Their Application to Handwriting Recognition. IEEE Transactions on System, Man And Cybernetics, 1992,2(22):418-435
17 杨卫平，李吉成．车牌目标的自动定位技术．中国图象图形学报，2002，7(8)：835-839
18 袁晓辉，李久贤，夏良正．一种新的车牌快速定位方法．东南大学学报：自然科学版，2003，33(1)：82-85
19 张宏林．Visual C++数字图像模式识别技术及工程实践．北京：人民邮电出版社，2003：2-5 300-310 422-423
20 肖志涛，孟翔宇．基于Hough变换的倾斜文本图像的检测．红外与激光工程，2002，31(4)：315-317 350
21 刘效静，成瑜．汽车牌照自动识别技术研究．南京航空航天大学学报，1998，30(5)：573-577
22 王少杰，朱志刚．货运列车车型车号自动分割和识别算法．模式识别与人工智能，1998，11(3)：328-334
23 飞思科技产品研发中心．MATLAB6.5辅助图像处理．北京：电子工业出版社，2003：173-176
24 鹿晓亮，陈继荣．复杂背景下快速车牌定位方法研究．计算机仿真，2006，23(7)：256-259
25 Richard G.Casey, Eric Lecolinet. Survey of Methods and Strategies in Character Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence,1996, 18(7):690-706
26 Charl Coetzee, Charl Botha, David Weber. PC Based Number Plate Recognition System. IEEE International Symposium on Industrial Electronics,1998,2:605-610
27 许健，段小梅．车牌定位技术在“电子警察”系统中的应用研究．自动化与信息工程，2006，27(3)：18-20
28 王润生．图像理解．北京：国防科技大学出版社，1995：156-159
29 牛欣，沈兰荪．汽车牌照识别技术的研究．测控技术，1999，18(12)：14-17
30 D.S.Kim, S.I.Chien. Automatic Car License Plate Extraction Using Modified Generalized Symmetry Transform and Image Warping. IEEE International Symposium on Industrial Electronics,2001,3:2022-2027
31 Christos Nikolaos E.Anagnostopoulos, Vassili Loumos. A License Plate-Recognition Algorithm for Intelligent Transportation System Applications. IEEE Transactions on Intelligent Transportation Systems,2006,7(3):377-391
32 S.H.Park, K.I.Kim. Locating Car License Plates Using Neural Networks. Electronics Letters, 1999,35(17): 1475-1477
33 郝永杰，刘文耀，路烁．畸变汽车牌照图像的空间校正．西南交通大学学报，2002，37(4)：417-420
34 叶晨洲，廖金周．车辆牌照字符识别系统．计算机系统应用，1999，(5)：10-13
35 胡强．基于特征信息的车牌识别系统的研究．[西南交通大学硕士学位论文]．2004：35-38
36 Chun-Ming Tsai, His-Jian Lee. Binarization of Color Document Images via Luminance and Saturation Color Features. IEEE Transaction on Image Processing,2002,11(4): 434-451
37 Cheng Shyi-Chyi, Kuo Chen-Tsung, Chen Hong-Jay. Visual Object Retrieval via Block-based Visual-pattern Matching. Pattern Recognition,2007,40(6):1695-1710
38 R.M.Brows, T.H.Fay. Handprinted Symbol Recognition System. Pattern Recognition, 1988,21(2):91-118
39 林纯青，徐立亚．汽车图像中字符目标的提取算法．上海交通大学学报，1998，32(10)：1-39
40 沈定刚，李艳斌．汽车牌照自动定位算法．无线电通信技术，1995，21(5)：35-38
41 杨枝灵，王开．数字图像获取处理及实践应用．北京：人民邮电出版社，2003：50-53
42 边肇棋，张学．模式识别．北京：清华大学出版社，2000：104-108
43 R.Parisi, G.Lucarelli. Car Plate Recognition by Neural Networks and Image Processing. IEEE International Symposium on Circuits and Systems, 1998,3:195-198
44 陶军．车牌识别技术研究与实现．[南京理工大学硕士学位论文]．2004：3-10
45 Y.T.Ching.Detecting Line Segments in An Image-A New Implementation for Hough Transform.Pattern Recognition Letters,2001,22(3-4):421-429
46 姜滔．基于神经网络的车牌识别系统的研究与设计．[武汉理工大学硕士学位论文]．2002：12-15 30-35 42-50
47 Kennetch R．Castleman．数字图像处理．朱志刚．北京：电子工业出版社，2002：124-127
48 何斌，马天予，王运坚．Visual C++数字图像处理．北京：人民邮电出版社，2002：394-397
49 廖金周，宣国荣．车辆牌照的自动分割．微型电脑应用，1999，15(7)：32-34
50 T.Sirithinaphong, K.Chamnongthai. Extracting of Car License Plate Using Motor Vehicle Regulation and Character Pattern Recognition. IEEE Asia-Pacific Conference of Circuits and Systems, 1998,24-27:559-562
51 吴炜，杨晓敏，刘大宇．一种基于模糊模板匹配的车牌汉字识别方法．微型机与应用，2005，24(11)：57-59
52 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，1999，16(7)：85-87
53 Vladimir N．Vapnik．统计学习理论的本质．张学工．北京：清华大学出版社，2000：45-50
54 邹晓涛，陈学全．汽车牌照自动识别系统的设计与研制．红外与激光工程，2002，31(5)：415-418
55 黄翰敏，易正俊．基于神经网络的字符识别技术研究．重庆大学学报，1999，22(6)：59-65
56 T.Naito, T.Tsukada, K.Yamada. Robust Licene-Plate Recognition Method for Passing Vehicles Under Outside Environment. IEEE Transactions on Vehicular Technology, 2000,49(6):2309-2319
57 Tin Kam Ho. Decision Combination in Multiple Classifier Systems. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994,16(1):66-75
58 Paolo Comelli, Paolo Ferragina. Optical Recogntion of Motor Vehicle License Plates. IEEE Transactions on Vehicular Technology,1995,44(4):790-799
59 迟晓君，孟庆春．基于投影特征值的车牌字符分割算法．计算机应用研究，2006，23(7)：256-257
60 陈景航，杨宜民．基于小波变换和神经网络的车牌识别系统．计算机工程，2005，31(15)：175-177
61 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．计算机测量与控制，2006，14(9)：1257-1259
62 王永茂，刘贺平．强噪声车牌图像中的字符识别．计算机仿真，2006，23(12)：244-246
63 胡乃平，王丽，周艳平．一种改进的BP算法及其在车牌识别中的应用．微计算机信息，2006，09S：313-314
64 任民宏．轮廓跟踪算法的改进及在字符识别技术中的应用．计算机应用，2006，26(10)：2378-2379 2382
65 王春，刘波，周新志．采用BP神经网络的车牌字符识别方法研究．中国测试技术，2005，31(1)：26-28
2 Kerry L.Clines. Intelligent Transportation Systems. Better Roads,2005,75(7):75-76
3 Brian L.Smith, William T.Scherer. Development of Integrated Intelligent Transportation Systems. Transportation Research Record, 1999,(1675):84-90
4 宋维明．国外智能交通系统建设模式综述及其启示．电子技术(上海)，2006，33(12)：19-22
5 廖翔云，许锦标，龚仕伟．车牌识别技术研究．微机发展，2003，13(a02)：31-32 35
6 唐汉征．车牌识别系统的工作原理及其应用．现代电子工程，2004，(2)：66-69
7 章毓晋．图象工程—图象处理和分析．北京：清华大学出版社，1999：100-106
8 Haiyuan Wu, Qian Chen, Masahiko Yachida. Face Detection from Color Images Using a Fuzzy Pattern Matching Method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999,21 (6):557-563
9 Yihong Xu,George Nagy. Prototype Extraction and Adaptive OCR. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999,21 (12): 1280-1296
10 Jonathan J.Hull, Sargur N.Srihari, Tin K.Ho. Regression Approach to Combination of Decisions by Multiple Character Recognition Algorithms. Proceedings of SPIE-The International Society for Optical Engineering, 1992,1661:137-145
11 C.Nadal, R.Legault, C.Y.Suen. Building A New Generation of Handwriting Recognition Systems. Pattern Recognition Letters, 1993,14(4):303
12 Masato Suzuki, Nei Kato. Handprinted Character Recognition System Using Image Transformation Based on Partial Inclination Detection. IEICE Transactions on Information and Systems, 1996,E79-D(5):504-509
13 崔屹．数字图像处理技术与应用．北京：电子工业出版社，1997：100-104
14 王泽华．车牌识别系统中倾斜车牌的一种定位方法．仪器仪表用户，2005，12(4)：86-88
15 Jun Cao, M.Ahmadi, M.Shridhar. Recognition of Handwritten Numerals with Multiple Feature and Multistage Classifier. Pattern Recognition, 1995,28(2): 153-160
16 Xu Lei. Methods of Combing Multiple Classifiers and Their Application to Handwriting Recognition. IEEE Transactions on System, Man And Cybernetics, 1992,2(22):418-435
17 杨卫平，李吉成．车牌目标的自动定位技术．中国图象图形学报，2002，7(8)：835-839
18 袁晓辉，李久贤，夏良正．一种新的车牌快速定位方法．东南大学学报：自然科学版，2003，33(1)：82-85
19 张宏林．Visual C++数字图像模式识别技术及工程实践．北京：人民邮电出版社，2003：2-5 300-310 422-423
20 肖志涛，孟翔宇．基于Hough变换的倾斜文本图像的检测．红外与激光工程，2002，31(4)：315-317 350
21 刘效静，成瑜．汽车牌照自动识别技术研究．南京航空航天大学学报，1998，30(5)：573-577
22 王少杰，朱志刚．货运列车车型车号自动分割和识别算法．模式识别与人工智能，1998，11(3)：328-334
23 飞思科技产品研发中心．MATLAB6.5辅助图像处理．北京：电子工业出版社，2003：173-176
24 鹿晓亮，陈继荣．复杂背景下快速车牌定位方法研究．计算机仿真，2006，23(7)：256-259
25 Richard G.Casey, Eric Lecolinet. Survey of Methods and Strategies in Character Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence,1996, 18(7):690-706
26 Charl Coetzee, Charl Botha, David Weber. PC Based Number Plate Recognition System. IEEE International Symposium on Industrial Electronics,1998,2:605-610
27 许健，段小梅．车牌定位技术在“电子警察”系统中的应用研究．自动化与信息工程，2006，27(3)：18-20
28 王润生．图像理解．北京：国防科技大学出版社，1995：156-159
29 牛欣，沈兰荪．汽车牌照识别技术的研究．测控技术，1999，18(12)：14-17
30 D.S.Kim, S.I.Chien. Automatic Car License Plate Extraction Using Modified Generalized Symmetry Transform and Image Warping. IEEE International Symposium on Industrial Electronics,2001,3:2022-2027
31 Christos Nikolaos E.Anagnostopoulos, Vassili Loumos. A License Plate-Recognition Algorithm for Intelligent Transportation System Applications. IEEE Transactions on Intelligent Transportation Systems,2006,7(3):377-391
32 S.H.Park, K.I.Kim. Locating Car License Plates Using Neural Networks. Electronics Letters, 1999,35(17): 1475-1477
33 郝永杰，刘文耀，路烁．畸变汽车牌照图像的空间校正．西南交通大学学报，2002，37(4)：417-420
34 叶晨洲，廖金周．车辆牌照字符识别系统．计算机系统应用，1999，(5)：10-13
35 胡强．基于特征信息的车牌识别系统的研究．[西南交通大学硕士学位论文]．2004：35-38
36 Chun-Ming Tsai, His-Jian Lee. Binarization of Color Document Images via Luminance and Saturation Color Features. IEEE Transaction on Image Processing,2002,11(4): 434-451
37 Cheng Shyi-Chyi, Kuo Chen-Tsung, Chen Hong-Jay. Visual Object Retrieval via Block-based Visual-pattern Matching. Pattern Recognition,2007,40(6):1695-1710
38 R.M.Brows, T.H.Fay. Handprinted Symbol Recognition System. Pattern Recognition, 1988,21(2):91-118
39 林纯青，徐立亚．汽车图像中字符目标的提取算法．上海交通大学学报，1998，32(10)：1-39
40 沈定刚，李艳斌．汽车牌照自动定位算法．无线电通信技术，1995，21(5)：35-38
41 杨枝灵，王开．数字图像获取处理及实践应用．北京：人民邮电出版社，2003：50-53
42 边肇棋，张学．模式识别．北京：清华大学出版社，2000：104-108
43 R.Parisi, G.Lucarelli. Car Plate Recognition by Neural Networks and Image Processing. IEEE International Symposium on Circuits and Systems, 1998,3:195-198
44 陶军．车牌识别技术研究与实现．[南京理工大学硕士学位论文]．2004：3-10
45 Y.T.Ching.Detecting Line Segments in An Image-A New Implementation for Hough Transform.Pattern Recognition Letters,2001,22(3-4):421-429
46 姜滔．基于神经网络的车牌识别系统的研究与设计．[武汉理工大学硕士学位论文]．2002：12-15 30-35 42-50
47 Kennetch R．Castleman．数字图像处理．朱志刚．北京：电子工业出版社，2002：124-127
48 何斌，马天予，王运坚．Visual C++数字图像处理．北京：人民邮电出版社，2002：394-397
49 廖金周，宣国荣．车辆牌照的自动分割．微型电脑应用，1999，15(7)：32-34
50 T.Sirithinaphong, K.Chamnongthai. Extracting of Car License Plate Using Motor Vehicle Regulation and Character Pattern Recognition. IEEE Asia-Pacific Conference of Circuits and Systems, 1998,24-27:559-562
51 吴炜，杨晓敏，刘大宇．一种基于模糊模板匹配的车牌汉字识别方法．微型机与应用，2005，24(11)：57-59
52 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，1999，16(7)：85-87
53 Vladimir N．Vapnik．统计学习理论的本质．张学工．北京：清华大学出版社，2000：45-50
54 邹晓涛，陈学全．汽车牌照自动识别系统的设计与研制．红外与激光工程，2002，31(5)：415-418
55 黄翰敏，易正俊．基于神经网络的字符识别技术研究．重庆大学学报，1999，22(6)：59-65
56 T.Naito, T.Tsukada, K.Yamada. Robust Licene-Plate Recognition Method for Passing Vehicles Under Outside Environment. IEEE Transactions on Vehicular Technology, 2000,49(6):2309-2319
57 Tin Kam Ho. Decision Combination in Multiple Classifier Systems. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994,16(1):66-75
58 Paolo Comelli, Paolo Ferragina. Optical Recogntion of Motor Vehicle License Plates. IEEE Transactions on Vehicular Technology,1995,44(4):790-799
59 迟晓君，孟庆春．基于投影特征值的车牌字符分割算法．计算机应用研究，2006，23(7)：256-257
60 陈景航，杨宜民．基于小波变换和神经网络的车牌识别系统．计算机工程，2005，31(15)：175-177
61 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．计算机测量与控制，2006，14(9)：1257-1259
62 王永茂，刘贺平．强噪声车牌图像中的字符识别．计算机仿真，2006，23(12)：244-246
63 胡乃平，王丽，周艳平．一种改进的BP算法及其在车牌识别中的应用．微计算机信息，2006，09S：313-314
64 任民宏．轮廓跟踪算法的改进及在字符识别技术中的应用．计算机应用，2006，26(10)：2378-2379 2382
65 王春，刘波，周新志．采用BP神经网络的车牌字符识别方法研究．中国测试技术，2005，31(1)：26-28