基于小波变换和神经网络的车牌识别系统研究
|
摘要
本文将现代信号处理技术——小波技术,应用到智能交通领域,即车牌识别技术当中来,并结合改进的BP神经网络对车牌字符进行分类识别。主要的研究内容和成果如下:
首先,对车辆图像进行灰度变换、平滑处理,通过分析传统图像增强的方法,提出了一种基于小波变换的高频非线性增强算法;结合边缘检测、形态学处理、投影法等算法,提出了一种基于小波变换的车牌定位算法。
其次,对车牌图像进行二值化、倾斜角校正处理,提出了一种基于小波变换的局部自适应多阈值消噪方法;在对字符进行分割的过程中,先去除车牌区域的上下边框,利用垂直投影和先验知识相结合的方法初步分割出单个字符区域,再寻找字符的形态学连通域,切出字符矩形最小区域,对误切分汉字进行合并处理。
最后,对字符进行归一化、细化处理;采用分类识别的方法,用改进的BP神经网络对字符进行识别。
In this dissertation, modern signal processing technique, namely wavelet technology is applied to the intelligent transportation field, which is License Plate Recognition System. And improved BP neural network is adopted to recognize license plate characters. The main contents and achievements are as follows:
Firstly, the car images are processed by gray transformation and smooth filtering. By way of analyzing the methods of traditional image enhancement, we put forward an algorithm of high-frequency nonlinear enhancement based on the wavelet transformation. Combining with algorithms of edge detection and morphology processing and projection method, we put forward an algorithm of license plate location based on the wavelet transformation.
Secondly, the license plate images are processed by binary method and correcting inclination angle. We put forward an algorithm of local adaptive threshold removing noise based on the wavelet transformation. During the process of character segmentation, we remove the margin height of the license plate area, use vertical projection information and the prior knowledge to get single characters, look for the morphology connected domain of the character, cut off the rectangle minimal area, and combine the error segmentations.
Finally, we normalize the character images and make them thinner; By way of classified recognition, we use improved BP neural network to recognize license plate characters.
首先,对车辆图像进行灰度变换、平滑处理,通过分析传统图像增强的方法,提出了一种基于小波变换的高频非线性增强算法;结合边缘检测、形态学处理、投影法等算法,提出了一种基于小波变换的车牌定位算法。
其次,对车牌图像进行二值化、倾斜角校正处理,提出了一种基于小波变换的局部自适应多阈值消噪方法;在对字符进行分割的过程中,先去除车牌区域的上下边框,利用垂直投影和先验知识相结合的方法初步分割出单个字符区域,再寻找字符的形态学连通域,切出字符矩形最小区域,对误切分汉字进行合并处理。
最后,对字符进行归一化、细化处理;采用分类识别的方法,用改进的BP神经网络对字符进行识别。
In this dissertation, modern signal processing technique, namely wavelet technology is applied to the intelligent transportation field, which is License Plate Recognition System. And improved BP neural network is adopted to recognize license plate characters. The main contents and achievements are as follows:
Firstly, the car images are processed by gray transformation and smooth filtering. By way of analyzing the methods of traditional image enhancement, we put forward an algorithm of high-frequency nonlinear enhancement based on the wavelet transformation. Combining with algorithms of edge detection and morphology processing and projection method, we put forward an algorithm of license plate location based on the wavelet transformation.
Secondly, the license plate images are processed by binary method and correcting inclination angle. We put forward an algorithm of local adaptive threshold removing noise based on the wavelet transformation. During the process of character segmentation, we remove the margin height of the license plate area, use vertical projection information and the prior knowledge to get single characters, look for the morphology connected domain of the character, cut off the rectangle minimal area, and combine the error segmentations.
Finally, we normalize the character images and make them thinner; By way of classified recognition, we use improved BP neural network to recognize license plate characters.
引文
[1]万宜.基于小波神经网络的车牌自动识别研究[D].硕士论文,东南大学,2004.
[2] Shi Qixin. The Present Situation of Road Transportation and Expectation of ITS Researches in China[C]. 3rd World Congress on ITS, 1996, 265-286.
[3] M.N.Grainier. F.Stabile and P.Camellia. Recognition of Motor Vehicle License Plates in Rear-View Images[J]. In: Jorge L.C. Saenz(Ed), Image Technology. Advances in Image Processing, Multimedia and Machine Vision, Springer Verlag, Berlin, 1996, 231-252.
[4]牛欣,沈兰荪.汽车牌照识别技术的研究[J] .测控技术,1999,18(12): 14-17.
[5]郭娟.车辆牌照自动识别系统[D].硕士论文,东北大学,2005.
[6]沈定刚,李艳斌,戚飞虎.汽车牌照自动定位算法[J].无线电通信技术,1995,21(5):35-38.
[7] Yi In. Machine Printed Character Segmentation-An overview[J]. Pattern Recognition, 1995, 28(1):67-80.
[8] Thanongsak. Sirthinaphuong. Extracting of Car License Plate Using Motor Vehicle Regulation and Character Pattern Recognition[C]. IEEE Asia Pacific Conference on Circuits and Systems-Proceedings, 1998, 559-562.
[9] M.H.terBrugge. J.H.Stevens. J.A.G. Nijhuis. License Plate Recognition[C]. Proceedings IEEE International Symposium on Circuits and Systems, 1999, 135- 138.
[10]王涛.基于小波变换和神经网络的车牌识别算法研究[D].硕士论文,武汉理工大学,2007.
[11]刘艳云.基于小波变换与RBF神经网络的车牌自动识别技术的研究[D].硕士论文,2006.
[12]林纯青.汽车图像中字符目标的提取算法[J].上海交通大学学报,1998,32(10):1-4.
[13]田村秀行,金喜子,乔双.计算机图像处理[M].北京:科学出版社,1998,1-20.
[14]朱俊梅,陈少平.基于改进的投影方法的车牌图像字符分割[J].中南民族大学学报(自然科学版),2007,26(4):58-61.
[15]薛宏全.基于小波分析的车牌识别系统研究[D].硕士论文,电子科技大学,2005.
[16]程正行,杨守志,冯晓霞.小波分析的理论、算法、进展和应用[M].北京:国防工业出版社,2007,1-11.
[17]飞思科技产品研发中心.小波分析理论与MATLAB7实现[M].北京:电子工业出版社,2005,3-16,74-81.
[18]姜成丽.基于小波变换的超宽带信号处理技术研究[D].硕士论文,黑龙江大学,2008.
[19]龚声蓉,刘纯平,王强.数字图像处理与分析[M].北京:清华大学出版社,2006,46-80.
[20]边肇棋,张学工.模式识别[M].北京:清华大学出版社(第二版),2000,315-329.
[21]王慧琴.数字图像处理[M].北京:北京邮电大学出版社,2006,80-103.
[22]何宏,唐志航,张细政,杨保安.基于小波多尺度积的图像增强新算法[J].计算机应用与软件,2007,24(3):163-165.
[23]彭玉华.小波变换与工程应用[M].北京:科学出版社,1999,23-70.
[24]戴天荣,张立明.一种改进的非线性外推图像增强算法及在高分辨率图像重建中的应用[J].红外与毫米波学报,2003,22(3):197-202.
[25]戴天荣,张立明,王建军.基于低通和非线性滤波的MR图像增强算法[J].中国医学物理学杂志,2003,20(3):146-148.
[26] Luis Salgado. Automatic Car Plate Detection and Recognition through Intelligent Vision Engineering[C]. IEEE Annual International Carnahan Conference on Security Technology Proceedings, 1999, 71-76.
[27] Yuntao Cui. Character Extraction of License Plates from Video[C]. Proceedings of The IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997, 502-507.
[28] Yuntao Cui. Automatic License Extraction from Moving Vehicles[C]. IEEE International Conference on Image Processing, 1997, (3):126-129.
[29] H.A.Hegt. Ron J. De La Haye. Nadeem A. Khan. A High Performance License Plate Recognition System[C]. Proceedings of IEEE International Conference on System, 1998, (5):4357-4362.
[30]郑南宁.汽车牌照自动识别中的目标与背景的快速分割[J].信息与控制,1988,(2):27-31.
[31] Young Sung Soh. Design of Real Time Vehicle Identification system [C]. Proceedings of The IEEE International Conference on Systems, 1994, (3):2147-2152.
[32] Thanongsak. Sirithinaphong. The Recognition of Car License Plate for Automatic Parking System[C]. Proceedings of the Fifth International Symposium on Signal Processing and Its Application, 1999, (1):455-457.
[33] Thanongsak. Sirithinaphong. Extracting of Car License Plate Using Motor Vehicle Regulation and Character Pattern Recognition[C]. IEEE Asia-Pacific Conference on Circuits and Systems Proceedings,1998, 559-562.
[34] M.H.ter Brugge. License Plate Recognition Using DTCNNs[C]. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications, 1998, 212-217.
[35] M.H.ter Brugge. Car License Plate Recognition with Neural Networks and Fuzzy Logic[C]. IEEE International Conference on Neural Networks Conference Proceedings, 1995, (5):2232-2236.
[36] S.H.Park. Locating Car License Plate Using Neural Networks[J]. Electronics Letters, 1999, (17):1475-1477.
[37] Rodolfo Zunino. Vector Quantization for License Plate Location and Image Coding[J]. IEEE Transactions on Industrial Electronics, 2000, 47(1):159-167.
[38] Rodolfo Zunino. Visual Location of License Plates by Vector Quantization[C]. Proceedings of The IEEE International Symposium on Circuits and Systems, 1999, (4):135-138.
[39]王郑耀.数字图像的边缘检测[D].硕士论文,西安交通大学,2003.
[40]冈萨雷斯.数字图像处理[M].北京:电子工业出版社,2007,255-284.
[41]章毓晋.图象处理和分析(图像工程上册)[M].北京:清华大学出版社,1999,224-226,254-277.
[42]杨帆,雷正平.基于二值化法的车牌图像自动定位技术研究[J].武汉化工学院学报,2004,26(1):67-69.
[43]李凌.一种改进的车牌图像二值化方法[J].人工智能及识别技术,2003,(9):162-164.
[44] Kamel Mohamed. Zhao Aiguo. Extraction of Binary Character/Graphics Image from Grayscale Document Images[J]. Graphical Models and Image Processing, 1993, 55(3):203.
[45] Wu Yiqian. Zhu Zhaoda. 30 Years (1962-1992) of The Developments in Threshold Selection Methods in Image Processing[J]. Journal of Data Acquisition & Processing, 1993, 8(3):193.
[46]韦平安.车牌识别系统技术研究[D].硕士论文,广西师范大学,2008.
[47]徐慧. Visual C++数字图像实用工程案例精选[M].北京:人民邮电出版社,2004,231-232.
[48]黄骥.汽车牌照识别系统中车牌定位与校正及字符分割的研究[D].硕士论文,南京航空航天大学,2007.
[49]谭艳丽,张丕状.基于自适应阈值的小波图像去噪法研究[J].人工智能及识别技术,2007,(5):1681-1683.
[50] S.G. Chang. B.Yu and V.Martin. Adaptive Wavelet Thresholding for Image Denoising and Compression[C]. IEEE Transactions on Image Processing, 2000, 9(9):1532-1546.
[51]尉世强.基于小波的图像阈值去噪方法[D].硕士论文,青岛大学,2006.
[52] C.M.Stein. Estimation of The Mean of A Multivariate Normal Distribution, Annual Statistical, 1981, 9(6):1135-1151.
[53]王益艳,王博,陈伟伟,梁娟.基于小波变换的图像自适应阈值去噪算法[J].微计算机应用,2008,29(1):15-18.
[54]曹迪铭,宣国荣.牌照字符分割中的区域分裂与合并[J].计算机工程,2000,26(10):18-21.
[55]邹永星.车牌字符分割方法的研究[D].硕士论文,湖南师范大学,2008.
[56] Michael Wroth. Survey of Neural Network Technology for Automatic Target Recognition[J]. IEEE Trans Neural Networks, 1990, 1(1):28-43.
[57] Alessandro Vinciarell. A Survey on Off-line Cursive Word Recognition[J]. Pattern Recognition, 2002, (35):1433-1446.
[58] V.K.Govinda. A.P.Shicaprasad. Character Recognition-A View[J]. Pattern Recognition, 1990, 23(7):671-683.
[59] Riedi R H. Crouse M S. Ribeiro V J. A Multi-scale Wavelet Model With Application to Network Traffic[J]. IEEE Trans oInfo Theory, 1999, 45(3):992-1018.
[60] Heutte L. Paquet T. Moreau J V. A Structural/statistical Feature Based Vector for Handwritten Character Recognition[J]. Pattern Recognition Letters, 1998, 19(7):629-641.
[61]庞东虎,金伟杰.英文字符特征提取系统[J].计算机仿真,2007,24(12):208-210.
[62]董长虹. Matlab神经网络与应用(第2版)[M].北京:国防工业出版社,2007,6-13,64-91.
[63]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005,1-9,69-100.
[64] A.Bouloutas. S.Calo. A.Finkel. Alarm Correlation and Fault Identification in Communication Networks[J]. IEEE Transaction on Communication, 1994, 42(1):523-533.
[65] Parisi R. Claudio E D. Lucharelli G.. Car Plate Recognition by Neural Networks and Image Processing[J]. IEEE International System On Circuit and System, 2005, 3(6):196-198.
[66] Parist R. Car Plate Recognition by Neural Networks and Image Processing[J]. In: Proc. IEEE International Symposium on Circuit and Systems, 2000, 5(3):31-37.
[67]汤红忠.基于神经网络的车牌识别系统研究[D].硕士论文,湘潭大学,2004.
[68]邢向华,顾国华.基于模板匹配和特征点匹配相结合的快速车牌识别方法[J].光电子技术,2003,23(4):268-270.
[69]求是科技. Visual C++数字图像处理典型算法及实现[M].北京:人民邮电出版社,2006,498-502.
[70] ShyangLih Chang. LiShien Chen. YunChung Chung. SeiWan Chen. Automatic License Plate Recognition[J]. IEEE Transactions on Intelligent Transportation systems, 2004, 5(1):42-53.
[2] Shi Qixin. The Present Situation of Road Transportation and Expectation of ITS Researches in China[C]. 3rd World Congress on ITS, 1996, 265-286.
[3] M.N.Grainier. F.Stabile and P.Camellia. Recognition of Motor Vehicle License Plates in Rear-View Images[J]. In: Jorge L.C. Saenz(Ed), Image Technology. Advances in Image Processing, Multimedia and Machine Vision, Springer Verlag, Berlin, 1996, 231-252.
[4]牛欣,沈兰荪.汽车牌照识别技术的研究[J] .测控技术,1999,18(12): 14-17.
[5]郭娟.车辆牌照自动识别系统[D].硕士论文,东北大学,2005.
[6]沈定刚,李艳斌,戚飞虎.汽车牌照自动定位算法[J].无线电通信技术,1995,21(5):35-38.
[7] Yi In. Machine Printed Character Segmentation-An overview[J]. Pattern Recognition, 1995, 28(1):67-80.
[8] Thanongsak. Sirthinaphuong. Extracting of Car License Plate Using Motor Vehicle Regulation and Character Pattern Recognition[C]. IEEE Asia Pacific Conference on Circuits and Systems-Proceedings, 1998, 559-562.
[9] M.H.terBrugge. J.H.Stevens. J.A.G. Nijhuis. License Plate Recognition[C]. Proceedings IEEE International Symposium on Circuits and Systems, 1999, 135- 138.
[10]王涛.基于小波变换和神经网络的车牌识别算法研究[D].硕士论文,武汉理工大学,2007.
[11]刘艳云.基于小波变换与RBF神经网络的车牌自动识别技术的研究[D].硕士论文,2006.
[12]林纯青.汽车图像中字符目标的提取算法[J].上海交通大学学报,1998,32(10):1-4.
[13]田村秀行,金喜子,乔双.计算机图像处理[M].北京:科学出版社,1998,1-20.
[14]朱俊梅,陈少平.基于改进的投影方法的车牌图像字符分割[J].中南民族大学学报(自然科学版),2007,26(4):58-61.
[15]薛宏全.基于小波分析的车牌识别系统研究[D].硕士论文,电子科技大学,2005.
[16]程正行,杨守志,冯晓霞.小波分析的理论、算法、进展和应用[M].北京:国防工业出版社,2007,1-11.
[17]飞思科技产品研发中心.小波分析理论与MATLAB7实现[M].北京:电子工业出版社,2005,3-16,74-81.
[18]姜成丽.基于小波变换的超宽带信号处理技术研究[D].硕士论文,黑龙江大学,2008.
[19]龚声蓉,刘纯平,王强.数字图像处理与分析[M].北京:清华大学出版社,2006,46-80.
[20]边肇棋,张学工.模式识别[M].北京:清华大学出版社(第二版),2000,315-329.
[21]王慧琴.数字图像处理[M].北京:北京邮电大学出版社,2006,80-103.
[22]何宏,唐志航,张细政,杨保安.基于小波多尺度积的图像增强新算法[J].计算机应用与软件,2007,24(3):163-165.
[23]彭玉华.小波变换与工程应用[M].北京:科学出版社,1999,23-70.
[24]戴天荣,张立明.一种改进的非线性外推图像增强算法及在高分辨率图像重建中的应用[J].红外与毫米波学报,2003,22(3):197-202.
[25]戴天荣,张立明,王建军.基于低通和非线性滤波的MR图像增强算法[J].中国医学物理学杂志,2003,20(3):146-148.
[26] Luis Salgado. Automatic Car Plate Detection and Recognition through Intelligent Vision Engineering[C]. IEEE Annual International Carnahan Conference on Security Technology Proceedings, 1999, 71-76.
[27] Yuntao Cui. Character Extraction of License Plates from Video[C]. Proceedings of The IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1997, 502-507.
[28] Yuntao Cui. Automatic License Extraction from Moving Vehicles[C]. IEEE International Conference on Image Processing, 1997, (3):126-129.
[29] H.A.Hegt. Ron J. De La Haye. Nadeem A. Khan. A High Performance License Plate Recognition System[C]. Proceedings of IEEE International Conference on System, 1998, (5):4357-4362.
[30]郑南宁.汽车牌照自动识别中的目标与背景的快速分割[J].信息与控制,1988,(2):27-31.
[31] Young Sung Soh. Design of Real Time Vehicle Identification system [C]. Proceedings of The IEEE International Conference on Systems, 1994, (3):2147-2152.
[32] Thanongsak. Sirithinaphong. The Recognition of Car License Plate for Automatic Parking System[C]. Proceedings of the Fifth International Symposium on Signal Processing and Its Application, 1999, (1):455-457.
[33] Thanongsak. Sirithinaphong. Extracting of Car License Plate Using Motor Vehicle Regulation and Character Pattern Recognition[C]. IEEE Asia-Pacific Conference on Circuits and Systems Proceedings,1998, 559-562.
[34] M.H.ter Brugge. License Plate Recognition Using DTCNNs[C]. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications, 1998, 212-217.
[35] M.H.ter Brugge. Car License Plate Recognition with Neural Networks and Fuzzy Logic[C]. IEEE International Conference on Neural Networks Conference Proceedings, 1995, (5):2232-2236.
[36] S.H.Park. Locating Car License Plate Using Neural Networks[J]. Electronics Letters, 1999, (17):1475-1477.
[37] Rodolfo Zunino. Vector Quantization for License Plate Location and Image Coding[J]. IEEE Transactions on Industrial Electronics, 2000, 47(1):159-167.
[38] Rodolfo Zunino. Visual Location of License Plates by Vector Quantization[C]. Proceedings of The IEEE International Symposium on Circuits and Systems, 1999, (4):135-138.
[39]王郑耀.数字图像的边缘检测[D].硕士论文,西安交通大学,2003.
[40]冈萨雷斯.数字图像处理[M].北京:电子工业出版社,2007,255-284.
[41]章毓晋.图象处理和分析(图像工程上册)[M].北京:清华大学出版社,1999,224-226,254-277.
[42]杨帆,雷正平.基于二值化法的车牌图像自动定位技术研究[J].武汉化工学院学报,2004,26(1):67-69.
[43]李凌.一种改进的车牌图像二值化方法[J].人工智能及识别技术,2003,(9):162-164.
[44] Kamel Mohamed. Zhao Aiguo. Extraction of Binary Character/Graphics Image from Grayscale Document Images[J]. Graphical Models and Image Processing, 1993, 55(3):203.
[45] Wu Yiqian. Zhu Zhaoda. 30 Years (1962-1992) of The Developments in Threshold Selection Methods in Image Processing[J]. Journal of Data Acquisition & Processing, 1993, 8(3):193.
[46]韦平安.车牌识别系统技术研究[D].硕士论文,广西师范大学,2008.
[47]徐慧. Visual C++数字图像实用工程案例精选[M].北京:人民邮电出版社,2004,231-232.
[48]黄骥.汽车牌照识别系统中车牌定位与校正及字符分割的研究[D].硕士论文,南京航空航天大学,2007.
[49]谭艳丽,张丕状.基于自适应阈值的小波图像去噪法研究[J].人工智能及识别技术,2007,(5):1681-1683.
[50] S.G. Chang. B.Yu and V.Martin. Adaptive Wavelet Thresholding for Image Denoising and Compression[C]. IEEE Transactions on Image Processing, 2000, 9(9):1532-1546.
[51]尉世强.基于小波的图像阈值去噪方法[D].硕士论文,青岛大学,2006.
[52] C.M.Stein. Estimation of The Mean of A Multivariate Normal Distribution, Annual Statistical, 1981, 9(6):1135-1151.
[53]王益艳,王博,陈伟伟,梁娟.基于小波变换的图像自适应阈值去噪算法[J].微计算机应用,2008,29(1):15-18.
[54]曹迪铭,宣国荣.牌照字符分割中的区域分裂与合并[J].计算机工程,2000,26(10):18-21.
[55]邹永星.车牌字符分割方法的研究[D].硕士论文,湖南师范大学,2008.
[56] Michael Wroth. Survey of Neural Network Technology for Automatic Target Recognition[J]. IEEE Trans Neural Networks, 1990, 1(1):28-43.
[57] Alessandro Vinciarell. A Survey on Off-line Cursive Word Recognition[J]. Pattern Recognition, 2002, (35):1433-1446.
[58] V.K.Govinda. A.P.Shicaprasad. Character Recognition-A View[J]. Pattern Recognition, 1990, 23(7):671-683.
[59] Riedi R H. Crouse M S. Ribeiro V J. A Multi-scale Wavelet Model With Application to Network Traffic[J]. IEEE Trans oInfo Theory, 1999, 45(3):992-1018.
[60] Heutte L. Paquet T. Moreau J V. A Structural/statistical Feature Based Vector for Handwritten Character Recognition[J]. Pattern Recognition Letters, 1998, 19(7):629-641.
[61]庞东虎,金伟杰.英文字符特征提取系统[J].计算机仿真,2007,24(12):208-210.
[62]董长虹. Matlab神经网络与应用(第2版)[M].北京:国防工业出版社,2007,6-13,64-91.
[63]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005,1-9,69-100.
[64] A.Bouloutas. S.Calo. A.Finkel. Alarm Correlation and Fault Identification in Communication Networks[J]. IEEE Transaction on Communication, 1994, 42(1):523-533.
[65] Parisi R. Claudio E D. Lucharelli G.. Car Plate Recognition by Neural Networks and Image Processing[J]. IEEE International System On Circuit and System, 2005, 3(6):196-198.
[66] Parist R. Car Plate Recognition by Neural Networks and Image Processing[J]. In: Proc. IEEE International Symposium on Circuit and Systems, 2000, 5(3):31-37.
[67]汤红忠.基于神经网络的车牌识别系统研究[D].硕士论文,湘潭大学,2004.
[68]邢向华,顾国华.基于模板匹配和特征点匹配相结合的快速车牌识别方法[J].光电子技术,2003,23(4):268-270.
[69]求是科技. Visual C++数字图像处理典型算法及实现[M].北京:人民邮电出版社,2006,498-502.
[70] ShyangLih Chang. LiShien Chen. YunChung Chung. SeiWan Chen. Automatic License Plate Recognition[J]. IEEE Transactions on Intelligent Transportation systems, 2004, 5(1):42-53.