基于支持向量机的字符识别系统的研究与实现
|
摘要
图像处理技术的发展自上世纪50年代,在20世纪60年代迅速发展并成为了一门新学科。到今天,数字图像处理在科学研究、工农业生产、军事技术、卫生医疗、政府部门等许多领域中,发挥着越来越重要的作用。传统的图像识别在PC机上实现,识别算法多基于神经网络和模板匹配等。此类方法需要在样本数目足够多的前提下才能获得较好结果。系统在便携移动性方面具有很大的局限性。随着时代的发展,人们对于系统的实时处理要求越来越高,字符识别系统在保证系统运算速度、识别精度高的前提下,逐渐向集成化、便携性方向发展。本文基于这样的背景,提出了在嵌入式平台上通过支持向量机算法实现字符图像识别。
(1)图像预处理。对字符定位、倾斜校正、字符分割、字符归一化等方面进行了研究,比较了各算法的优缺点,对于关键的字符定位和字符分割两方面提出了自己解决方法。并且具有一定的通用性。
(2)字符识别。深入学习支持向量机算法,在提取字符图像的轮廓线数特征的基础上,利用傅立叶描绘子提取字符外轮廓线特征,将两者相结合作为SVM的向量进行训练、识别,最终实现字符识别。
(3)系统总体方案的提出。设计了字符识别系统的软件和硬件的总体框架。对嵌入式Linux系统开发进行了深入的研究和探讨。
(4)在嵌入式Linux平台上实现了以下功能:图像采集模块的开发过程中,对Linux下的USB摄像头驱动和V4L标准进行了深入的研究,并在此基础上实现了图像采集存储。移植并实现了PPP协议,使得终端能够无线上网。编写了socket服务器端和客户端程序,使得两者之间能进行数据交换,传输识别的字符。在此功能基础上,结合本文实现的字符识别功能,构成了一个完整的字符识别系统。
Image processing technology began in the 1950s, it became a new subject in the 1960s quickly. With the development of the society, the image processing technology has played a more and more important role in our life, such as in science research, military technology, medicial and health service, industrial production and government department. However, traditional statistic mode for recognition realized on the base of PC, such as template matching and neural network. For this way, it could get good effectiveness only under the condition of adequate samples. Its system has great limitations on the portable and moving hands. With the development of the society, people have the increasing need of real time data processing. On based of this present situation, this paper put forward a way to realize character image recognition using support vector machine algorithm on the platform of embedded Linux operation system.
(1) For the pretreatment of the image, on the hands of image capture, character location, character segmentation, author compares the good points and bad points of all kinds of algorithm. Meanwhile, for the important two hands (character location, character segmentation), author also puts forward his new thoughts and solvements.
(2) Character recognition. After deeply learning the Support Vector Machine algorithm, on the base of Fourier descriptors and support vector machine is presented. Character features are extracted from the outer contour by Fourier descriptors, which constructs the input vector of the multi-classes support vector machine. The test results show the effectiveness of the algorithm even with limited samples.
(3) The overall design of the system. This paper firstly summarizes the development course and current situation of the research for character recognition system. Then it designs the framework of the software and hardware of the character recognition system. It also has a serious study and discussion for the development of embedded Linux system.
(4) On the platform of Linux operation system, it will realize the following functions. Firstly, it realizes the video-capturing module based on the research of the V4L standard and the USB camera driver under Linux. Second, it realizes PPP protocol on the embedded Linux system, which endows the intelligent terminal with the functions of wireless internet connection and transfer a large amount of data.
(1)图像预处理。对字符定位、倾斜校正、字符分割、字符归一化等方面进行了研究,比较了各算法的优缺点,对于关键的字符定位和字符分割两方面提出了自己解决方法。并且具有一定的通用性。
(2)字符识别。深入学习支持向量机算法,在提取字符图像的轮廓线数特征的基础上,利用傅立叶描绘子提取字符外轮廓线特征,将两者相结合作为SVM的向量进行训练、识别,最终实现字符识别。
(3)系统总体方案的提出。设计了字符识别系统的软件和硬件的总体框架。对嵌入式Linux系统开发进行了深入的研究和探讨。
(4)在嵌入式Linux平台上实现了以下功能:图像采集模块的开发过程中,对Linux下的USB摄像头驱动和V4L标准进行了深入的研究,并在此基础上实现了图像采集存储。移植并实现了PPP协议,使得终端能够无线上网。编写了socket服务器端和客户端程序,使得两者之间能进行数据交换,传输识别的字符。在此功能基础上,结合本文实现的字符识别功能,构成了一个完整的字符识别系统。
Image processing technology began in the 1950s, it became a new subject in the 1960s quickly. With the development of the society, the image processing technology has played a more and more important role in our life, such as in science research, military technology, medicial and health service, industrial production and government department. However, traditional statistic mode for recognition realized on the base of PC, such as template matching and neural network. For this way, it could get good effectiveness only under the condition of adequate samples. Its system has great limitations on the portable and moving hands. With the development of the society, people have the increasing need of real time data processing. On based of this present situation, this paper put forward a way to realize character image recognition using support vector machine algorithm on the platform of embedded Linux operation system.
(1) For the pretreatment of the image, on the hands of image capture, character location, character segmentation, author compares the good points and bad points of all kinds of algorithm. Meanwhile, for the important two hands (character location, character segmentation), author also puts forward his new thoughts and solvements.
(2) Character recognition. After deeply learning the Support Vector Machine algorithm, on the base of Fourier descriptors and support vector machine is presented. Character features are extracted from the outer contour by Fourier descriptors, which constructs the input vector of the multi-classes support vector machine. The test results show the effectiveness of the algorithm even with limited samples.
(3) The overall design of the system. This paper firstly summarizes the development course and current situation of the research for character recognition system. Then it designs the framework of the software and hardware of the character recognition system. It also has a serious study and discussion for the development of embedded Linux system.
(4) On the platform of Linux operation system, it will realize the following functions. Firstly, it realizes the video-capturing module based on the research of the V4L standard and the USB camera driver under Linux. Second, it realizes PPP protocol on the embedded Linux system, which endows the intelligent terminal with the functions of wireless internet connection and transfer a large amount of data.
引文
[1]边肇祺,张学工.模式识别[M].清华大学出版社,2002.
[2]Vapnik V.Statistical Learning Theory[M].Wiley,New York,NY,1998.
[3]Hong Z.Algebraic feature extraction of image for fecognition Pattern Recognition[J],1991,24:211-219.
[4]Wenming Zheng,Cairong Zou,Zhao Li.Face Recognition Using Two Novel Nearest Neighbor Classifiers[C].In:Proceedings of IC-ASSP,2004.725-72.
[5]徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,2002,7.
[6]王晓光,王晓华.一种基于SVM的车牌汉字的有效识别方法[J].计算机工程与应用,2004.24:208-209.
[7]李士勇.模糊控制、神经网络和智能控制[M].哈尔滨:哈尔滨工业大学出版社,1996:40-41.
[8]张宏林,张立科.VC++数字图像处理模式识别技术及工程实践[M].北京:人民邮电出版社,2003.
[9]陈锻生,谢志鹏,刘征凯.复杂背景下彩色图像车牌提取与字符技术[J].小型微型计算机系统,2002-9,23:1144-1148.
[10]周德新,张向利.Linux与嵌入式操作系统[J].桂林电子工业学院学报,2000,4:21-23.
[11]吴冰,秦志远.自动确定图像二值化阈值的新方法[J].绘测学院院报,2000.
[12]CHARL C,CHARL B,DAVID W.PC based number plate recognition system [C].Proc.IEEE International Symposium on Industrial Electronics,Pretoria:[s.n.],1998:605-610.
[13]梁栋,高隽,付启众,等.基于形状特性和反Hough变换的车牌区域定位与重建[J].计算机应用,2002,22(5):43-47.
[14]郭勇,吴乐南.行驶车辆的牌照识别系统[J].光电工程,2000,27(4):60-71.
[15]张美多,郭宝龙.车牌识别系统关键技术研究[J].计算机工程,33(16):186-188.
[16]章毓晋,图像处理与分析[M],清华大学出版社,1999.2.
[17]Yi Lu,Machine printed character segmentation-An Overview[J],Pattern Recognition,1995,28(1):67-80.
[18]刘成安,孙涛.车牌自动定位与识别方法研究.微计算机信息,23(9):61-63.
[19]Vapnik V N.The nature of statistical learning theory[M].NY:SpringerVerlag,1995.
[20]Cortes C,Vapnik V.Support vector networks[J].Machine Learning,1995:273-297.
[21]Mangasarian.Generalized support vector machine[R].Techincal Report Mathematical Programming TR 98-14.University of Widconsin in Madison,1998.
[22]Wahba G,Support vector machines,reproducing kernel Hibert spaces and the randomized Gacv[R].Technical Report 984,Department of Statistics,University of Wisconsin,Nips97 workshop on Support Vector machines.
[23]Weston J and Watkins C.Multi-class Support Vector Machines.In M.Verleysen,editor,Proceedings of ESSANN99,Brussels.D.Facto Press,1999.
[24]Francis E H,Cao L J.Modified Support Vector Machines in Financial Time Series Forecasting[J].Neurcomputing,2002,48:847-861.
[25]Crammer K and Singer Y.On the learnability and design of output codes for multiclass problems[C].In Computational Learing Theory,2000:35-46.
[26]Krebel U.Pairwise Classification and Support Vector Machines,In B.Scholkopf,C J C Burgea,A J Smola,ed,Advances in Kernel Methods:Support Vector Learning,MIT Press,Cambridge,MA,1999:255-268.
[27]Chih-Chung Chang,Chih-Jen Lin.LIBSVM:a Library for Support Vector Machines(Version 2.31),September 7,2001.
[28]Scholkopf B,Burges C,Vapnik V.Extracting support data for a given task[C].In U.M.Fayyad and R.Uthurusamy,editors,First International Conference on Knowledge Discovery & Data Mining.AAAI Press,1995.
[29]Blanz V,B Scholkopf,II Bultho,Burges C,Vapnik V,Vetter T.Comparision of view-based object recognition algorithms using realistic 3D models.In C. yonder Malsburg,W Von Seelen,J C Vorbruggen,B.Sendho,editors,Arificial Neural Networks-ICANN'96,Berlin.Springer Lecture Notes in Computer Science Vol.1112.1996,251-256.
[30]白亮,老松杨,胡艳丽。支持向量机训练算法比较研究[J]。计算机工程与应用,2005,(17):79-81.
[31]Burges C.A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998,2(2):143.
[32]杜晓东,李岐强,支持向量机及其算法研究[J]。信号处理与模式识别,2005,(3):37-40.
[33]Cortes C,Vapnik V.Support vector networks[J].Machine Learning,1995,(20):273-279.
[34]Ahmed S N.Incremental learning with support vector machines[J].In workshop on support vector machines,Stockholm,Sweden,1999:38-42.
[35]Cauwenberghs G,Ppggio T.Incremental and decremental support vector machine[J].Machine Leafing,2001,(13):29-37.
[36]CHELLAPPA R,BAGDAZIAN R.Fourier coding of image boundaries[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1984,6(1):102-105.
[37]C.- C.Chang,C.-J.Lin.Libsvm:A library for support vector machines[R].Taibei.
[38]Cruz-Perez F.A,GHemandez-Valdez,Ortigoza-Guerrero L.Performance evaluation of mobile wireless communication systems with link adaptation[C].IEEE Communications Letters,Dec.2003,7(12):587589.
[39]TachiKawa K.A perspective on the evolution of mobile communications[C].IEEE Communications Magazine,Oct 2003,41(10):6673.
[40]Cheung N.K.Mobile communications for anything that moves[C].IEEE Communications Magazine,Oct 2003,41(10):64-64.
[41]Lain Bate,Steve Liu,Real-time Embedded Systems[J].Computing &Control Engineering Journal,2002,8.
[42]Bruce Powel Douglass,Real-Time Design Patterns[J],Embedded Systems Conference Papers,San Francisco,2001.
[43]Developer's Guide Motorola g20 Cellular Engine Module Description,2004.07.
[44]ROBERT Love.Linux Kernel Development[M].Indiana:SAMA,2003.
[45]BOVERT DP.CESATI M..Understanding the Linux kernel[M].O'REILLY,2000.9.
[46]Karim Yagbmour..Building Embedded Linux Systems[M].O'REILLY,2004.12.
[47]JONATHAN CORBET.,ALESSANDRO RUBINI.Linux Device Drivers[M].O'REILLY,2006.1.
[48]陈三宝.基于ARM芯片的嵌入式Linux智能通讯终端的设计[D].2005.6.
[49]Karim Yagbmour..Building Embedded Linux Systems[M].O'REILLY,2004.12.
[50]郑人杰,殷人昆,陶永雷.实用软件工程[M].北京:清华大学出版社,1996.
[51]A.A.Samjani.General Packet Radio Service[GPRS].IEEE Potentials,April-May.2002,21(2):1215.
[52]I.Goetz.Keeping up with GPRS[J].Communications Engineer,April/May 2003,1(2):4646.
[53]The Point-To-Point Protocol(PPP)by Simpson W RFC 1661,1994.
[54]黄梓锋,潘登,黄胜华.一种嵌入式系统的新型PPP连接方案[J].计算机工程,2003.29(16):175-177.
[55]Comin Light-williams,Joshua Drake,Linux PPP Howto.
[56]李建华,郭明.RS-232和调制解调器高级通信编程[M].北京:人民邮电出版社,2001.
[57]张明珊.基于GPRS网络的移动数据接入终端的研究与设计[D].2004.12.
[58]Hui Wang,Xiaofeng Liao and Chuandong Li.Existence and exponential stability of periodic solution of BAM nural networks with impulse and time varying delay.Chaos,Solitons & Fractals,2007,33(3)1028-1039.
[59]Richard Stevens,Bill Fenner,Andrew M.Rudoff.Unix Network Programming,Vol.1:The Sockets Networking API,Third Edition.2005
[2]Vapnik V.Statistical Learning Theory[M].Wiley,New York,NY,1998.
[3]Hong Z.Algebraic feature extraction of image for fecognition Pattern Recognition[J],1991,24:211-219.
[4]Wenming Zheng,Cairong Zou,Zhao Li.Face Recognition Using Two Novel Nearest Neighbor Classifiers[C].In:Proceedings of IC-ASSP,2004.725-72.
[5]徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,2002,7.
[6]王晓光,王晓华.一种基于SVM的车牌汉字的有效识别方法[J].计算机工程与应用,2004.24:208-209.
[7]李士勇.模糊控制、神经网络和智能控制[M].哈尔滨:哈尔滨工业大学出版社,1996:40-41.
[8]张宏林,张立科.VC++数字图像处理模式识别技术及工程实践[M].北京:人民邮电出版社,2003.
[9]陈锻生,谢志鹏,刘征凯.复杂背景下彩色图像车牌提取与字符技术[J].小型微型计算机系统,2002-9,23:1144-1148.
[10]周德新,张向利.Linux与嵌入式操作系统[J].桂林电子工业学院学报,2000,4:21-23.
[11]吴冰,秦志远.自动确定图像二值化阈值的新方法[J].绘测学院院报,2000.
[12]CHARL C,CHARL B,DAVID W.PC based number plate recognition system [C].Proc.IEEE International Symposium on Industrial Electronics,Pretoria:[s.n.],1998:605-610.
[13]梁栋,高隽,付启众,等.基于形状特性和反Hough变换的车牌区域定位与重建[J].计算机应用,2002,22(5):43-47.
[14]郭勇,吴乐南.行驶车辆的牌照识别系统[J].光电工程,2000,27(4):60-71.
[15]张美多,郭宝龙.车牌识别系统关键技术研究[J].计算机工程,33(16):186-188.
[16]章毓晋,图像处理与分析[M],清华大学出版社,1999.2.
[17]Yi Lu,Machine printed character segmentation-An Overview[J],Pattern Recognition,1995,28(1):67-80.
[18]刘成安,孙涛.车牌自动定位与识别方法研究.微计算机信息,23(9):61-63.
[19]Vapnik V N.The nature of statistical learning theory[M].NY:SpringerVerlag,1995.
[20]Cortes C,Vapnik V.Support vector networks[J].Machine Learning,1995:273-297.
[21]Mangasarian.Generalized support vector machine[R].Techincal Report Mathematical Programming TR 98-14.University of Widconsin in Madison,1998.
[22]Wahba G,Support vector machines,reproducing kernel Hibert spaces and the randomized Gacv[R].Technical Report 984,Department of Statistics,University of Wisconsin,Nips97 workshop on Support Vector machines.
[23]Weston J and Watkins C.Multi-class Support Vector Machines.In M.Verleysen,editor,Proceedings of ESSANN99,Brussels.D.Facto Press,1999.
[24]Francis E H,Cao L J.Modified Support Vector Machines in Financial Time Series Forecasting[J].Neurcomputing,2002,48:847-861.
[25]Crammer K and Singer Y.On the learnability and design of output codes for multiclass problems[C].In Computational Learing Theory,2000:35-46.
[26]Krebel U.Pairwise Classification and Support Vector Machines,In B.Scholkopf,C J C Burgea,A J Smola,ed,Advances in Kernel Methods:Support Vector Learning,MIT Press,Cambridge,MA,1999:255-268.
[27]Chih-Chung Chang,Chih-Jen Lin.LIBSVM:a Library for Support Vector Machines(Version 2.31),September 7,2001.
[28]Scholkopf B,Burges C,Vapnik V.Extracting support data for a given task[C].In U.M.Fayyad and R.Uthurusamy,editors,First International Conference on Knowledge Discovery & Data Mining.AAAI Press,1995.
[29]Blanz V,B Scholkopf,II Bultho,Burges C,Vapnik V,Vetter T.Comparision of view-based object recognition algorithms using realistic 3D models.In C. yonder Malsburg,W Von Seelen,J C Vorbruggen,B.Sendho,editors,Arificial Neural Networks-ICANN'96,Berlin.Springer Lecture Notes in Computer Science Vol.1112.1996,251-256.
[30]白亮,老松杨,胡艳丽。支持向量机训练算法比较研究[J]。计算机工程与应用,2005,(17):79-81.
[31]Burges C.A tutorial on support vector machines for pattern recognition[J].Data Mining and Knowledge Discovery,1998,2(2):143.
[32]杜晓东,李岐强,支持向量机及其算法研究[J]。信号处理与模式识别,2005,(3):37-40.
[33]Cortes C,Vapnik V.Support vector networks[J].Machine Learning,1995,(20):273-279.
[34]Ahmed S N.Incremental learning with support vector machines[J].In workshop on support vector machines,Stockholm,Sweden,1999:38-42.
[35]Cauwenberghs G,Ppggio T.Incremental and decremental support vector machine[J].Machine Leafing,2001,(13):29-37.
[36]CHELLAPPA R,BAGDAZIAN R.Fourier coding of image boundaries[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1984,6(1):102-105.
[37]C.- C.Chang,C.-J.Lin.Libsvm:A library for support vector machines[R].Taibei.
[38]Cruz-Perez F.A,GHemandez-Valdez,Ortigoza-Guerrero L.Performance evaluation of mobile wireless communication systems with link adaptation[C].IEEE Communications Letters,Dec.2003,7(12):587589.
[39]TachiKawa K.A perspective on the evolution of mobile communications[C].IEEE Communications Magazine,Oct 2003,41(10):6673.
[40]Cheung N.K.Mobile communications for anything that moves[C].IEEE Communications Magazine,Oct 2003,41(10):64-64.
[41]Lain Bate,Steve Liu,Real-time Embedded Systems[J].Computing &Control Engineering Journal,2002,8.
[42]Bruce Powel Douglass,Real-Time Design Patterns[J],Embedded Systems Conference Papers,San Francisco,2001.
[43]Developer's Guide Motorola g20 Cellular Engine Module Description,2004.07.
[44]ROBERT Love.Linux Kernel Development[M].Indiana:SAMA,2003.
[45]BOVERT DP.CESATI M..Understanding the Linux kernel[M].O'REILLY,2000.9.
[46]Karim Yagbmour..Building Embedded Linux Systems[M].O'REILLY,2004.12.
[47]JONATHAN CORBET.,ALESSANDRO RUBINI.Linux Device Drivers[M].O'REILLY,2006.1.
[48]陈三宝.基于ARM芯片的嵌入式Linux智能通讯终端的设计[D].2005.6.
[49]Karim Yagbmour..Building Embedded Linux Systems[M].O'REILLY,2004.12.
[50]郑人杰,殷人昆,陶永雷.实用软件工程[M].北京:清华大学出版社,1996.
[51]A.A.Samjani.General Packet Radio Service[GPRS].IEEE Potentials,April-May.2002,21(2):1215.
[52]I.Goetz.Keeping up with GPRS[J].Communications Engineer,April/May 2003,1(2):4646.
[53]The Point-To-Point Protocol(PPP)by Simpson W RFC 1661,1994.
[54]黄梓锋,潘登,黄胜华.一种嵌入式系统的新型PPP连接方案[J].计算机工程,2003.29(16):175-177.
[55]Comin Light-williams,Joshua Drake,Linux PPP Howto.
[56]李建华,郭明.RS-232和调制解调器高级通信编程[M].北京:人民邮电出版社,2001.
[57]张明珊.基于GPRS网络的移动数据接入终端的研究与设计[D].2004.12.
[58]Hui Wang,Xiaofeng Liao and Chuandong Li.Existence and exponential stability of periodic solution of BAM nural networks with impulse and time varying delay.Chaos,Solitons & Fractals,2007,33(3)1028-1039.
[59]Richard Stevens,Bill Fenner,Andrew M.Rudoff.Unix Network Programming,Vol.1:The Sockets Networking API,Third Edition.2005
© 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 |