维吾尔文笔迹鉴别关键技术研究
|
摘要
笔迹鉴别是依据手写笔迹对书写人身份进行判别的一门技术。随着计算机技术的发展,笔迹鉴别的重要性在当今的社会越来越明显。在工作中,各国政府之间的协议和备忘录的签订,官方文件,以及法令和法规的颁布,银行支票的签署汇兑,都需要当事人的亲笔签名才有效。在实际生活中,社会交往信函,则不管是手写还是打印,最终也是作者本人的亲笔签名。用计算机实现笔迹鉴别可以减轻文检人员的工作压力。笔迹鉴别已成为计算机视觉和模式识别领域研究的热点问题。
本文首先分析了笔迹鉴别的发展历史及应用背景,并介绍了目前的技术发展状况。以笔迹书写人身份鉴别问题为背景,研究基于改进型的多通道Gabor小波变换的笔迹鉴别问题,建立了基于该算法的笔迹身份鉴别系统。本文工作涉及:笔迹图像的预处理,笔迹图像的纹理特征提取,笔迹图像的分类匹配,以及基于改进型的多通道Gabor小波变换的笔迹鉴别系统的构造和实现。通过实验测试,系统准确率可以达到70%,基本完成了系统设计目标。系统编程平台为VS.net 2005。
本文取得的主要研究成果如下:
(1)在改进型Gabor小波变换算法的基础上进行实现方案上的改进,提出了适合维吾尔笔迹特征提取的纹理分析算法。该算法与笔迹所写内容无关,可记录下每一个通道的书写人笔迹风格的特征向量――均值和方差,它们记录下了每个通道笔迹图像纹理特征的重要信息。
(2)采用最近邻距离和对笔迹样本进行分类匹配,将训练后的32通道64维特征向量以纯文本格式保存于相应的笔迹库中。其优点为数据存储量小、便于管理,辨别速度快。
The handwriting identification is a kind of technology used to identify the figure of a person’s. With the development computer technology, the importance of handwriting identification is becoming clearer and clearer in today's society. The agreements and memorandum between the governments signed, the official documents, laws and regulations, bank checks signed and exchanged are all effective by the autographed from both parties. In real life, the social despondence letters must be signed by the author himself, no matter it was written or printed. Using the computer to identify the autograph can reduce the pressure of the staffs’. It also becomes a key problem in the computer vision methodology and pattern recognition.
This paper firstly analyzed the history of development and the application background of handwriting identification, and introduced the current condition of it. This paper considered the reorganization of writer’s identity as the background, the research based on the problem of improving the multi-channel Gabor wavelet transform, handwriting identification based on improve the multi-channel Gabor wavelet transform , established the writing identification system of its own algorithm. This study involved handwriting image preprocessing, texture feature extraction of the handwriting image, handwriting image classification and match, and the construction and achievement of the improved handwriting identification systems with the multi-channel Gabor wavelet. The experiment showed the rate of correctness is 70%, which achieved the goal of the system design. The system is accomplished in VS.net 2005.
The results of this paper are as follows:
(1) On the improvement of the Gabor wavelet transform, it presented the suitable texture analysis feature extraction algorithms in the Xinjiang Uygur handwriting. This arithmetic is a text independent method, which can record the mean and standard deviation of each channel. These are the important information of the textural characters.
(2)This paper also designed the classification of the handwriting image, using nearest neighbor classifier to fulfill the identification task. Its advantages are small memory of data storage, manageable and fast identification.
本文首先分析了笔迹鉴别的发展历史及应用背景,并介绍了目前的技术发展状况。以笔迹书写人身份鉴别问题为背景,研究基于改进型的多通道Gabor小波变换的笔迹鉴别问题,建立了基于该算法的笔迹身份鉴别系统。本文工作涉及:笔迹图像的预处理,笔迹图像的纹理特征提取,笔迹图像的分类匹配,以及基于改进型的多通道Gabor小波变换的笔迹鉴别系统的构造和实现。通过实验测试,系统准确率可以达到70%,基本完成了系统设计目标。系统编程平台为VS.net 2005。
本文取得的主要研究成果如下:
(1)在改进型Gabor小波变换算法的基础上进行实现方案上的改进,提出了适合维吾尔笔迹特征提取的纹理分析算法。该算法与笔迹所写内容无关,可记录下每一个通道的书写人笔迹风格的特征向量――均值和方差,它们记录下了每个通道笔迹图像纹理特征的重要信息。
(2)采用最近邻距离和对笔迹样本进行分类匹配,将训练后的32通道64维特征向量以纯文本格式保存于相应的笔迹库中。其优点为数据存储量小、便于管理,辨别速度快。
The handwriting identification is a kind of technology used to identify the figure of a person’s. With the development computer technology, the importance of handwriting identification is becoming clearer and clearer in today's society. The agreements and memorandum between the governments signed, the official documents, laws and regulations, bank checks signed and exchanged are all effective by the autographed from both parties. In real life, the social despondence letters must be signed by the author himself, no matter it was written or printed. Using the computer to identify the autograph can reduce the pressure of the staffs’. It also becomes a key problem in the computer vision methodology and pattern recognition.
This paper firstly analyzed the history of development and the application background of handwriting identification, and introduced the current condition of it. This paper considered the reorganization of writer’s identity as the background, the research based on the problem of improving the multi-channel Gabor wavelet transform, handwriting identification based on improve the multi-channel Gabor wavelet transform , established the writing identification system of its own algorithm. This study involved handwriting image preprocessing, texture feature extraction of the handwriting image, handwriting image classification and match, and the construction and achievement of the improved handwriting identification systems with the multi-channel Gabor wavelet. The experiment showed the rate of correctness is 70%, which achieved the goal of the system design. The system is accomplished in VS.net 2005.
The results of this paper are as follows:
(1) On the improvement of the Gabor wavelet transform, it presented the suitable texture analysis feature extraction algorithms in the Xinjiang Uygur handwriting. This arithmetic is a text independent method, which can record the mean and standard deviation of each channel. These are the important information of the textural characters.
(2)This paper also designed the classification of the handwriting image, using nearest neighbor classifier to fulfill the identification task. Its advantages are small memory of data storage, manageable and fast identification.
引文
[1] Plamond R, Lorette G. Automatic signature verification and writer identification the state of art [J]. Pattern Recognition, 1989, 22(2):107-131.
[2] Willliam K Prratt.邓鲁华,张延恒,等译.数字图像处理[M].北京:机械工业出版社,2005.
[3]边肇祺,张学工.模式识别[M].北京:清华大学出版社,2000:1-10.
[4] Klement V. An application system for the computer-assisted identification of handwritings[C]. In: Int Carnahan Conf on Security Technology, 1983:75-79.
[5] Naske R D. Writer recognition by prototype related deformation of handprinted characters[C]. In:Proc 6th ICPR, 1982:819-822.
[6]刘成林,戴汝为,刘迎建.基于多通道分解与匹配的笔迹鉴别研究[J].自动化学报,1997, 23(1):57-63.
[7]刘成林,戴汝为,刘迎建.简化的Wigner分布及其在笔迹鉴别中的应用[J].计算机学报,1997,20(11):1018-1923.
[8] Said H E S, Tan T N, Baker K D.Personal identification based on handwriting[J].Pattern Recognition,2000,33(1):149-160.
[9] Zhu Yong,Tan Tieniu,Wang Yunhong.Biometric personal identification based on handwriting[C]. In:ICPR2000, the 15th International Conference on Pattern Recognition. Barcelona, Spain, 2000. 801-804.
[10] Amit Jain, Aditya Kamat. Personal identification based on handwriting[D].2000.
[11] G. S. Peake and T. N. Tan, Script and Language Identification from Document Image, Proc. BMVC97, vo1.2, 1997, pp.169-184, Essex, UK.
[12]陈书海,傅录祥.实用数字图像处理[M].北京:科学出版社,2005:149-278.
[13] Duvernoy J. Handwriting synthesis and classification by means of space-variant transform and Karhunen-Loeve analysis[J]. Journal of Opt Soc Am, 1975, 65:1331-1336.
[14] J.G. Daugman, Uncertainty Relation for Resolution in Space, Spatial Frequency, and Orientation Optimized by Two-dimensional visual Cortical Filters, J. Opt. Soc. Am. A, 2(7), 1985:1160-1169.
[15] de Valois K K. Spatial Vision[R].Annual Review of Physiology, 1984.
[16] Compbell F W, Robson J G. Application of Fourier analysis to the visibility of gratings[J]. Journal of Physiology, 1968, 197:551-556.
[17]四维科技,胡小峰,赵辉.Visual C++/MATLAB图像处理与识别实用案例精选[M].北京:人民邮电出版社,2004:344-350.
[18] Richard O.Duda, Peter E.Hart, David G.Stock,李宏东,姚天翔译.Pattern Classification, second edition.北京:机械工业出版社,2004:155-236.
[19]孙广萍.身份验证中的签名鉴别技术.黑龙江通信技术,2003,1:34-35.
[20]赵永健,李永勃.基于小波变换的汉字签名鉴别.计算机工程,2003,29(2):243-245.
[21] Xuewen Wang,Xiaoqing Ding,Changsong Liu.Gabor filters-based feature extraction for character recognition.Pattern Recognition,2005,38(1):369-379.
[22]万莉,芦苇,尹朝庆.基于BP神经网络的手写签名识别方法.交通与计算机,2006,24(4):83-85.
[23] P.M.Lallican,C.Viard-Gaudin.Off-line handwriting modeling as a trajectory problem,in:Advances in Handwriting Recognition,Series in Machine Perception and Artificial Intelligence,Vol. 34,World Scientific,Singapore,1999:449-458.
[24]何斌,马天宇等.Visual C++数字图像处理(第二版).北京:人民邮电出版社,2002:1-255.
[25]刘宏,李锦涛.基于SVM和纹理的笔迹鉴别方法[J].计算机辅助设计与图形学学报. 2003,15(12):1479-1484.
[26]王凤岭,刘连芳,蒋宗礼,高伟锋.离线手写体笔迹鉴别方法研究.计算机工程与设计2006.27(14):2581-2584.
[27]朱学芳.手写数字识别实验系统的研究[D].南京大学学报,1996,32(1):36-42.
[28]邹伟.高精度手写体数字识别的算法研究及应用[D].北京邮电大学,2001.
[29]瞿海金.手写体数字识别方法的研究与实现[D].南京理工大学,2005.
[30]张世辉.汉字图像预处理算法的研究和实现[J].微机发展,2003,13(4).
[31] H. E. S. Said, T. N. Tan and K. D. Baker, Writer Identification Based on Handwriting, IEE Third European Workshop on Handwriting Analysis and Recognition, July,1998,p.4/1-6.
[32]田玉敏,乃尚学,高有行等.基于整数小波系数的纹理图像检索方法研究.西安电子科技大学学报(自然科学版) [J].2003,30(1):90-93.
[33]朱勇,谭铁牛,王蕴红.基于笔迹的身份鉴别[J].自动化学报,2001,27:229-234.
[34]公安部文件检验教材[M].沈阳:沈阳出版社,1985:6-13.
[35]于明,苗晓峰,范书瑞.基于纹理的文本依存的离线笔迹鉴别[J].河北工业大学学报.2007,36(5):95-100.
[36] [易东,陈庆虎.基于多分类器组合的笔迹验证[J].计算机应用,2006,26(1):172-173.
[37]王凤岭,韦智勇,刘连芳.基于纹理分析笔迹鉴别系统的设计与实现[J].广西民族大学学报(自然科学版).2007,13(3):97-103.
[38]万峰,杜明辉.小样本条件下采用Gabor特征的人脸识别[J].计算机辅助设计与图形学学报.2005,17(2):197-201.
[39]张慧档,贺昱曜.基于小波变换和神经网络集成的笔迹鉴别方法[J].计算机应用研究.2008,25(3):741-743.
[40]张德贤,郭小波,刘永平.笔迹鉴别预处理与特征抽取技术研究[J].《微计算机信息》(测控自动化).2006,22(9-1):310-312.
[41]沈聪.基于改进的多通道Gabor小波变换的笔迹鉴别[D].北京:北京工业大学, 2002.
[2] Willliam K Prratt.邓鲁华,张延恒,等译.数字图像处理[M].北京:机械工业出版社,2005.
[3]边肇祺,张学工.模式识别[M].北京:清华大学出版社,2000:1-10.
[4] Klement V. An application system for the computer-assisted identification of handwritings[C]. In: Int Carnahan Conf on Security Technology, 1983:75-79.
[5] Naske R D. Writer recognition by prototype related deformation of handprinted characters[C]. In:Proc 6th ICPR, 1982:819-822.
[6]刘成林,戴汝为,刘迎建.基于多通道分解与匹配的笔迹鉴别研究[J].自动化学报,1997, 23(1):57-63.
[7]刘成林,戴汝为,刘迎建.简化的Wigner分布及其在笔迹鉴别中的应用[J].计算机学报,1997,20(11):1018-1923.
[8] Said H E S, Tan T N, Baker K D.Personal identification based on handwriting[J].Pattern Recognition,2000,33(1):149-160.
[9] Zhu Yong,Tan Tieniu,Wang Yunhong.Biometric personal identification based on handwriting[C]. In:ICPR2000, the 15th International Conference on Pattern Recognition. Barcelona, Spain, 2000. 801-804.
[10] Amit Jain, Aditya Kamat. Personal identification based on handwriting[D].2000.
[11] G. S. Peake and T. N. Tan, Script and Language Identification from Document Image, Proc. BMVC97, vo1.2, 1997, pp.169-184, Essex, UK.
[12]陈书海,傅录祥.实用数字图像处理[M].北京:科学出版社,2005:149-278.
[13] Duvernoy J. Handwriting synthesis and classification by means of space-variant transform and Karhunen-Loeve analysis[J]. Journal of Opt Soc Am, 1975, 65:1331-1336.
[14] J.G. Daugman, Uncertainty Relation for Resolution in Space, Spatial Frequency, and Orientation Optimized by Two-dimensional visual Cortical Filters, J. Opt. Soc. Am. A, 2(7), 1985:1160-1169.
[15] de Valois K K. Spatial Vision[R].Annual Review of Physiology, 1984.
[16] Compbell F W, Robson J G. Application of Fourier analysis to the visibility of gratings[J]. Journal of Physiology, 1968, 197:551-556.
[17]四维科技,胡小峰,赵辉.Visual C++/MATLAB图像处理与识别实用案例精选[M].北京:人民邮电出版社,2004:344-350.
[18] Richard O.Duda, Peter E.Hart, David G.Stock,李宏东,姚天翔译.Pattern Classification, second edition.北京:机械工业出版社,2004:155-236.
[19]孙广萍.身份验证中的签名鉴别技术.黑龙江通信技术,2003,1:34-35.
[20]赵永健,李永勃.基于小波变换的汉字签名鉴别.计算机工程,2003,29(2):243-245.
[21] Xuewen Wang,Xiaoqing Ding,Changsong Liu.Gabor filters-based feature extraction for character recognition.Pattern Recognition,2005,38(1):369-379.
[22]万莉,芦苇,尹朝庆.基于BP神经网络的手写签名识别方法.交通与计算机,2006,24(4):83-85.
[23] P.M.Lallican,C.Viard-Gaudin.Off-line handwriting modeling as a trajectory problem,in:Advances in Handwriting Recognition,Series in Machine Perception and Artificial Intelligence,Vol. 34,World Scientific,Singapore,1999:449-458.
[24]何斌,马天宇等.Visual C++数字图像处理(第二版).北京:人民邮电出版社,2002:1-255.
[25]刘宏,李锦涛.基于SVM和纹理的笔迹鉴别方法[J].计算机辅助设计与图形学学报. 2003,15(12):1479-1484.
[26]王凤岭,刘连芳,蒋宗礼,高伟锋.离线手写体笔迹鉴别方法研究.计算机工程与设计2006.27(14):2581-2584.
[27]朱学芳.手写数字识别实验系统的研究[D].南京大学学报,1996,32(1):36-42.
[28]邹伟.高精度手写体数字识别的算法研究及应用[D].北京邮电大学,2001.
[29]瞿海金.手写体数字识别方法的研究与实现[D].南京理工大学,2005.
[30]张世辉.汉字图像预处理算法的研究和实现[J].微机发展,2003,13(4).
[31] H. E. S. Said, T. N. Tan and K. D. Baker, Writer Identification Based on Handwriting, IEE Third European Workshop on Handwriting Analysis and Recognition, July,1998,p.4/1-6.
[32]田玉敏,乃尚学,高有行等.基于整数小波系数的纹理图像检索方法研究.西安电子科技大学学报(自然科学版) [J].2003,30(1):90-93.
[33]朱勇,谭铁牛,王蕴红.基于笔迹的身份鉴别[J].自动化学报,2001,27:229-234.
[34]公安部文件检验教材[M].沈阳:沈阳出版社,1985:6-13.
[35]于明,苗晓峰,范书瑞.基于纹理的文本依存的离线笔迹鉴别[J].河北工业大学学报.2007,36(5):95-100.
[36] [易东,陈庆虎.基于多分类器组合的笔迹验证[J].计算机应用,2006,26(1):172-173.
[37]王凤岭,韦智勇,刘连芳.基于纹理分析笔迹鉴别系统的设计与实现[J].广西民族大学学报(自然科学版).2007,13(3):97-103.
[38]万峰,杜明辉.小样本条件下采用Gabor特征的人脸识别[J].计算机辅助设计与图形学学报.2005,17(2):197-201.
[39]张慧档,贺昱曜.基于小波变换和神经网络集成的笔迹鉴别方法[J].计算机应用研究.2008,25(3):741-743.
[40]张德贤,郭小波,刘永平.笔迹鉴别预处理与特征抽取技术研究[J].《微计算机信息》(测控自动化).2006,22(9-1):310-312.
[41]沈聪.基于改进的多通道Gabor小波变换的笔迹鉴别[D].北京:北京工业大学, 2002.