离线笔迹鉴别的特征提取技术研究
|
摘要
随着科学技术的发展,基于笔迹的身份鉴别方法已经成为重要生物特征识别手段之一,广泛应用于公安、司法、考古、金融、电子商务等领域。近年来,社会对计算机笔迹鉴别技术提出了新的要求。笔迹特征提取技术作为笔迹鉴别过程中的关键技术,直接影响鉴别效果。研究特征提取技术具有十分重要的理论意义和实用价值。
本文在对已有的笔迹特征提取方法进行详细研究的基础上,提出了将文本分块,并对各文本块提取重心特征、形状特征,最后结合文本整体的纹理特征进行笔迹鉴别的方法。其中重心特征提取的是各个笔迹块的重心,这些重心整体上反映了书写的笔迹相对于水平方向上的偏移,是一种与文本无关的笔迹特征。形状特征是在分析了几何矩物理性质的前提下提出的,通过将笔迹分块后提取笔迹块的形状信息作为特征。也是一种文本无关的笔迹特征,纹理特征反映了笔迹的纹理特性。它是通过对笔迹图像进行Gabor滤波获得的。这种特征完全摆脱了文本内容的限制,是一种被广泛使用的特征。
为了判别所提取笔迹特征的有效性,论文设计了一个简单的笔迹鉴别系统。这个系统包括预处理模块、重心特征提取与分类模块、形状特征提取与分类模块、纹理特征提取与分类模块,对各个识别结果进行综合的模块。通过这几个模块对所提出的特征提取方法进行了测试,结果表明:基于三种特征的鉴别方法都达到了良好的效果,而且三种方法的综合效果最佳。
With the development of science, writer identification (WI) based on handwriting has become an important technology of biometric personal identification. This technology has been widely used in the public security, administration of justice, archaeology, finance and electronic business areas. In recent years, social backgrounds urge more achievements in computer (WI). Features extraction is an important part of handwriting recognition, and has a direct impact on the recognition results. So researching on feature extraction technology has important theoretical significance and application value.
After detailed researching on the related technology of handwriting feature extraction, this thesis proposes to segment handwriting image to sub-image and extract the center of gravity features, shape features of each sub-image, then extract texture features for the whole image to realize handwriting identification, and at last to synthesize the results of each way to get the final result. In these ways the central of gravity features reflect handwriting gravity, it is the performance of writing habits and it is also a kind of text independent features. Shape features are proposed after analyzing the physical properties of geometric moments. These features are extracted from handwriting blocks, and it is also a text independent feature. Texture features reflect the texture characteristics of handwriting. These features are obtained by filtering image used Gabor filter. It is a kind of text independent features absolutely and it is used widely.
Finally in this thesis, I design a simple handwriting identification system for testing effectiveness of each feature The system includes pre-processing module, the central of gravity feature extraction and classification modules, shape features extraction and classification modules, texture features extraction and classification modules, also includes an integrated module for each recognition result. Each proposed method has been tested through these modules. Results showed that: the handwriting identification based on these three kinds' features achieves good results, and integrated result of each way can get better results.
本文在对已有的笔迹特征提取方法进行详细研究的基础上,提出了将文本分块,并对各文本块提取重心特征、形状特征,最后结合文本整体的纹理特征进行笔迹鉴别的方法。其中重心特征提取的是各个笔迹块的重心,这些重心整体上反映了书写的笔迹相对于水平方向上的偏移,是一种与文本无关的笔迹特征。形状特征是在分析了几何矩物理性质的前提下提出的,通过将笔迹分块后提取笔迹块的形状信息作为特征。也是一种文本无关的笔迹特征,纹理特征反映了笔迹的纹理特性。它是通过对笔迹图像进行Gabor滤波获得的。这种特征完全摆脱了文本内容的限制,是一种被广泛使用的特征。
为了判别所提取笔迹特征的有效性,论文设计了一个简单的笔迹鉴别系统。这个系统包括预处理模块、重心特征提取与分类模块、形状特征提取与分类模块、纹理特征提取与分类模块,对各个识别结果进行综合的模块。通过这几个模块对所提出的特征提取方法进行了测试,结果表明:基于三种特征的鉴别方法都达到了良好的效果,而且三种方法的综合效果最佳。
With the development of science, writer identification (WI) based on handwriting has become an important technology of biometric personal identification. This technology has been widely used in the public security, administration of justice, archaeology, finance and electronic business areas. In recent years, social backgrounds urge more achievements in computer (WI). Features extraction is an important part of handwriting recognition, and has a direct impact on the recognition results. So researching on feature extraction technology has important theoretical significance and application value.
After detailed researching on the related technology of handwriting feature extraction, this thesis proposes to segment handwriting image to sub-image and extract the center of gravity features, shape features of each sub-image, then extract texture features for the whole image to realize handwriting identification, and at last to synthesize the results of each way to get the final result. In these ways the central of gravity features reflect handwriting gravity, it is the performance of writing habits and it is also a kind of text independent features. Shape features are proposed after analyzing the physical properties of geometric moments. These features are extracted from handwriting blocks, and it is also a text independent feature. Texture features reflect the texture characteristics of handwriting. These features are obtained by filtering image used Gabor filter. It is a kind of text independent features absolutely and it is used widely.
Finally in this thesis, I design a simple handwriting identification system for testing effectiveness of each feature The system includes pre-processing module, the central of gravity feature extraction and classification modules, shape features extraction and classification modules, texture features extraction and classification modules, also includes an integrated module for each recognition result. Each proposed method has been tested through these modules. Results showed that: the handwriting identification based on these three kinds' features achieves good results, and integrated result of each way can get better results.
引文
[1]H.E.S.Said,et al.Personal identification based on handwriting.Pattern Recognition,33(2000):149-160P
[2]黄敏霁.离线手写体笔迹鉴别多分类器研究.福州:福州大学
[3]R.Plamondon,G.Lorrtte,Automatic signature verification and writer identification—the state of the art.Pattern Recognition,1989,37(12)
[4]边肇祺,张学工等.模式识别,北京:清华大学出版社,1999.9
[5]杨枝灵,王开等编著.数字图像获取、处理及实践应用.人民邮电出版社,2000
[6]V.lement.An application system for the Computer-assisted identification of handwritings.Int.arnahan Conf.on Security technology,1983:75-79P.
[7]Kuckuck.W,Writer Recognition by Spectral Analysis[J].Int Conf:Security through Sci and Engng,1980:5-11P
[8]S.Impcdovo.An off-line Writer Identification System Based on a Syntactic Approach[C].Proc 9th IWFHR,1990:53-61P
[9]杨子华,吴敏.基于纹理分析的笔迹识别系统.湖南工程学院学报,2004,14(2):67-69页
[10]黄雅平,罗四维,陈恩义.基于独立分量的笔迹识别.中文信息学报,2003,17(4)
[11]杨子华,吴敏等.基于灰度共生矩阵的笔迹识别.信息安全与通信密,2006
[12]Yong Zhu,Tieniu Tan and Yunhong Wang.Biometric Personal Identification Based on Handwriting.IEEE(2000):797-800P
[13]Stephane Mallat.A wavelet tour of signal processing(Second Edition).杨力华,戴道清,黄文泉等译.北京:机械工业出版社,2002:1-11页
[14]沈聪.基于改进多通道Gabor小波变换的笔迹鉴别.北京:北京工业大学
[15]Y.Zhu,T.Tan,Y.Wang,Iris Image Acquisition System.Chinese Patent Application,1999.No.99217063.X
[16]Liu Hong.Text-dependent Chinese writer identification using optimal Gabor filter.ACCV,2004
[17]文颖,龚裕,张宪荣.基于基本笔画运笔特征的汉字笔迹鉴定的研究.上海大学学报,2002.2
[18]吴赛,刘俊,张宪荣.基于基本笔画起收笔特征的手写汉字的笔迹鉴定,上海大学学报.2004.6
[19]刘成林,戴汝为,刘迎成.简化的Wigner分布及其在笔迹鉴别中的应用.计算机学报,20(11),1997:1018-1023页
[20]张慧档.笔迹鉴别方法研究.河南:郑州大学,2004
[21]章毓晋.图像分割.北京:科技出版社,2001.2
[22]刘成林.计算机笔迹鉴别理论与方法.北京:中国科学院自动化研究所,1995
[23]王文豪,严云洋.基于图像分块的LDA人脸识别.计算机工程与设计,2007:28(12)
[24]吴佑寿,丁晓青.汉字识别.北京:高等教育出版社,1992.7 198-211页
[25]姚敏等.数字图像处理.机械工业出版社,2006
[26]章毓晋.图像分割.北京:科技出版社,2001
[27]H Tamura,et al,Textural Features Corresponding to Visual Perception,IEEE Trans,1978,8(16):460-476P
[28]F Tomita,S Tsuji.Computer Analysis of Visual Textures,Kluwer Academic,1990:85-93P
[29]徐建华.图像处理与分析.北京:科学出版社;1992:173-204页
[30]M Tuceryan and A K Jain.Texture Analysis,in C.H.Chen et al(eds),Handbook of Pattern Recognition and Compute Vision,1993.235-276P
[31]Bing Feng et al.Chinese handwriting recognition using hidden Markov models.IEEE(2002):1051-4651P
[32]H.BUNKE.et al.Off-line cursive handwriting recognition using hidden markov models.Pattern Recognition,1995:1399-1413P
[33]Zhenyu He,et al.Writer identification of Chinese handwriting documents using hidden Markov tree model.Pattern Recognition,2008(41):1295-1307P
[34]郭晶,孙伟娟.小波分析理论与MATLAB7实现.北京:电子工业出版社,2005
[35]何震宇.中文笔迹鉴别软件研究与开发.武汉:武汉理工大学
[36]许春哗,郭宝兰.基于Gabor函数的汉字字体识别.河北大学学报(自然科学版),2001,21(2):167-190页
[37]Bovic A C,Clark M,Geisler W S.Multi-channel texture analysis using localized spatial filters.1EEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):55-73P
[38]朱勇,谭铁牛,王蕴红.基于笔迹的身份鉴别.自动化学报,2001
[39]Ⅱ-Seok Oh,Jin-Seon Lee,Ching Y.Suen.Analysis of class separation and combination of class-dependent features for handwriting recognition.IEEE Tro.on PAMI.1999,21(10),1089-1094P
[40]A.I.Koerich,R.Sabourin,C.Y.Large Vocabulary Off-line recognition:A survey.Pattern Anal Applic.2003,6:97-121P
[41]康耀红,数据融合及应用.西安:西安电子科技大学出版社,1997
[42]Cao J,Shridhar M,Ahmadi M.Handwritten Numeral Recognition with Neural Networks and Information fusion.Midwest Symposium on Circuits and System.1994:569-572P
[2]黄敏霁.离线手写体笔迹鉴别多分类器研究.福州:福州大学
[3]R.Plamondon,G.Lorrtte,Automatic signature verification and writer identification—the state of the art.Pattern Recognition,1989,37(12)
[4]边肇祺,张学工等.模式识别,北京:清华大学出版社,1999.9
[5]杨枝灵,王开等编著.数字图像获取、处理及实践应用.人民邮电出版社,2000
[6]V.lement.An application system for the Computer-assisted identification of handwritings.Int.arnahan Conf.on Security technology,1983:75-79P.
[7]Kuckuck.W,Writer Recognition by Spectral Analysis[J].Int Conf:Security through Sci and Engng,1980:5-11P
[8]S.Impcdovo.An off-line Writer Identification System Based on a Syntactic Approach[C].Proc 9th IWFHR,1990:53-61P
[9]杨子华,吴敏.基于纹理分析的笔迹识别系统.湖南工程学院学报,2004,14(2):67-69页
[10]黄雅平,罗四维,陈恩义.基于独立分量的笔迹识别.中文信息学报,2003,17(4)
[11]杨子华,吴敏等.基于灰度共生矩阵的笔迹识别.信息安全与通信密,2006
[12]Yong Zhu,Tieniu Tan and Yunhong Wang.Biometric Personal Identification Based on Handwriting.IEEE(2000):797-800P
[13]Stephane Mallat.A wavelet tour of signal processing(Second Edition).杨力华,戴道清,黄文泉等译.北京:机械工业出版社,2002:1-11页
[14]沈聪.基于改进多通道Gabor小波变换的笔迹鉴别.北京:北京工业大学
[15]Y.Zhu,T.Tan,Y.Wang,Iris Image Acquisition System.Chinese Patent Application,1999.No.99217063.X
[16]Liu Hong.Text-dependent Chinese writer identification using optimal Gabor filter.ACCV,2004
[17]文颖,龚裕,张宪荣.基于基本笔画运笔特征的汉字笔迹鉴定的研究.上海大学学报,2002.2
[18]吴赛,刘俊,张宪荣.基于基本笔画起收笔特征的手写汉字的笔迹鉴定,上海大学学报.2004.6
[19]刘成林,戴汝为,刘迎成.简化的Wigner分布及其在笔迹鉴别中的应用.计算机学报,20(11),1997:1018-1023页
[20]张慧档.笔迹鉴别方法研究.河南:郑州大学,2004
[21]章毓晋.图像分割.北京:科技出版社,2001.2
[22]刘成林.计算机笔迹鉴别理论与方法.北京:中国科学院自动化研究所,1995
[23]王文豪,严云洋.基于图像分块的LDA人脸识别.计算机工程与设计,2007:28(12)
[24]吴佑寿,丁晓青.汉字识别.北京:高等教育出版社,1992.7 198-211页
[25]姚敏等.数字图像处理.机械工业出版社,2006
[26]章毓晋.图像分割.北京:科技出版社,2001
[27]H Tamura,et al,Textural Features Corresponding to Visual Perception,IEEE Trans,1978,8(16):460-476P
[28]F Tomita,S Tsuji.Computer Analysis of Visual Textures,Kluwer Academic,1990:85-93P
[29]徐建华.图像处理与分析.北京:科学出版社;1992:173-204页
[30]M Tuceryan and A K Jain.Texture Analysis,in C.H.Chen et al(eds),Handbook of Pattern Recognition and Compute Vision,1993.235-276P
[31]Bing Feng et al.Chinese handwriting recognition using hidden Markov models.IEEE(2002):1051-4651P
[32]H.BUNKE.et al.Off-line cursive handwriting recognition using hidden markov models.Pattern Recognition,1995:1399-1413P
[33]Zhenyu He,et al.Writer identification of Chinese handwriting documents using hidden Markov tree model.Pattern Recognition,2008(41):1295-1307P
[34]郭晶,孙伟娟.小波分析理论与MATLAB7实现.北京:电子工业出版社,2005
[35]何震宇.中文笔迹鉴别软件研究与开发.武汉:武汉理工大学
[36]许春哗,郭宝兰.基于Gabor函数的汉字字体识别.河北大学学报(自然科学版),2001,21(2):167-190页
[37]Bovic A C,Clark M,Geisler W S.Multi-channel texture analysis using localized spatial filters.1EEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(1):55-73P
[38]朱勇,谭铁牛,王蕴红.基于笔迹的身份鉴别.自动化学报,2001
[39]Ⅱ-Seok Oh,Jin-Seon Lee,Ching Y.Suen.Analysis of class separation and combination of class-dependent features for handwriting recognition.IEEE Tro.on PAMI.1999,21(10),1089-1094P
[40]A.I.Koerich,R.Sabourin,C.Y.Large Vocabulary Off-line recognition:A survey.Pattern Anal Applic.2003,6:97-121P
[41]康耀红,数据融合及应用.西安:西安电子科技大学出版社,1997
[42]Cao J,Shridhar M,Ahmadi M.Handwritten Numeral Recognition with Neural Networks and Information fusion.Midwest Symposium on Circuits and System.1994:569-572P