票据自动处理系统中若干关键技术研究
|
摘要
随着我国经济的迅速发展以及全国票据交换系统的推广,使得金融票据凭证的使用量呈现了跨越式增长。现今我国的信息化已经进入全方位、多层次推进的新阶段,信息化也从对银行发展的“支持”阶段走向“支撑”阶段,由经济全球化带来的行业竞争不断加剧,国内金融业对票据自动化处理系统的需求也渐大,票据自动处理系统的市场前景十分广阔。
票据自动处理系统以实现自动的票据输入与复核为目标,覆盖了从前端信息录入到后端事后监督的主要部分:直接从票据凭证影像中提取要素数据(如凭证号,账号,日期,金额,磁码等),在后台进行OCR流水识别,自动建立凭证索引,以便于支票图像存档检索;与银行事后监督系统相结合,生成待监督数据文件,通过与流水识别取得的业务系统中临柜帐务数据进行核对,替代操作人员完成事后监督工作;配有印章验证系统后,自动将凭证图像中的客户印章与系统中预留的印鉴进行比较,完成印章的真伪识别,提升银行业务处理效率。
作为票据自动化处理过程中不可或缺的核心技术,票据OCR系统主要根据票据影像,来完成种类和主附件关系的判定,以及票据要素的自动提取以及识别,并将数据提供给后续的相关业务使用。在学科上票据OCR识别属于模式识别和人工智能的范畴,不仅对银行业有非常大的实用价值,而且容易在其他领域中得到转化应用,在国内外保险、海关、税务、教育、邮政、医务、政府行政管理等领域都有着广泛的应用前景。
票据自动处理系统实际应用的关键在于,确保票据各识别域识别结果的高可靠性。本文对票据自动处理系统的各个模块进行相应的分析,对票据自动识别中的若干关键技术进行了深入的研究,并给出了相应的实现方案。主要研究工作可归纳为以下三部分:
(一)在版面分析中,首先根据票据中框线目标的特点,提出了一种有效的框线检测与提取算法;其次,基于框线提取,采用基于框线相关性的相似度模型来计算票据框线间的相似度,提出了由粗到细的多类别票据版面判定的方法。在真实数据集上的试验结果表明了该算法的有效性。
(二)预处理中,根据票据图像的特点1)通过综合字符笔画双边缘特征与背景抑制增强,来提取复杂背景下识别域子图中的字符目标;2)采用连通链结构来描述框线检测结果与字符目标提取结果融合后的框线区域,通过对交叠进行检测和标记,来判别字符与框线的交叠方式,并据此保留字符笔画去除框线干扰,还原待识别字串真实的面貌;3)结合轮廓分析与拓扑结构分析,来确定粘连数字串的分割策略,对无限制手写数字字符串进行有效的切分。最后采用视觉效果评判和基于字符识别的同类算法对比实验的评价方式,结果证实了提出的算法更为有效。
(三)在手写体数字字符识别中,分别从构建代表训练样本集和组合分类器与特征的角度出发,对手写体数字识别进行了研究,提出了基于AP与LDA的手写阿拉伯数字识别算法,及组合结构特征和统计特征的手写数字识别算法。所提算法在仿真数据集以及现实应用中都取得了比较好的效果。
本文最后简要介绍了票据自动识别子系统在银行票据后督系统和支票影像交换系统行内系统中的应用实例,均已在实际中得到应用,取得了良好的效果。
Nowadays, the informatization course of our country has been stepped into a new phase, which is more significant for the development of commercial banks. The amount of financial document has been risen greatly because of not only the domestic active financial market stimulated by the increasing costumer requirements but also the global business extending of these banks. The amount of these kinds of documents increases so rapidly that they are becoming not tractable. This urgent situations demand for efficient and effective automatic financial document processing systems..
A typical automatic financial document processing system always consists of front end cheque processing system and background subsequent supervision system. When a bank note is inputted into a cheque processing system, the elements of the bank note such as the check number, account, date and value will be extracted, processed and recognized automatically by image processing and OCR techniques. Then, these information will be send to the subsequent supervision system. Some unique elements will be treated as the index of this bank note, which will help to search and store those images. The subsequent supervision system will store these information and verify the correctness of the information by comparing them with the information provided by the core business system. For those cheques with seals, the seal recognition system will verify the validity of the seal by comparing with the corresponding valid seal existed in the seal base of the bank. All the procedures are done automatically by intelligent systems, so the valuable human resources are saved and the efficiencies of the business processing are greatly increased.
As the most important component of the automatic financial document processing system, the bank document OCR system first performs the layout analysis and document classification tasks, and then extracts and recognizes the business elements automatically for further processing. It is a comprehensive system involving image processing, document analysis, form processing, feature extraction, classification and many other intelligence technologies. It is a typical application of Pattern Recognition and Artificial Intelligence techniques. The system is valuable not only for bank businesses, but also for document processing tasks in many other areas such as insurance、CIQ、revenue、education、post、hospital and government.
The key point of a successful financial document automatic processing system is to keep good recognition rate with high reliability and robustness when confront different situations. To accomplish this purpose, this dissertation studies several pivotal problems in the system and gives corresponding practical resolution. The contributions of the dissertation can be concluded in three aspect(?).
1. To improve the performance of layout analysis, we first introduce an accurate frame line detection algorithm on the basis of the characteristic of form document image. Secondly, a frame-line based classification method is proposed to identify financial documents in different categories. In the method, the matching degree between sample and bill templates is done through a new correlative matching model.The experimental results show the effectiveness of this algorithm.
2. In the area of image preprocessing, three new algorithms are proposed: 1) A binary algorithm based on the MDE characteristic of strokes and the enhancement of the background restraint is proposed to overcome the difficulties of character extracting in complicated background derived mainly from the seal imprint with different types and positions, which are often dark and stroke-like. 2) An improved frame line removal algorithm is introduced. First, after the line detection procedure, chain code method is applied to describe the detected frame line region in gray images. Then, cross-points of characters and lines are detected, analyzed and marked by its overlapping types. Finally, frame lines are removed with the marks of cross-points. 3) A new segmentation strategy of unrestricted handwritten digits is realized by integrating the information obtained from profile analysis with topology structure analysis. The experimental results demonstrate the superiority over some other algorithms.
3. In order to improve the performance of handwritten digit recognition, two methods with different emphases are proposed: 1) an algorithm that fuse the structural feature and statistical feature is proposed to make good use of the complementary information of these two different features and enhance the recognition rate remarkably; 2) another method that combines LDA(linear discriminant analysis ) methods with AP( affinity propagation) clustering method is proposed, which not only avoids the disturbance of noise in the training set, but also improves the recognition efficiency. The two proposeed algorithm work well on both simulation data sets and real-world applications.
Finally, we present two application instances of our system in the bank subsequent supervision system and the sub-system of CIS (the national Cheque Image System). The application results on real financial bill images illustrate the validity and practicability of our system.
票据自动处理系统以实现自动的票据输入与复核为目标,覆盖了从前端信息录入到后端事后监督的主要部分:直接从票据凭证影像中提取要素数据(如凭证号,账号,日期,金额,磁码等),在后台进行OCR流水识别,自动建立凭证索引,以便于支票图像存档检索;与银行事后监督系统相结合,生成待监督数据文件,通过与流水识别取得的业务系统中临柜帐务数据进行核对,替代操作人员完成事后监督工作;配有印章验证系统后,自动将凭证图像中的客户印章与系统中预留的印鉴进行比较,完成印章的真伪识别,提升银行业务处理效率。
作为票据自动化处理过程中不可或缺的核心技术,票据OCR系统主要根据票据影像,来完成种类和主附件关系的判定,以及票据要素的自动提取以及识别,并将数据提供给后续的相关业务使用。在学科上票据OCR识别属于模式识别和人工智能的范畴,不仅对银行业有非常大的实用价值,而且容易在其他领域中得到转化应用,在国内外保险、海关、税务、教育、邮政、医务、政府行政管理等领域都有着广泛的应用前景。
票据自动处理系统实际应用的关键在于,确保票据各识别域识别结果的高可靠性。本文对票据自动处理系统的各个模块进行相应的分析,对票据自动识别中的若干关键技术进行了深入的研究,并给出了相应的实现方案。主要研究工作可归纳为以下三部分:
(一)在版面分析中,首先根据票据中框线目标的特点,提出了一种有效的框线检测与提取算法;其次,基于框线提取,采用基于框线相关性的相似度模型来计算票据框线间的相似度,提出了由粗到细的多类别票据版面判定的方法。在真实数据集上的试验结果表明了该算法的有效性。
(二)预处理中,根据票据图像的特点1)通过综合字符笔画双边缘特征与背景抑制增强,来提取复杂背景下识别域子图中的字符目标;2)采用连通链结构来描述框线检测结果与字符目标提取结果融合后的框线区域,通过对交叠进行检测和标记,来判别字符与框线的交叠方式,并据此保留字符笔画去除框线干扰,还原待识别字串真实的面貌;3)结合轮廓分析与拓扑结构分析,来确定粘连数字串的分割策略,对无限制手写数字字符串进行有效的切分。最后采用视觉效果评判和基于字符识别的同类算法对比实验的评价方式,结果证实了提出的算法更为有效。
(三)在手写体数字字符识别中,分别从构建代表训练样本集和组合分类器与特征的角度出发,对手写体数字识别进行了研究,提出了基于AP与LDA的手写阿拉伯数字识别算法,及组合结构特征和统计特征的手写数字识别算法。所提算法在仿真数据集以及现实应用中都取得了比较好的效果。
本文最后简要介绍了票据自动识别子系统在银行票据后督系统和支票影像交换系统行内系统中的应用实例,均已在实际中得到应用,取得了良好的效果。
Nowadays, the informatization course of our country has been stepped into a new phase, which is more significant for the development of commercial banks. The amount of financial document has been risen greatly because of not only the domestic active financial market stimulated by the increasing costumer requirements but also the global business extending of these banks. The amount of these kinds of documents increases so rapidly that they are becoming not tractable. This urgent situations demand for efficient and effective automatic financial document processing systems..
A typical automatic financial document processing system always consists of front end cheque processing system and background subsequent supervision system. When a bank note is inputted into a cheque processing system, the elements of the bank note such as the check number, account, date and value will be extracted, processed and recognized automatically by image processing and OCR techniques. Then, these information will be send to the subsequent supervision system. Some unique elements will be treated as the index of this bank note, which will help to search and store those images. The subsequent supervision system will store these information and verify the correctness of the information by comparing them with the information provided by the core business system. For those cheques with seals, the seal recognition system will verify the validity of the seal by comparing with the corresponding valid seal existed in the seal base of the bank. All the procedures are done automatically by intelligent systems, so the valuable human resources are saved and the efficiencies of the business processing are greatly increased.
As the most important component of the automatic financial document processing system, the bank document OCR system first performs the layout analysis and document classification tasks, and then extracts and recognizes the business elements automatically for further processing. It is a comprehensive system involving image processing, document analysis, form processing, feature extraction, classification and many other intelligence technologies. It is a typical application of Pattern Recognition and Artificial Intelligence techniques. The system is valuable not only for bank businesses, but also for document processing tasks in many other areas such as insurance、CIQ、revenue、education、post、hospital and government.
The key point of a successful financial document automatic processing system is to keep good recognition rate with high reliability and robustness when confront different situations. To accomplish this purpose, this dissertation studies several pivotal problems in the system and gives corresponding practical resolution. The contributions of the dissertation can be concluded in three aspect(?).
1. To improve the performance of layout analysis, we first introduce an accurate frame line detection algorithm on the basis of the characteristic of form document image. Secondly, a frame-line based classification method is proposed to identify financial documents in different categories. In the method, the matching degree between sample and bill templates is done through a new correlative matching model.The experimental results show the effectiveness of this algorithm.
2. In the area of image preprocessing, three new algorithms are proposed: 1) A binary algorithm based on the MDE characteristic of strokes and the enhancement of the background restraint is proposed to overcome the difficulties of character extracting in complicated background derived mainly from the seal imprint with different types and positions, which are often dark and stroke-like. 2) An improved frame line removal algorithm is introduced. First, after the line detection procedure, chain code method is applied to describe the detected frame line region in gray images. Then, cross-points of characters and lines are detected, analyzed and marked by its overlapping types. Finally, frame lines are removed with the marks of cross-points. 3) A new segmentation strategy of unrestricted handwritten digits is realized by integrating the information obtained from profile analysis with topology structure analysis. The experimental results demonstrate the superiority over some other algorithms.
3. In order to improve the performance of handwritten digit recognition, two methods with different emphases are proposed: 1) an algorithm that fuse the structural feature and statistical feature is proposed to make good use of the complementary information of these two different features and enhance the recognition rate remarkably; 2) another method that combines LDA(linear discriminant analysis ) methods with AP( affinity propagation) clustering method is proposed, which not only avoids the disturbance of noise in the training set, but also improves the recognition efficiency. The two proposeed algorithm work well on both simulation data sets and real-world applications.
Finally, we present two application instances of our system in the bank subsequent supervision system and the sub-system of CIS (the national Cheque Image System). The application results on real financial bill images illustrate the validity and practicability of our system.
引文
[1]Mori S.,Suen C.Y.,Yamamoto K..Historical Review of OCR Research and Development[C].Proc.IEEE.1992,80(7):1029-1058
[2]赵斌.基于支持向量机的金融票据识别系统研究[D].北京:清华大学,2000
[3]Cheng-Lin Liu,Kazuki Nakashima,Hiroshi Sako,Hiromichi Fujisawa.Handwritten digit recognition:investigation of normalization and feature extraction techniques[J],Pattern Recognition.2004,37(2):265-279
[4]张重阳.票据自动处理系统中的预处理技术研究[D].南京:南京理工大学,2004
[5]Wang Song,Ma Feng,Xia Shaowei.A fault tolerant Chinese bank check recognition system based on SOM neural networks[C].ICNN97 Pattern Recognition and Image Processing Session,Houston USA,1997,4:2560-2565
[6]陈强,杨静宇,娄震.基于模板匹配和差影处理的票据图像检测[J].计算机工程与应用,2004,40(26):207-219
[7]李琥,卜佳俊,陈纯.一种新的基于特征线选取的票据识别算法[J].浙江大学学报,2003,37(2):173-177
[8]N.Otsu.A threshold selection method from grey-level histograms.IEEE Trans.on Systems Man Cybernetics.1979,9:62-66
[9]邓雁萍,李介谷.图像分割的性能评估[J].模式识别与人工智能.1996,9(2):144-148
[10]罗希平,田捷,诸葛婴,王靖,戴汝为.图像分割方法综述[J].模式识别与人工智能.1999,12(3):300-312
[11]N.B.Venkateswarlu.Implementation of some image thresholding algorithms on a connection machine-200[J].Pattern Recognition Letters,1995,16(7):759-768
[12]Cheriet M.,Said J.N.,Suen C.Y..A recursive thresholding technique for image segmentation.IEEE Trans.On Image Processing,1998,7(6):918-921
[13]Liu Y.,Srihari S.N..Document Image Binarization Based on Texture Features.IEEE Trans.Pattern Analysis and Machine Intelligence,1997,19(5):540-544
[14]Palumbo P.W.,Swaminathan P.,Srihari S.N..Document Image Binarization:Evaluation of Algorithms.In:Proc.SPIE,1986,697:278-285
[15]Parker J.R..Gray level thresholding in badly illuminated images.IEEE Trans.Pattern Analysis and Machine Intelligence.1991,13(8):813-819
[16]M.Kamel,A.Zhao.Extraction of binary character/graphics images from grayscale document images.CVGIP:Graphical Models and Image Processing,1993,55(3):203-217
[17]Q.D.Trier,A.K.Jain.Goal-directed evaluation of binarization methods.IEEE Trans.Pattern Analysis and Machine Intelligence.1995,7(12):1191-1201.
[18]Q.D.Trier,A.K.Jain.Evaluation of binarization methods for document images.IEEE Trans.Pattern Analysis and Machine Intelligence.1995,17(3):312-314
[19]J.Bernsen.Dynamic thresholding of gray-level images.Proc.Int.Conf.Pattern Recognition.LOS Angeles,1986(2):1251-1255
[20]J.Ohya,A.Shio,and S.Akamatsu.Recognizing characters in scene images.IEEE Trans.Pattern Analysis and Machine Intelligence.1994,16(2):214-220.
[21]L.Wang,T.Pavlidis.Direct gray-scale extraction of features for character recognition.IEEE Trans.Pattern Analysis and Machine Intelligence.1993,15(10):1053-1067.
[22]M.Cheriet.Extraction of handwritten data from noisy gray-level images using a multi-scale approach.In:Proc.Vision Interface,1998,1:389-396
[23]S.Djeziri,F.Nouboud,R.Plamondon.Extraction of signatures from check background based on a filiformity criterion.IEEE Trans.Image Processing.1998,7(10):1425-1438
[24]Xiangyun Ye,Mohamed Cheriet,Ching Y.Suen,Stroke-Model-Based Character Extraction from Gray-Level Document Images,IEEE Trans.Image Processing,2001(10):1152-1161
[25]Bin Yu,Ani K Jain,A generic system for form dropout[J].IEEE Trans on PAMI,1996,18(11):1127-1134
[26]刘长松,潘世言,郑冶枫,等.一种表格框线检测和字线分离算法[J].电子与信息学报,2002,24(9),1190-1196
[27]Xiangyun Ye,Mohamed Cheriet,Ching Y Suen.A generic method of cleaning and enhancing handwritten data from business forms[J].Journal of Doctor Analects Recognition,2001,4(2):84-96
[28]Jain-Shiue Chen,Din-Chang Tseng.Overlapped-character separation and reconstruction for table-form documents[C].In:Proc Int'l Conf on Image Processing,Lausanne,Switzerland,1996.233-236
[29]Yi-Hong Tseng,His-Jian Lee.Interfered-character recognition by removing interfering-lines and adjusting feature weights[C].In:The 14th Int'l Conf on pattern Recognition,Brisbane,Qld,Austrialia,1998.1865-1867
[30]胡钟山,娄震,杨静宇,等.文档处理中消除线噪声的研究[J].计算机研究与发展,1999,36(8):992-995
[31]郑冶枫,刘长松,丁晓青.线宽阈值法去除表格框线[J].模式识别与人工智能, 2001,14(2):206-210
[32]张重阳,陈强,娄震,杨静宇.基于灰度图像的表格框线去除算法[J].计算机研究与发展,2005,42(4):635-639
[33]Mark C K Yang,etal.Hough Transform Modified by Line Connectively and Line Thickness[J].IEEE Trans on PAMI,1997,19(8):905-910
[34]Nitin Aggarwal,William Clem Karl.Line Detection in Images Through Regularized Hough Transform[J].IEEE Trans on Image Processing,2006,15(3):582-591
[35]Nacken P.A Metric for Line Segments[J].IEEE Trans on PAMI,1993,15(12):1312-1318
[36]郑冶枫,刘长松,丁晓青,潘世言.基于有向单连通链的表格框线检测算法[J].软件学报,2002,13(4):790-796
[37]Yefeng Zheng,Huiping Li,David Doermann.A Parallel-Line Detection Algorithm Based on HMM Decoding[J].IEEE Trans on PAMI,2005,27(5):777-792
[38]Chun-Ta Ho,Ling-Hwei Chen,A high-speed algorithm for line detection[J].Pattern Recognition Letters,1996,17(5):467-473
[39]MORI S.,SUEN C.Y.,YAMAMOTO K..Historical Review of OCR Research and Development.Proc.IEEE.1992,80(7):1029-1057
[40]边肇祺,张学工.模式识别[M](第2版).北京:清华大学出版社,2000.
[41]丁晓青.汉字识别研究的回顾[J].电子学报,2002,30(9):1364-1368
[42]Notbohm K.et al.Automatic Digit Recognition in a Mail Sorting Machine.Nachrichtentech,Electron.1986,36:472-476
[43]Gopisetty S.et al.Automated Forms-Processing Software and Services[J].IBM Journal of Research and Development,1996,40(2):211-230.
[44]Rafael Palacios,Amar Gupta,A System for Processing Handwiritten Bank Checks Automatically(February 2002).MIT Sloan Working Paper No.4346-02;Eller College Working Paper No.1028-05.
[45]Greco N.,Impedovo D.,Lucchese M.G.,Salzo A.,Sarcinella L.Bank-check Processing System:Modifications Due to the New European Currency.Proc Seventh Int.Conf on Document Analysis and Recognition,2003,Vol.1,pp.343-348
[46]Zhi Han,Chang-Ping Liu.A two-stage handwritten character segmentation approach in mail address recognition,Proceedings of the Eighth International Conference on Document Analysis and Recognition,Seoul,Korea,2005,Vol.1,pp.111-115
[47]Oliveira L S,et al.A new approach to segment handwritten digits.In:Seventh International Workshop on Frontiers in Handwritten Recognition(IWFHR-7),Amsterdam,Nijmegen:International Unipen Foundation,2000,pp.577-582
[48]Sadri J.,Suen C.Y.,Bui T.D..Automatic Segmentation of Unconstrained Handwritten Numeral Strings.IWFHR,2004,pp.317-322
[49]Jayarathna U.K.S.,Bandara G.E.M.D.C..New Segmentation Algorithm for Offline Handwritten Connected Character Segmentation,ICIIS,2006:540-546
[50]Zhang Chuang,Lin Zhiqing,Guo Jun.Study on Segmentation Algorithm for Unconstrained Handwritten Numeral Strings.lecture notes of computer science.2005,pp.1242-1247
[51]吕岳,施鹏飞,张克华.基于组件合并的手写体汉字串分割[J].软件学报,2000,11(11):1554-1559
[52]Reda Alhajj and Ashraf Elnagar,Multiagents to Separating Handwritten Connected Digits.IEEE Trans.Systems,Man and Cybernetics-Part A:Systems and Humans,2005,35(5):593-602
[53]Yi-Kai Chen,Jing-Fa Wang,Segmentation of single- or Multiple- touching handwritten numeral string using background and foreground analysis,IEEE Trans.on PAMI,2000,22(11):1304-1317
[54]Pal U,Belad A,Choisy Chi.Touching numeral segmentat ion using water reservoir concept[J].PatternRecognition Letters,2003,24(13):261-272.
[55]T Bayer,U KreBel,M Hammelsbeck.Segmenting merged characters.Pattern Recognition,1992,25(2):346-349
[56]A Nomura,K Michishita,S Uchida,M Suzuki.Detection and Segmentation of Touching Characters in Mathematical Expressions.IEEE Proceedings of the Seventh International Conference on Document Analysis and Recognition,2003:vol.1,pp.126-130.
[57]H Fujisawa,Y N akano,K Kurino.Segmentation methods for character recognition:From segmentation to document structure analysis.Proceeding of the IEEE,1992,80(7):1079-1092
[58]Qiang Fu,X.Q.Ding,Tong Liu,Yan Jiang,Zheng Ren.A Novel Segmentation and Recognition Algorithm for Chinese Handwritten Address Character Strings,ICPR,2006,pp.974-977
[59]Suen C.Y.,Kim J.,Kim K.,Xu Q.,Lain L.,Handwriting recognition---the last frontiers[J],Proc.15th ICPR,Barcelona,Vol.4,pp.1-10,200
[60]高学,金连文,尹俊勋,等.一种基于支持向量机的手写汉字识别方法[J].电子学报,2002,30(5):651-654.
[61]Kim I J , Kim J H.Statistical character structure modeling and its application to handwritten Chinese character recognition [J].IEEE Trans PAMI, 2003, 25 (11):1422-1436.
[62]L N Teow, K F Loe.Robust vision-based features and classification schemes for off-line handwritten digit recognition[J].Pattern Recognition,2002,35(3): 2355～2364
[63]E.Lethelier, M.Leroux, M.Gilloux, An automatic reading system for handwritten numeral amounts on trench checks, Third International Conference on Document Analysis and Recognition, 1995, vol.1, pp.92～97.
[64]L.Heutte, P.Barbosa-Pereira, 0.Bougeois, J.V.Moreau, B.Plessis,P.Courtellemont, Y.ecourtier, Multi-bank check recognition system:consideration on the numeral amount recognition module, International Journal of Pattern Recognition and Artificial Intelligence 1997,11 (4):595～618.
[65]G.Kaufmann, H.Bunke, A system for the automated reading of check amounts—some key ideas, Proceedings of the Third International Association of Pattern Recognition Workshop on Document Analysis Systems.Nagano, Japan, 1998, pp.302-315
[66]OLIVEIRA L S, SABOURIN R, BORTOLOZZI F, et al.A modular system to recognize numerical amounts on Brazilian bank cheques, Proceedings of the 6th International Conference on Document Analysis and Recognition, 2001, Seattle, USA.IEEE Computer Society, 2001,pp.389～394.
[67]Kim K.K., Kim J.H., Chung Y.K., Suen C.Y., Legal amount recognition based on the segmentation hypotheses for bank check processing, Proceedings of the Sixth International Conference on Document Analysis and Recognition, 2001, pp.964-967.
[68]XU Q Z, LAM L, SUEN C Y.Automatic segmentation and recognition system for handwritten dates on Canadian bank cheques, Proceedings of the 7th International Conference on Document Analysis and Recognition,Aug 3-6, 2003, Edinburgh, Scotland.Piscataway, NJ, USA: IEEE, 2003,pp.704～708.
[69]R.Fan, L.Lam, C.Y.Suen, Processing of date information on cheques in:A.C.Downton, C.Impedovo (Eds.), Progress in Handwriting Recognition,World Scientific,Singapore, 1997, pp.473-479.
[70]C.Y.Suen, Q.Xu, L.Lam, Automatic recognition of handwritten data on cheques—fact or fiction?, Pattern Recognition Letters,1999(20):1287～1295.
[71]S.Knerr, V.Anisimov, O.Beret, N.Gorski, D.Price, J.C.Simon, The A2iA intercheque system:courtesy amount and legal amount recognition for french checks,International Journal of Pattern Recognition and Artificial Intelligence,1997,11(4):505-547.
[72]N.Gorski,V.Anisimov,E.Augustin,O.Baret,D.Price,J.C.Simon,A2iA check reader:a family of bank recognition systems,Fifth International Conference on Document Analysis and Recognition,Bangalore,India,1999,pp.523-526.
[73]张黔,胡庆,杨静宇,统计和结构模式识别方法结合的多特征印鉴真伪鉴别方法,计算机学报,1995,18(3):190-198
[74]Su H,Zhao B,Ma F,et al.A fault-tolerant Chinese check recognition system.International Journal of Pattern Recognition and Artificial Intelligence,1997,11(4):571-593.
[75]郭丽,黄元元,杨静宇.基于连通域的版面分割研究.南京理工大学学报,2003,27(1):16-19.
[76]张重阳,杨静宇,李伟,等.文档处理中背景字符的去除.计算机科学,2006,33(8):229-231.
[77]徐蔚然,张洪刚,刘刚,等.基于知识的银行票据二值化方法.中文信息学报,2002,16(2):60-64.
[78]张洪刚,吴铭,刘刚,等.基于模具的手写数字串切分算法及其应用.计算机学报,2003,26(7):819-824.
[79]薛炳如,杨静宇,胡钟山,等.小类别数手写汉字识别.计算机研究与发展,2000,37(4):483-492.
[80]刘刚,张洪刚,郭军.用于脱机手写数字识别的隐马尔可夫模型.计算机研究与发展,2003,40(8):1252-1257.
[81]Mansouri,A.,Malowany,S.,Levine,M.D.Line detection in digital pictures:A hypothesis prediction/verification paradigm.Computer Vision Graphics Image Process.1987,40:95-114
[82]Burns,J.B.,Hanson,A.R.,Riseman,E.M.Extracting straight lines.IEEE Trans.Pattern Analasis and Machine Intelligence.1986,8(4):425-455
[83]Nelson,R.C.Finding line segments by stick growing.IEEE Trans.Pattern Analasis and Machine Intelligence.1994,16(5):519-523
[84]Nevatia,R.,Babu,K.R.Linear feature extraction and description.Computer Vision Graphics Image Process.1980,13:257-269
[85]Duda,R.O.,Hart,P.E.Use of Hought transformation to detect lines and curves in pictures.Commnunication ACM,1972,15(1):11-15
[86]Li,H.,Lavin,M.A.,Le Master,R.J.Fast Hought transform:A hierarchical approach.Computer Vision Graphics Image Process.1986,36:139-161
[87]Atiquzzaman,M.Multiresolution Hough transform--an efficient method of detecting patterns in images.IEEE Trans.Pattern Analasis and Machine Intelligence.1992,14(11):1090-1095
[88]Galambos,C.Matas,J.,Kittler,J.Progressive probabilistic Hough transform for line detection.In:Conf.On Computer Vision and Pattern Tecognition,IEEE Computer Society,1999,1:554-560
[89]Guru,D.S.,Shekar,B.H.,Nagabhushan,P.A simple and robust line detection algorithm based on small eigenvalue analysis.Pattern Recognition Letters.2004,25:1-13
[90]Lee,Y.S.,Koo,H.S.,Jeong,C.S.A straight line detection using principal component analysis.Pattern Recognition Letters,2006,27:1744-1754
[91]孙兴华,郭丽,王正群,等.基于子图像多特征组合的商标图像检索[J].模式识别与人工智能,2002,15(1):14-20
[92]D.Marr,E.Hildreth.Theory of edge detection.In:Proc.R.Soc.Lond,1980,B-207:187-217
[93]F.Bergholm,Edge focusing,IEEE Trans.Pattern Analysis and Machine Intelligence.1987,9(6):726-741
[94]M.Kamel,A.Zhao.Extraction of binary character/graphics images from grayscale document images.CVGIP,1993,55(3):203-217
[95]S.Djeziri,F.Nouboud,R.Plamondon.Extraction of signatures from check background based on a filiformity criterion.IEEE Trans.Image Processing.1998,7(10):1425-1438
[96]Xiangyun Ye,Mohamed Cheriet,Ching Y.Suen,Stroke-Model-Based Character Extraction from Gray-Level Document Images,IEEE Trans.Image Processing 2001(10):1152-1161
[97]Y.Deng,C.Kenney,M.S.Moore,B.S.Manjunath.Peer group filtering and perceptual color image quantization.In:Proc.ISCA,1999,4:21-24.
[98]R.O.Duda,P.E.Hart.Pattern classification and scene anlysis.A Wiley-Interscience Publication,New York:Wiley,1973
[99]刘建庄,粟文青.灰度图像的二维Otsu自动阈值分割法.自动化学报,1993,19(1):101-105.
[100]J.Gong et al.Fast recursive algorithm for two-dimensional thresholding.Pattern Recognition,1998,31(3):295-300.
[101]范九伦,赵风.灰度图像的二维曲线阈值分割法.电子学报,2007,35(4):751-755.
[102]J.N.Kapur,P.K.Sahoo,A.K.Wong.A new method for gray-level picture thresholding using the entropy of the histogram.CVGIP,1985,29:273-285.
[103]Xiangyun Ye,Mohamed Cheriet,Ching Y.Suen,Ke Liu.Extraction of bankcheck items by mathematical morphology.J.Doc.Anal.Recognit.,1999,2:53-66.
[104]Ren M.W.,Yang J.Y.,Sun H.Tracing boundary contours in a binary image,Image and Vision Computing,2002,20(2):125-131
[105]任明武,杨静宇,孙涵.一种快速的基于链码描述的轮廓填充方法,中国图象图形学报,2001,6(4):248-252
[106]K.K.Kim,C.Y.Suen,J.H.Kim.Recognition of unconstrained handwritten numeral strings by composite segmentation method.In:Proceedings of 15th International Conference on Pattern Recognition,2000,vol.2,pp.594-597
[107]张闯,吴铭,郭军.非限制自由手写粘连数字串数字个数判断,北京邮电大学学报,2004,27(3):63-67
[108]Choi W P,Lam K M,Siu W C.An efficient algorithm for extraction of a euclidean sketleton.In:Proceedings of IEEE International Conference on Acoustics,Speech and Signal.NewYork,USA:IEEE,2002,3241-3244
[109]Rockett P I.An improved rotation-invariant thinning algorithm.IEEE Trans.on Pattern Analysis and MachineIntelligence,2005,27(10):1671-1674
[110]Ahmed M,Ward R.A rotation invariant rule-based thinning algorithm for character recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(12):1672-1678.
[111]Bouaynaya N,Charif-Chefchaouni M,Schonfeld D.Spatially variant morphological restoration and skeleton representation.IEEE Trans on Image Processing,2006,15(11):3579-3582.
[112]Coeurjolly D,Montanvert A.Optimal separable algorithms to compute the reverse euclidean distance transformation and discrete medial axis in arbitrary dimension.IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(3):437-449.
[113]Kegl,Krzyzak A.,et al.Piecewise linear skeletonization using Principal curves.IEEE Transaetions on Pattern Analysis and Machine Intelligence,2002,24(1):59-74
[114]Hastie T,Stuetzle W.Principal curves.Journal of the American Statistical Association,1988,84(406):502-516
[115]Hastie T.Principal Curves and Surfaces.Laboratory for Computational Statistics,Stanford University,Department of Statistics:Technical Report 11,1984
[116]张军平,王珏.主曲线综述.计算机学报,2003,26(2):129-146
[117]Banfield J D,Raftery A E.Ice floe identification in satellite images using mathematical morphology and clustering about principal curves.Journal of the American Statistical Association,1992,87(417):7-16
[118]Kegl B,Krzyzak A,et al.A polygonal Line algorithm for constructing principal curves.Proceedings of Neural Information Processing System.Denver Colorado,USA,1999,501-507
[119]Verbeek J.J.,Vlassis N,Krose B.A k-segments algorithm for finding principal curve.Computer Science of Institute,University of Amsterdam,IAS-UVA-00-11,2000
[120]Delicado P.Another look at principal curves andsurfaces.Journal of Multivariate Analysis,2001,77(1 ):84-116
[121]苗夺谦,张红云,李道国等.基于主曲线的脱机手写数字识别,电子学报,2005,33(9):1639-1643
[122]S.Suzuki,K.Abe.Topological Structural Analysis of Digital Binary Images by Border Following.CVGIP,1985,1(30):32-46.
[123]G.C,et al.Segmentation of numeric strings.In:Proceedings of the Third International Conference on Document Analysis and Recognition,Montreal,Que.,Canada,1995,vol.2,pp.1038-1041
[124]Zhao B,Su H,Xia S.A new method for segmenting unconstrained handwritten numeral string.In:Proceedings of the International Conference on Document Analysis and Recognition,Ulm,Germany,1997,vol.2,pp.524-527
[125]D.Gorgevik,D.Cakmakov,V.Radevski.Handwritten digit recognition by combining Support Vector Machines using rule-based reasoning,The 23rd Information Technology Interfaces(ITI2001),Pula Croatia:SRCE University Computing Center,University of Zagreb,2001:139-144
[126]J.Wierer,N.Boston.A handwritten digit recognition algorithm using two-dimensional Hidden Markov Models for feature extraction,The 32nd IEEE International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2007),Honolulu,Hawaii:Hawai'I Convertion Center,USA,2007:505-508
[127]荆晓远,杨静宇.基于相关性和有效互补性分析的多分类器组合方法.自动化学报,2000,26(6):741-747
[128]Cheng-Lin Liu,K.NaKashima,H.Sako,H.Fujisawa.Handwritten digit recognition:benchmarking of state-of-the-art techniques,The journal of the Pattern Recognition,2003,36:2271-2285
[129]Brendan J.Frey,Delbert Dueck.Clustering by passing messages between data points,Science,2007,315(5814):972-976
[130]M.A.Turk,A.P.Pentland,"Face recognition using eigenfaces," Computer Vision and Pattern Recognition,Proceedings CVPR'91.,IEEE Computer Society Conference on,1991,pp.586-591
[131]P.N.Belhumeur,J.P.Hespanha,D.J.Kriegman.Eigenfaces vs.Fisherfaces:recognition using class specific linear projection,IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720
[132]C.Y.Suen,et al.Computer recognition of unconstrained handwritten numerals,Proc,IEEE 1992,80(7):1162-1180
[133]娄震,金忠,杨静宇.基于类条件置信变换的后验概率估计方法,计算机学报,2005,28(1):18-24
[134]S.Belongie,J.Malik,J.Puzicha.Shape matching and object recognition using shape contexts[J],IEEE Trans.on PAMI,2002,24(24):509-522
[135]Christos H.P.,Steiglitz K..Combinational Optimization:Algorithm and Complexity,Prentice Hall,New Jersey,1982
[136]K.Han,I.Sethi,AnOff-lineCursive HandwrittenWord Recognition System and its Application to Legal Amount Interpretation,Automatic Bankcheck Processing,Wold Scientific Press,Singapore,1997.pp.295-308.
[137]C.O.de Almendra Freitas,A.el Yacoubi,F.Bortolozzi,R.Sabourin,Brazilian Bank Check Handwritten Legal Amount Recognition,Proceedings ⅩⅢ Brazilian Symposium on Computer Graphics and ImageProcessing,2000,pp.97-104.
[138]K.Ueda,T.Mutoh,K.Matsuo,Automatic verification system for seal imprints on Japanese bankchecks,in:Proceedings of the International Conference on Pattern Recognition,1998,vol.1,pp.629-632
[139]袁小四.票据综合监督系统的设计与实现.中国金融电脑,2001,12:32-33
[140]高翔,银行票据稽核系统的研究与实现,山东:山东大学,2004
[141]中国人民银行科技司,全国支票影像交换系统商业银行直接连接分中心实施指引,2007.01.
[2]赵斌.基于支持向量机的金融票据识别系统研究[D].北京:清华大学,2000
[3]Cheng-Lin Liu,Kazuki Nakashima,Hiroshi Sako,Hiromichi Fujisawa.Handwritten digit recognition:investigation of normalization and feature extraction techniques[J],Pattern Recognition.2004,37(2):265-279
[4]张重阳.票据自动处理系统中的预处理技术研究[D].南京:南京理工大学,2004
[5]Wang Song,Ma Feng,Xia Shaowei.A fault tolerant Chinese bank check recognition system based on SOM neural networks[C].ICNN97 Pattern Recognition and Image Processing Session,Houston USA,1997,4:2560-2565
[6]陈强,杨静宇,娄震.基于模板匹配和差影处理的票据图像检测[J].计算机工程与应用,2004,40(26):207-219
[7]李琥,卜佳俊,陈纯.一种新的基于特征线选取的票据识别算法[J].浙江大学学报,2003,37(2):173-177
[8]N.Otsu.A threshold selection method from grey-level histograms.IEEE Trans.on Systems Man Cybernetics.1979,9:62-66
[9]邓雁萍,李介谷.图像分割的性能评估[J].模式识别与人工智能.1996,9(2):144-148
[10]罗希平,田捷,诸葛婴,王靖,戴汝为.图像分割方法综述[J].模式识别与人工智能.1999,12(3):300-312
[11]N.B.Venkateswarlu.Implementation of some image thresholding algorithms on a connection machine-200[J].Pattern Recognition Letters,1995,16(7):759-768
[12]Cheriet M.,Said J.N.,Suen C.Y..A recursive thresholding technique for image segmentation.IEEE Trans.On Image Processing,1998,7(6):918-921
[13]Liu Y.,Srihari S.N..Document Image Binarization Based on Texture Features.IEEE Trans.Pattern Analysis and Machine Intelligence,1997,19(5):540-544
[14]Palumbo P.W.,Swaminathan P.,Srihari S.N..Document Image Binarization:Evaluation of Algorithms.In:Proc.SPIE,1986,697:278-285
[15]Parker J.R..Gray level thresholding in badly illuminated images.IEEE Trans.Pattern Analysis and Machine Intelligence.1991,13(8):813-819
[16]M.Kamel,A.Zhao.Extraction of binary character/graphics images from grayscale document images.CVGIP:Graphical Models and Image Processing,1993,55(3):203-217
[17]Q.D.Trier,A.K.Jain.Goal-directed evaluation of binarization methods.IEEE Trans.Pattern Analysis and Machine Intelligence.1995,7(12):1191-1201.
[18]Q.D.Trier,A.K.Jain.Evaluation of binarization methods for document images.IEEE Trans.Pattern Analysis and Machine Intelligence.1995,17(3):312-314
[19]J.Bernsen.Dynamic thresholding of gray-level images.Proc.Int.Conf.Pattern Recognition.LOS Angeles,1986(2):1251-1255
[20]J.Ohya,A.Shio,and S.Akamatsu.Recognizing characters in scene images.IEEE Trans.Pattern Analysis and Machine Intelligence.1994,16(2):214-220.
[21]L.Wang,T.Pavlidis.Direct gray-scale extraction of features for character recognition.IEEE Trans.Pattern Analysis and Machine Intelligence.1993,15(10):1053-1067.
[22]M.Cheriet.Extraction of handwritten data from noisy gray-level images using a multi-scale approach.In:Proc.Vision Interface,1998,1:389-396
[23]S.Djeziri,F.Nouboud,R.Plamondon.Extraction of signatures from check background based on a filiformity criterion.IEEE Trans.Image Processing.1998,7(10):1425-1438
[24]Xiangyun Ye,Mohamed Cheriet,Ching Y.Suen,Stroke-Model-Based Character Extraction from Gray-Level Document Images,IEEE Trans.Image Processing,2001(10):1152-1161
[25]Bin Yu,Ani K Jain,A generic system for form dropout[J].IEEE Trans on PAMI,1996,18(11):1127-1134
[26]刘长松,潘世言,郑冶枫,等.一种表格框线检测和字线分离算法[J].电子与信息学报,2002,24(9),1190-1196
[27]Xiangyun Ye,Mohamed Cheriet,Ching Y Suen.A generic method of cleaning and enhancing handwritten data from business forms[J].Journal of Doctor Analects Recognition,2001,4(2):84-96
[28]Jain-Shiue Chen,Din-Chang Tseng.Overlapped-character separation and reconstruction for table-form documents[C].In:Proc Int'l Conf on Image Processing,Lausanne,Switzerland,1996.233-236
[29]Yi-Hong Tseng,His-Jian Lee.Interfered-character recognition by removing interfering-lines and adjusting feature weights[C].In:The 14th Int'l Conf on pattern Recognition,Brisbane,Qld,Austrialia,1998.1865-1867
[30]胡钟山,娄震,杨静宇,等.文档处理中消除线噪声的研究[J].计算机研究与发展,1999,36(8):992-995
[31]郑冶枫,刘长松,丁晓青.线宽阈值法去除表格框线[J].模式识别与人工智能, 2001,14(2):206-210
[32]张重阳,陈强,娄震,杨静宇.基于灰度图像的表格框线去除算法[J].计算机研究与发展,2005,42(4):635-639
[33]Mark C K Yang,etal.Hough Transform Modified by Line Connectively and Line Thickness[J].IEEE Trans on PAMI,1997,19(8):905-910
[34]Nitin Aggarwal,William Clem Karl.Line Detection in Images Through Regularized Hough Transform[J].IEEE Trans on Image Processing,2006,15(3):582-591
[35]Nacken P.A Metric for Line Segments[J].IEEE Trans on PAMI,1993,15(12):1312-1318
[36]郑冶枫,刘长松,丁晓青,潘世言.基于有向单连通链的表格框线检测算法[J].软件学报,2002,13(4):790-796
[37]Yefeng Zheng,Huiping Li,David Doermann.A Parallel-Line Detection Algorithm Based on HMM Decoding[J].IEEE Trans on PAMI,2005,27(5):777-792
[38]Chun-Ta Ho,Ling-Hwei Chen,A high-speed algorithm for line detection[J].Pattern Recognition Letters,1996,17(5):467-473
[39]MORI S.,SUEN C.Y.,YAMAMOTO K..Historical Review of OCR Research and Development.Proc.IEEE.1992,80(7):1029-1057
[40]边肇祺,张学工.模式识别[M](第2版).北京:清华大学出版社,2000.
[41]丁晓青.汉字识别研究的回顾[J].电子学报,2002,30(9):1364-1368
[42]Notbohm K.et al.Automatic Digit Recognition in a Mail Sorting Machine.Nachrichtentech,Electron.1986,36:472-476
[43]Gopisetty S.et al.Automated Forms-Processing Software and Services[J].IBM Journal of Research and Development,1996,40(2):211-230.
[44]Rafael Palacios,Amar Gupta,A System for Processing Handwiritten Bank Checks Automatically(February 2002).MIT Sloan Working Paper No.4346-02;Eller College Working Paper No.1028-05.
[45]Greco N.,Impedovo D.,Lucchese M.G.,Salzo A.,Sarcinella L.Bank-check Processing System:Modifications Due to the New European Currency.Proc Seventh Int.Conf on Document Analysis and Recognition,2003,Vol.1,pp.343-348
[46]Zhi Han,Chang-Ping Liu.A two-stage handwritten character segmentation approach in mail address recognition,Proceedings of the Eighth International Conference on Document Analysis and Recognition,Seoul,Korea,2005,Vol.1,pp.111-115
[47]Oliveira L S,et al.A new approach to segment handwritten digits.In:Seventh International Workshop on Frontiers in Handwritten Recognition(IWFHR-7),Amsterdam,Nijmegen:International Unipen Foundation,2000,pp.577-582
[48]Sadri J.,Suen C.Y.,Bui T.D..Automatic Segmentation of Unconstrained Handwritten Numeral Strings.IWFHR,2004,pp.317-322
[49]Jayarathna U.K.S.,Bandara G.E.M.D.C..New Segmentation Algorithm for Offline Handwritten Connected Character Segmentation,ICIIS,2006:540-546
[50]Zhang Chuang,Lin Zhiqing,Guo Jun.Study on Segmentation Algorithm for Unconstrained Handwritten Numeral Strings.lecture notes of computer science.2005,pp.1242-1247
[51]吕岳,施鹏飞,张克华.基于组件合并的手写体汉字串分割[J].软件学报,2000,11(11):1554-1559
[52]Reda Alhajj and Ashraf Elnagar,Multiagents to Separating Handwritten Connected Digits.IEEE Trans.Systems,Man and Cybernetics-Part A:Systems and Humans,2005,35(5):593-602
[53]Yi-Kai Chen,Jing-Fa Wang,Segmentation of single- or Multiple- touching handwritten numeral string using background and foreground analysis,IEEE Trans.on PAMI,2000,22(11):1304-1317
[54]Pal U,Belad A,Choisy Chi.Touching numeral segmentat ion using water reservoir concept[J].PatternRecognition Letters,2003,24(13):261-272.
[55]T Bayer,U KreBel,M Hammelsbeck.Segmenting merged characters.Pattern Recognition,1992,25(2):346-349
[56]A Nomura,K Michishita,S Uchida,M Suzuki.Detection and Segmentation of Touching Characters in Mathematical Expressions.IEEE Proceedings of the Seventh International Conference on Document Analysis and Recognition,2003:vol.1,pp.126-130.
[57]H Fujisawa,Y N akano,K Kurino.Segmentation methods for character recognition:From segmentation to document structure analysis.Proceeding of the IEEE,1992,80(7):1079-1092
[58]Qiang Fu,X.Q.Ding,Tong Liu,Yan Jiang,Zheng Ren.A Novel Segmentation and Recognition Algorithm for Chinese Handwritten Address Character Strings,ICPR,2006,pp.974-977
[59]Suen C.Y.,Kim J.,Kim K.,Xu Q.,Lain L.,Handwriting recognition---the last frontiers[J],Proc.15th ICPR,Barcelona,Vol.4,pp.1-10,200
[60]高学,金连文,尹俊勋,等.一种基于支持向量机的手写汉字识别方法[J].电子学报,2002,30(5):651-654.
[61]Kim I J , Kim J H.Statistical character structure modeling and its application to handwritten Chinese character recognition [J].IEEE Trans PAMI, 2003, 25 (11):1422-1436.
[62]L N Teow, K F Loe.Robust vision-based features and classification schemes for off-line handwritten digit recognition[J].Pattern Recognition,2002,35(3): 2355～2364
[63]E.Lethelier, M.Leroux, M.Gilloux, An automatic reading system for handwritten numeral amounts on trench checks, Third International Conference on Document Analysis and Recognition, 1995, vol.1, pp.92～97.
[64]L.Heutte, P.Barbosa-Pereira, 0.Bougeois, J.V.Moreau, B.Plessis,P.Courtellemont, Y.ecourtier, Multi-bank check recognition system:consideration on the numeral amount recognition module, International Journal of Pattern Recognition and Artificial Intelligence 1997,11 (4):595～618.
[65]G.Kaufmann, H.Bunke, A system for the automated reading of check amounts—some key ideas, Proceedings of the Third International Association of Pattern Recognition Workshop on Document Analysis Systems.Nagano, Japan, 1998, pp.302-315
[66]OLIVEIRA L S, SABOURIN R, BORTOLOZZI F, et al.A modular system to recognize numerical amounts on Brazilian bank cheques, Proceedings of the 6th International Conference on Document Analysis and Recognition, 2001, Seattle, USA.IEEE Computer Society, 2001,pp.389～394.
[67]Kim K.K., Kim J.H., Chung Y.K., Suen C.Y., Legal amount recognition based on the segmentation hypotheses for bank check processing, Proceedings of the Sixth International Conference on Document Analysis and Recognition, 2001, pp.964-967.
[68]XU Q Z, LAM L, SUEN C Y.Automatic segmentation and recognition system for handwritten dates on Canadian bank cheques, Proceedings of the 7th International Conference on Document Analysis and Recognition,Aug 3-6, 2003, Edinburgh, Scotland.Piscataway, NJ, USA: IEEE, 2003,pp.704～708.
[69]R.Fan, L.Lam, C.Y.Suen, Processing of date information on cheques in:A.C.Downton, C.Impedovo (Eds.), Progress in Handwriting Recognition,World Scientific,Singapore, 1997, pp.473-479.
[70]C.Y.Suen, Q.Xu, L.Lam, Automatic recognition of handwritten data on cheques—fact or fiction?, Pattern Recognition Letters,1999(20):1287～1295.
[71]S.Knerr, V.Anisimov, O.Beret, N.Gorski, D.Price, J.C.Simon, The A2iA intercheque system:courtesy amount and legal amount recognition for french checks,International Journal of Pattern Recognition and Artificial Intelligence,1997,11(4):505-547.
[72]N.Gorski,V.Anisimov,E.Augustin,O.Baret,D.Price,J.C.Simon,A2iA check reader:a family of bank recognition systems,Fifth International Conference on Document Analysis and Recognition,Bangalore,India,1999,pp.523-526.
[73]张黔,胡庆,杨静宇,统计和结构模式识别方法结合的多特征印鉴真伪鉴别方法,计算机学报,1995,18(3):190-198
[74]Su H,Zhao B,Ma F,et al.A fault-tolerant Chinese check recognition system.International Journal of Pattern Recognition and Artificial Intelligence,1997,11(4):571-593.
[75]郭丽,黄元元,杨静宇.基于连通域的版面分割研究.南京理工大学学报,2003,27(1):16-19.
[76]张重阳,杨静宇,李伟,等.文档处理中背景字符的去除.计算机科学,2006,33(8):229-231.
[77]徐蔚然,张洪刚,刘刚,等.基于知识的银行票据二值化方法.中文信息学报,2002,16(2):60-64.
[78]张洪刚,吴铭,刘刚,等.基于模具的手写数字串切分算法及其应用.计算机学报,2003,26(7):819-824.
[79]薛炳如,杨静宇,胡钟山,等.小类别数手写汉字识别.计算机研究与发展,2000,37(4):483-492.
[80]刘刚,张洪刚,郭军.用于脱机手写数字识别的隐马尔可夫模型.计算机研究与发展,2003,40(8):1252-1257.
[81]Mansouri,A.,Malowany,S.,Levine,M.D.Line detection in digital pictures:A hypothesis prediction/verification paradigm.Computer Vision Graphics Image Process.1987,40:95-114
[82]Burns,J.B.,Hanson,A.R.,Riseman,E.M.Extracting straight lines.IEEE Trans.Pattern Analasis and Machine Intelligence.1986,8(4):425-455
[83]Nelson,R.C.Finding line segments by stick growing.IEEE Trans.Pattern Analasis and Machine Intelligence.1994,16(5):519-523
[84]Nevatia,R.,Babu,K.R.Linear feature extraction and description.Computer Vision Graphics Image Process.1980,13:257-269
[85]Duda,R.O.,Hart,P.E.Use of Hought transformation to detect lines and curves in pictures.Commnunication ACM,1972,15(1):11-15
[86]Li,H.,Lavin,M.A.,Le Master,R.J.Fast Hought transform:A hierarchical approach.Computer Vision Graphics Image Process.1986,36:139-161
[87]Atiquzzaman,M.Multiresolution Hough transform--an efficient method of detecting patterns in images.IEEE Trans.Pattern Analasis and Machine Intelligence.1992,14(11):1090-1095
[88]Galambos,C.Matas,J.,Kittler,J.Progressive probabilistic Hough transform for line detection.In:Conf.On Computer Vision and Pattern Tecognition,IEEE Computer Society,1999,1:554-560
[89]Guru,D.S.,Shekar,B.H.,Nagabhushan,P.A simple and robust line detection algorithm based on small eigenvalue analysis.Pattern Recognition Letters.2004,25:1-13
[90]Lee,Y.S.,Koo,H.S.,Jeong,C.S.A straight line detection using principal component analysis.Pattern Recognition Letters,2006,27:1744-1754
[91]孙兴华,郭丽,王正群,等.基于子图像多特征组合的商标图像检索[J].模式识别与人工智能,2002,15(1):14-20
[92]D.Marr,E.Hildreth.Theory of edge detection.In:Proc.R.Soc.Lond,1980,B-207:187-217
[93]F.Bergholm,Edge focusing,IEEE Trans.Pattern Analysis and Machine Intelligence.1987,9(6):726-741
[94]M.Kamel,A.Zhao.Extraction of binary character/graphics images from grayscale document images.CVGIP,1993,55(3):203-217
[95]S.Djeziri,F.Nouboud,R.Plamondon.Extraction of signatures from check background based on a filiformity criterion.IEEE Trans.Image Processing.1998,7(10):1425-1438
[96]Xiangyun Ye,Mohamed Cheriet,Ching Y.Suen,Stroke-Model-Based Character Extraction from Gray-Level Document Images,IEEE Trans.Image Processing 2001(10):1152-1161
[97]Y.Deng,C.Kenney,M.S.Moore,B.S.Manjunath.Peer group filtering and perceptual color image quantization.In:Proc.ISCA,1999,4:21-24.
[98]R.O.Duda,P.E.Hart.Pattern classification and scene anlysis.A Wiley-Interscience Publication,New York:Wiley,1973
[99]刘建庄,粟文青.灰度图像的二维Otsu自动阈值分割法.自动化学报,1993,19(1):101-105.
[100]J.Gong et al.Fast recursive algorithm for two-dimensional thresholding.Pattern Recognition,1998,31(3):295-300.
[101]范九伦,赵风.灰度图像的二维曲线阈值分割法.电子学报,2007,35(4):751-755.
[102]J.N.Kapur,P.K.Sahoo,A.K.Wong.A new method for gray-level picture thresholding using the entropy of the histogram.CVGIP,1985,29:273-285.
[103]Xiangyun Ye,Mohamed Cheriet,Ching Y.Suen,Ke Liu.Extraction of bankcheck items by mathematical morphology.J.Doc.Anal.Recognit.,1999,2:53-66.
[104]Ren M.W.,Yang J.Y.,Sun H.Tracing boundary contours in a binary image,Image and Vision Computing,2002,20(2):125-131
[105]任明武,杨静宇,孙涵.一种快速的基于链码描述的轮廓填充方法,中国图象图形学报,2001,6(4):248-252
[106]K.K.Kim,C.Y.Suen,J.H.Kim.Recognition of unconstrained handwritten numeral strings by composite segmentation method.In:Proceedings of 15th International Conference on Pattern Recognition,2000,vol.2,pp.594-597
[107]张闯,吴铭,郭军.非限制自由手写粘连数字串数字个数判断,北京邮电大学学报,2004,27(3):63-67
[108]Choi W P,Lam K M,Siu W C.An efficient algorithm for extraction of a euclidean sketleton.In:Proceedings of IEEE International Conference on Acoustics,Speech and Signal.NewYork,USA:IEEE,2002,3241-3244
[109]Rockett P I.An improved rotation-invariant thinning algorithm.IEEE Trans.on Pattern Analysis and MachineIntelligence,2005,27(10):1671-1674
[110]Ahmed M,Ward R.A rotation invariant rule-based thinning algorithm for character recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(12):1672-1678.
[111]Bouaynaya N,Charif-Chefchaouni M,Schonfeld D.Spatially variant morphological restoration and skeleton representation.IEEE Trans on Image Processing,2006,15(11):3579-3582.
[112]Coeurjolly D,Montanvert A.Optimal separable algorithms to compute the reverse euclidean distance transformation and discrete medial axis in arbitrary dimension.IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(3):437-449.
[113]Kegl,Krzyzak A.,et al.Piecewise linear skeletonization using Principal curves.IEEE Transaetions on Pattern Analysis and Machine Intelligence,2002,24(1):59-74
[114]Hastie T,Stuetzle W.Principal curves.Journal of the American Statistical Association,1988,84(406):502-516
[115]Hastie T.Principal Curves and Surfaces.Laboratory for Computational Statistics,Stanford University,Department of Statistics:Technical Report 11,1984
[116]张军平,王珏.主曲线综述.计算机学报,2003,26(2):129-146
[117]Banfield J D,Raftery A E.Ice floe identification in satellite images using mathematical morphology and clustering about principal curves.Journal of the American Statistical Association,1992,87(417):7-16
[118]Kegl B,Krzyzak A,et al.A polygonal Line algorithm for constructing principal curves.Proceedings of Neural Information Processing System.Denver Colorado,USA,1999,501-507
[119]Verbeek J.J.,Vlassis N,Krose B.A k-segments algorithm for finding principal curve.Computer Science of Institute,University of Amsterdam,IAS-UVA-00-11,2000
[120]Delicado P.Another look at principal curves andsurfaces.Journal of Multivariate Analysis,2001,77(1 ):84-116
[121]苗夺谦,张红云,李道国等.基于主曲线的脱机手写数字识别,电子学报,2005,33(9):1639-1643
[122]S.Suzuki,K.Abe.Topological Structural Analysis of Digital Binary Images by Border Following.CVGIP,1985,1(30):32-46.
[123]G.C,et al.Segmentation of numeric strings.In:Proceedings of the Third International Conference on Document Analysis and Recognition,Montreal,Que.,Canada,1995,vol.2,pp.1038-1041
[124]Zhao B,Su H,Xia S.A new method for segmenting unconstrained handwritten numeral string.In:Proceedings of the International Conference on Document Analysis and Recognition,Ulm,Germany,1997,vol.2,pp.524-527
[125]D.Gorgevik,D.Cakmakov,V.Radevski.Handwritten digit recognition by combining Support Vector Machines using rule-based reasoning,The 23rd Information Technology Interfaces(ITI2001),Pula Croatia:SRCE University Computing Center,University of Zagreb,2001:139-144
[126]J.Wierer,N.Boston.A handwritten digit recognition algorithm using two-dimensional Hidden Markov Models for feature extraction,The 32nd IEEE International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2007),Honolulu,Hawaii:Hawai'I Convertion Center,USA,2007:505-508
[127]荆晓远,杨静宇.基于相关性和有效互补性分析的多分类器组合方法.自动化学报,2000,26(6):741-747
[128]Cheng-Lin Liu,K.NaKashima,H.Sako,H.Fujisawa.Handwritten digit recognition:benchmarking of state-of-the-art techniques,The journal of the Pattern Recognition,2003,36:2271-2285
[129]Brendan J.Frey,Delbert Dueck.Clustering by passing messages between data points,Science,2007,315(5814):972-976
[130]M.A.Turk,A.P.Pentland,"Face recognition using eigenfaces," Computer Vision and Pattern Recognition,Proceedings CVPR'91.,IEEE Computer Society Conference on,1991,pp.586-591
[131]P.N.Belhumeur,J.P.Hespanha,D.J.Kriegman.Eigenfaces vs.Fisherfaces:recognition using class specific linear projection,IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720
[132]C.Y.Suen,et al.Computer recognition of unconstrained handwritten numerals,Proc,IEEE 1992,80(7):1162-1180
[133]娄震,金忠,杨静宇.基于类条件置信变换的后验概率估计方法,计算机学报,2005,28(1):18-24
[134]S.Belongie,J.Malik,J.Puzicha.Shape matching and object recognition using shape contexts[J],IEEE Trans.on PAMI,2002,24(24):509-522
[135]Christos H.P.,Steiglitz K..Combinational Optimization:Algorithm and Complexity,Prentice Hall,New Jersey,1982
[136]K.Han,I.Sethi,AnOff-lineCursive HandwrittenWord Recognition System and its Application to Legal Amount Interpretation,Automatic Bankcheck Processing,Wold Scientific Press,Singapore,1997.pp.295-308.
[137]C.O.de Almendra Freitas,A.el Yacoubi,F.Bortolozzi,R.Sabourin,Brazilian Bank Check Handwritten Legal Amount Recognition,Proceedings ⅩⅢ Brazilian Symposium on Computer Graphics and ImageProcessing,2000,pp.97-104.
[138]K.Ueda,T.Mutoh,K.Matsuo,Automatic verification system for seal imprints on Japanese bankchecks,in:Proceedings of the International Conference on Pattern Recognition,1998,vol.1,pp.629-632
[139]袁小四.票据综合监督系统的设计与实现.中国金融电脑,2001,12:32-33
[140]高翔,银行票据稽核系统的研究与实现,山东:山东大学,2004
[141]中国人民银行科技司,全国支票影像交换系统商业银行直接连接分中心实施指引,2007.01.