手写数字识别的研究与应用
|
摘要
手写字符的识别研究时冷时热，在过去几十年里，人们提出了许多识别方法和识别技术，但由于识别的关键技术没有解决，再加上产品定位等方面的原因，使得已有的识别系统远不能达到实际应用的要求，这其中有理论研究和技术实现等多方面因素。手写体数字识别是字符识别的一个分支，问题虽然简单，但却有较大的实用价值。目前我国在信函通信时广泛使用了邮政编码，用手写体数字识别技术进行信函的自动分拣对减轻邮电职工的手工分拣工作有很大意义。手写数字虽然只有10个种类，但很多情况下，对识别的精度要求非常高，而且，手写数字的变动性非常大，在这种情况下，要想做到高精度的识别就不是那么容易了。
本论文首先阐述计算机字符识别技术的必要性，论述手写数字识别的意义；接着讨论了手写数字识别的预处理技术，包括二值化、行字切分、平滑、去噪声、规范化和细化等。二值化时对整体阈值二值化、局部阈值二值化、动态阈值二值化和利用空间信息进行阈值选取几种常用的阈值选取方法进行讨论，特别对利用空间信息进行阈值选取进行了详细论述；在对通过对基于数学形态学的细化的基础上，讨论序贯同伦形态细化算法和保形的快速形态细化算法；然后依据联机字符识别原理框图，分析了手写数字的结构特点，提出了基于笔划特征的任意手写数字在线识别技术和基于多级分类器任意手写数字在线识别技术，对其中涉及的笔划识别前的噪声处理、笔划间特征量的定义及识别、整字匹配的距离准则进行了详细叙述；继而在对手写数字的分割的基础下对脱机手写数字识别进行了研究，对基于最小距离分类器字符识别、基于树分类器的字符识别、基于自适应共振(ART)网络的字符识别分别进行了详细讨论，并引入置信度分析将多个分类器进行了混合集成；最后简单阐述了手写数字识别的典型应用，对其在大规模数据统计、财务、税务、金融及邮件分拣中的应用进行了探索。
本论文对手写数字识别的原理、方法进行了深入的研究，提出的识别技术精度较高，可以达到实际应用的要求。本论文成果对于信息的自动化、国民经济信息网络的推广具有重要意义，对于手写汉字识别的研究具有很高的参考价值。
The recognition research of handwritten character sometimes cold and sometimes hot Over the past dozens of years, people propose a lot of recognition method and recognition technology, but because the key technology of recognition was not solved, in addition, such reasons of the aspect as the products make a reservation, which made the existing recognition system be unable to meet the requirement of practical application. There are factors in many aspects, such as theoretical research and technology, etc. Handwritten digit recognition is one branch of character recognition.Though it is simple, there is greater practical value. At present, zip codes of are extensively used in letter communicating in our country. Automatically sorting letter with handwritten digital recognition technology have very heavy meaning to lightening post worker's manual sorting. Handwritten numeral has 10 kinds only, but in a lot of situations, recognition precision have very high expectations, in addition, the change of the handwrit
ten numeral is very large. In this case, it is not so easy making sure that high-accuracy recognition.
This thesis explains the necessity of the character recognition technology of the computer at first, describe the meaning in which the handwritten numeral discerns; Pretreatment technology of handwritten numeral recognition, including two value, line segmentation, word segmentation smooth, removing noising,standardization and thinning are discussed Two value concretely discusses whole threshold value, some threshold value, dynamic threshold value and utilize space information to carry on threshold, which are several kinds of common method of choosing threshold value, especially utilize space information to carry on threshold value is describe in detail; adopting to the foundation of thinning based on mathematics morphology, Thinning algorithm of serials same and thinning algorithm of protecting shape are discussed; Afterwards, according to principle's diagram of the on-line character recognition, by analyzing the structure feature of the handwritten numeral, this thesis has proposed the online recognition te
chnology of the free handwritten numeral based on the stroke feature and the online recognition technology of the free handwritten numeral based on the multistage classifying device.
Detail narrated noise removing, stroke characteristic definition and discernment, distance criterion of whole word match; then under the foundation of handwritten numeral segmentation, off-line handwritten numeral recognition is researched. Especially minimum distance classifying device, tree classifying device and adaptive resonance (ART) network classifying device is discussed At the same time, believes degree analyses are introduced to integrate a lot of classifying devices; At the end, the typical application of the handwritten numeral recognition was briefly narrated, its application in extensive data statistics, financial affairs, tax, finance and mail sorting have been explored.
This thesis deeply researched into the principle and method of handwritten numeral recognition. The recognition technology putted forward is relatively high in precision, can meet the requirement of practical application. This achievement of thesis has significant meaning to the automation of information and popularization of national economic information network, and has very high reference value to the research of handwritten Chinese character recognition.
本论文首先阐述计算机字符识别技术的必要性，论述手写数字识别的意义；接着讨论了手写数字识别的预处理技术，包括二值化、行字切分、平滑、去噪声、规范化和细化等。二值化时对整体阈值二值化、局部阈值二值化、动态阈值二值化和利用空间信息进行阈值选取几种常用的阈值选取方法进行讨论，特别对利用空间信息进行阈值选取进行了详细论述；在对通过对基于数学形态学的细化的基础上，讨论序贯同伦形态细化算法和保形的快速形态细化算法；然后依据联机字符识别原理框图，分析了手写数字的结构特点，提出了基于笔划特征的任意手写数字在线识别技术和基于多级分类器任意手写数字在线识别技术，对其中涉及的笔划识别前的噪声处理、笔划间特征量的定义及识别、整字匹配的距离准则进行了详细叙述；继而在对手写数字的分割的基础下对脱机手写数字识别进行了研究，对基于最小距离分类器字符识别、基于树分类器的字符识别、基于自适应共振(ART)网络的字符识别分别进行了详细讨论，并引入置信度分析将多个分类器进行了混合集成；最后简单阐述了手写数字识别的典型应用，对其在大规模数据统计、财务、税务、金融及邮件分拣中的应用进行了探索。
本论文对手写数字识别的原理、方法进行了深入的研究，提出的识别技术精度较高，可以达到实际应用的要求。本论文成果对于信息的自动化、国民经济信息网络的推广具有重要意义，对于手写汉字识别的研究具有很高的参考价值。
The recognition research of handwritten character sometimes cold and sometimes hot Over the past dozens of years, people propose a lot of recognition method and recognition technology, but because the key technology of recognition was not solved, in addition, such reasons of the aspect as the products make a reservation, which made the existing recognition system be unable to meet the requirement of practical application. There are factors in many aspects, such as theoretical research and technology, etc. Handwritten digit recognition is one branch of character recognition.Though it is simple, there is greater practical value. At present, zip codes of are extensively used in letter communicating in our country. Automatically sorting letter with handwritten digital recognition technology have very heavy meaning to lightening post worker's manual sorting. Handwritten numeral has 10 kinds only, but in a lot of situations, recognition precision have very high expectations, in addition, the change of the handwrit
ten numeral is very large. In this case, it is not so easy making sure that high-accuracy recognition.
This thesis explains the necessity of the character recognition technology of the computer at first, describe the meaning in which the handwritten numeral discerns; Pretreatment technology of handwritten numeral recognition, including two value, line segmentation, word segmentation smooth, removing noising,standardization and thinning are discussed Two value concretely discusses whole threshold value, some threshold value, dynamic threshold value and utilize space information to carry on threshold, which are several kinds of common method of choosing threshold value, especially utilize space information to carry on threshold value is describe in detail; adopting to the foundation of thinning based on mathematics morphology, Thinning algorithm of serials same and thinning algorithm of protecting shape are discussed; Afterwards, according to principle's diagram of the on-line character recognition, by analyzing the structure feature of the handwritten numeral, this thesis has proposed the online recognition te
chnology of the free handwritten numeral based on the stroke feature and the online recognition technology of the free handwritten numeral based on the multistage classifying device.
Detail narrated noise removing, stroke characteristic definition and discernment, distance criterion of whole word match; then under the foundation of handwritten numeral segmentation, off-line handwritten numeral recognition is researched. Especially minimum distance classifying device, tree classifying device and adaptive resonance (ART) network classifying device is discussed At the same time, believes degree analyses are introduced to integrate a lot of classifying devices; At the end, the typical application of the handwritten numeral recognition was briefly narrated, its application in extensive data statistics, financial affairs, tax, finance and mail sorting have been explored.
This thesis deeply researched into the principle and method of handwritten numeral recognition. The recognition technology putted forward is relatively high in precision, can meet the requirement of practical application. This achievement of thesis has significant meaning to the automation of information and popularization of national economic information network, and has very high reference value to the research of handwritten Chinese character recognition.
引文
[1]GovindanVK, Character recognition—areview.Pattem Recognition, 1991,23(7):671～683
[2]Lam L,Suen C Y. Structural classification and relaxation matching of totally unconstrained handwritten ZIP—code number. Pattern Reeognition, 1995,21(1):19～31
[3]Suen C Y,Nadal C,Legault R,etal. Computer recognition of unconstrainted handwritten numerals.Proc IEEE, 1992,80(7): 1162～1180
[4]洪沁，何振亚．手写体数字的神经网络识别方法．模式识别与人工智能．1994,7(1)：66～70
[5]郝红卫，戴汝为．人机结合的集成方法及其在字符识别中的应用．模式识别与人工智能，1996,9(1)：10～20
[6]张炘中．汉字识别技术．清华大学出版社 1992
[7]吴佑寿，丁晓青．汉字识别—原理方法与实现．高等教育出版社，1992
[8]吴佑寿．教电脑识字—浅谈汉字识别．清华大学出版社，2000
[9]张炘中．计算机汉字自动识别技术．中国印刷，26期，1989
[10]潘保昌．浮动模板法．计算机学报，1998，(6)：469～477
[11]GAADER P. Recognition of handwritten digits using template and model matching[J]. Pattern recognition,1991,24(5): 421～431
[12]MORI S. Historical review of theory and practice of handwritten character recognition[A].In:Sebastian,Impedove,Fundamentals in Handwritten Recognition. Berlin: Springer—erlag,1994,43～69
[13]SUEN C Y, Legault R,Nadal Cetal. Building a new generation of handwriting recognition system[J]. Pattern Recognition Letters, 1993,14(4):303～315
[14]Mai T, Suen C Y.A generalized knowledge—based system for recognition of unconstrained handwritten numerals, IEEE. Trans SystMan Cybern, 1990,20(4):835～848
[15]杜昊，张立明．基于模糊特征抽取的神经网络手写数字识别方法．见：第三届中国神经网络学术大会论文集，第三届中国神经网络学术大会．西安，1993：837～878
[16]Lee S,ChoiY. Translation,rotation,scaling and distortion invafiant recognition of handwritten nuerals.IJCNN, 1992;2:185～196
[17]洪沁，伺振亚．手写数字的神经网络分类方法模式识别与人工智能，1994；7(1)：66～71
[18]Ye M,Fan J B,Jin F.A hybrid method for recognizing handwritten number.In:Proe.of IEEE int. Conf. On Neural Networks(Vol.Ⅶ), IEEE World Congress on Computational
intelligence,Florida,Orlando, 1994,Piseataway, NJ:IEEE, 1994:4269～4277
[19]李榕，何大可，杨宗凯，姚天任．分形理论和神经网络在手写数字识别中的应用．神经网络理论及应用94'最新进展．武汉：华中理工大学出版社．1994：383～386
[20]朱学芳，石青云，程民德．用BP网识别无限制手写数字的研究神经网络理论及应用94'最新进民武汉：华中理工大学出版社．1994：379～382
[21]谢光毅，钟义信．神经网络用于手写体数字识别．模式识别与人工智能，1994；7(4)：334～337
[22]刘元来，李炳成，马颂德．基于曲线矩的手写体数字识别．模式识别与人工智能，1995；8(2)：153～159
[23]吕岳，芮剑明，余德华．邮政编码数字识别系统的设计与实现．计算机工程与应用,1999；6：128～129
[24]王正群．手写汉字识别研究，[博士学位论文]，南京：南京理工大学，2001．8
[25]余松煜，周源华，吴时光．数字图像处理，北京：电子工业出版社，1989
[26]A. Rosenfeld and A. C.kak, "Difital Processing", Vol.2,Academic Press, 1982
[27]R. M. Haralick and L. G. Shapiro ,Survey: image segmentation techniques, CVGIP, Vol.29, 1985, PP, 100～132
[28]D.P. Panda and A. Rosenfeld, Imagesegrnentation by pixel classification in (gray level, edgevalue) space, IEEE Trans. Comput.C—27, 1978, PP, 875～879
[29]胡家忠，计算机文字识别技术，北京：气象文学出版社，1994
[30]王积分，张新荣．计算机图像识别．北京：中国铁道出版社，1988
[31]Scrra J. Image Analysis and Mathematical Morphology. London: Academic Press. 1982
[32]盛业华，郭达志．一种保形的数字形态学细化算法。中国矿业大学学报，1997，26(3)：63～66
[33]Jang B k, Chin R T. analysis of thinning algorithms using mathematical morphology. IEEE Trans PAMI, 1990,26(3): 63～66
[34]H. Yamada, T. Saito, K.Yamamoto, "Line density equalization—a nonlinear normalization for correlation method" ,Trans, IECE (日本电子通信学会论文志), Vol.J67-D,No.4, PP, 1379～1383,1984.
[35]J. Tsuktumo, H. Tanaks, "Classification of handprinted Chinese characters using nonlinear normalization and correlation methods, Proc. 9th Int. Conf.. Pattern Recogn, PP,168～171, 1988.
[36]H. Yamada, K. Yamamoto, T.Saito, "a nonlinear normalization method for handprinted Kanji character recognition—line density equalization", Pattern Recogn., pp,1023～1029,1990.
[37]S.W. Lee, J. S. Park, "Nonfinear shape normnliztion methods for the recognition of large-set handwritten characters", Pattem Recogn, Vol.27, pp,895～902,1994
[38]边肈祺，张学工等．模式识别(第二版)，北京：清华大学出版社，2000．
[39]吕风军，数字图像处理编程入门，北京：金华大学出版社，1999．9
[40]胡正平，卡片自动录入系统算法的研究．燕山大学硕士学位论文．1999．
[41]王煦法，庄镇泉，王东升．C语言图像处理程序设计．安徽：中国科学技术大学出版社，1994．
[42]C.H. Leung. etc. A Knowledge—Based stroke--Matching Method for Chinese Character Recognition. IEEE Trans. On SMC, Vol. 21, No.1,1987:993～1003.
[43]Cheng, Fang—Hsuan. Multi-stroke relaxation matching method for handwritten Chinese Character recognition. Pattern Recogniton. 1998 Vol. 31, No.4 Elsevier Sci Ltd 401～410.
[44]Gaader P. Recognition of handwritten digits using template and model matching[J]. Pattern recognition, 1991,24(5): 421～431
[45]Mori S. Historieal review of theory and practicee of handwritten character recognition[A]. In: Sebastian, Impedovo. Fundamentals in Handwritten Recognition. Berlin: Springer--eflag, 1994 : 43～69
[46]Suen C Y, Legault R, Nadal Cetal. Building a mew generation of handwriting recognition system[J]. Pattern Recogniton Letters, 1993, 14(4): 303～315
[47]Weidenmen W E. A comparison of a nearest neighbor elassifyer and a neural network for numeric handprint character recognition[A]. In: Proc UCNN, 1989,117～120
[48]Almallin H, Yamaguchi S.Amethod of recognition of arabic cursive handwriting[J], IEEE Trans Pattern and Machine Intelligence, 1987, PAMI-9(5): 715～733
[49]赵学军．手写数学表达式自动识别的研究[D]．重庆：重庆大学光电信息学院，1998
[50]Richard G.Casey and Erie Lecolinet, "A Survey of Methods and Strategies in Character Segmentation", IEEE Trans on Pattern Analysis and Machine Intelligence , Vol. 18, No.7,July,1998
[51]Secong, WhanLee, "A new Methodology for Gray-Scale Character Segmentation and Recognition", IEEE Trans on Pattern Analysis and Machine Intelligence, Vol. 18,No. 10,1996
[52]M.H. ter Brugge etc Lieense Platc Recognition Using DTCNNS, 1998 Fifth IEEE, international Workshop Cellular Neural Networks and their Application, London, England, April 1998:14～17
[53]Shridhar M. Badreeldin A," Context-directed segmentation algodthrn for handwritten numeral strings",Image Vision Compute. 1987,5:3--8
[54]Suters M., Yan H., "Connected handwritten digit separation using external boundary curvature:, Joural of Elechtronic Imaging, 1994, 3(3):251～256
[55]Fenrich R., "Segmentation of automatically located handwritten numeric strings", Forontiers in
Handwriting Recognition, 1992, 47～59
[56] Fujisawa H.,Naknamo Y., Kurina K., "Segmentation of automatically located handwritten numeric strings", Frontiers in Handwriting recognition, 1992,47～59
[57] Nishida H., Moil S. "Model-based split and merge strings". Adv. Structure Syntactic Pattern Recognition 1992,5:301～309
[58] Zhao Z., Suters M., Yan H., Connected handwritten digit separation by optimal contour partition. Proc. ConfDigit Image Computing Techniques and Applications, 786～793,1993
[59] Westall J. M. ,Narasimha M. S.,"Vertex directed segmentation ofhandwritten numerals", Pattern Recognition, 1993,26(10):1473～1486
[60] Strathy N. W., Suen C. Y., Krzyzk A. "Segmentation of handwritten digits using contour features". Proc. 2nd Int't. ConfDoeument Analysis and Recognition, 1993,577～780
[61] KirnuraF,Shridhar M. "Segmentation-recognition algorithm for Zip code field recognition",Mach. Vis. Appl. 1992, 5:199～210
[62] Lu Z., Chi Z., Siu W. C., etc. "A background-thinning-based approach for separating and Recognizing connected handwritten digit strings",Pattern Recognition, 1999,32(6): 921～933
[63] 董林，陈锡先，唐远炎，吴善培．一种新的手写体数字识别方法．北京邮电大学学报．1997．3
[64] 赵健龙．基于神经网络的集装箱字符识别．北京理工大学硕士学位论文．2002．2：32～38
[65] 周春光等．一种改进的ART1算法及其在人脸识别中的应用．小型微型计算机系统．1999．10
[66] 林桦，王正光．ART网在地图彩色分类中的应用．西安电子科技大学学报．1994．12
[67] 史永平等．ART1神经网络模型在成组技术中的应用．数据采集与处理．1995．3
[68] Battiti R, Colla A, "Democracy in Neural Nets Voting Schemes for Classification", Neural Networks, 1994, 7
[2]Lam L,Suen C Y. Structural classification and relaxation matching of totally unconstrained handwritten ZIP—code number. Pattern Reeognition, 1995,21(1):19～31
[3]Suen C Y,Nadal C,Legault R,etal. Computer recognition of unconstrainted handwritten numerals.Proc IEEE, 1992,80(7): 1162～1180
[4]洪沁，何振亚．手写体数字的神经网络识别方法．模式识别与人工智能．1994,7(1)：66～70
[5]郝红卫，戴汝为．人机结合的集成方法及其在字符识别中的应用．模式识别与人工智能，1996,9(1)：10～20
[6]张炘中．汉字识别技术．清华大学出版社 1992
[7]吴佑寿，丁晓青．汉字识别—原理方法与实现．高等教育出版社，1992
[8]吴佑寿．教电脑识字—浅谈汉字识别．清华大学出版社，2000
[9]张炘中．计算机汉字自动识别技术．中国印刷，26期，1989
[10]潘保昌．浮动模板法．计算机学报，1998，(6)：469～477
[11]GAADER P. Recognition of handwritten digits using template and model matching[J]. Pattern recognition,1991,24(5): 421～431
[12]MORI S. Historical review of theory and practice of handwritten character recognition[A].In:Sebastian,Impedove,Fundamentals in Handwritten Recognition. Berlin: Springer—erlag,1994,43～69
[13]SUEN C Y, Legault R,Nadal Cetal. Building a new generation of handwriting recognition system[J]. Pattern Recognition Letters, 1993,14(4):303～315
[14]Mai T, Suen C Y.A generalized knowledge—based system for recognition of unconstrained handwritten numerals, IEEE. Trans SystMan Cybern, 1990,20(4):835～848
[15]杜昊，张立明．基于模糊特征抽取的神经网络手写数字识别方法．见：第三届中国神经网络学术大会论文集，第三届中国神经网络学术大会．西安，1993：837～878
[16]Lee S,ChoiY. Translation,rotation,scaling and distortion invafiant recognition of handwritten nuerals.IJCNN, 1992;2:185～196
[17]洪沁，伺振亚．手写数字的神经网络分类方法模式识别与人工智能，1994；7(1)：66～71
[18]Ye M,Fan J B,Jin F.A hybrid method for recognizing handwritten number.In:Proe.of IEEE int. Conf. On Neural Networks(Vol.Ⅶ), IEEE World Congress on Computational
intelligence,Florida,Orlando, 1994,Piseataway, NJ:IEEE, 1994:4269～4277
[19]李榕，何大可，杨宗凯，姚天任．分形理论和神经网络在手写数字识别中的应用．神经网络理论及应用94'最新进展．武汉：华中理工大学出版社．1994：383～386
[20]朱学芳，石青云，程民德．用BP网识别无限制手写数字的研究神经网络理论及应用94'最新进民武汉：华中理工大学出版社．1994：379～382
[21]谢光毅，钟义信．神经网络用于手写体数字识别．模式识别与人工智能，1994；7(4)：334～337
[22]刘元来，李炳成，马颂德．基于曲线矩的手写体数字识别．模式识别与人工智能，1995；8(2)：153～159
[23]吕岳，芮剑明，余德华．邮政编码数字识别系统的设计与实现．计算机工程与应用,1999；6：128～129
[24]王正群．手写汉字识别研究，[博士学位论文]，南京：南京理工大学，2001．8
[25]余松煜，周源华，吴时光．数字图像处理，北京：电子工业出版社，1989
[26]A. Rosenfeld and A. C.kak, "Difital Processing", Vol.2,Academic Press, 1982
[27]R. M. Haralick and L. G. Shapiro ,Survey: image segmentation techniques, CVGIP, Vol.29, 1985, PP, 100～132
[28]D.P. Panda and A. Rosenfeld, Imagesegrnentation by pixel classification in (gray level, edgevalue) space, IEEE Trans. Comput.C—27, 1978, PP, 875～879
[29]胡家忠，计算机文字识别技术，北京：气象文学出版社，1994
[30]王积分，张新荣．计算机图像识别．北京：中国铁道出版社，1988
[31]Scrra J. Image Analysis and Mathematical Morphology. London: Academic Press. 1982
[32]盛业华，郭达志．一种保形的数字形态学细化算法。中国矿业大学学报，1997，26(3)：63～66
[33]Jang B k, Chin R T. analysis of thinning algorithms using mathematical morphology. IEEE Trans PAMI, 1990,26(3): 63～66
[34]H. Yamada, T. Saito, K.Yamamoto, "Line density equalization—a nonlinear normalization for correlation method" ,Trans, IECE (日本电子通信学会论文志), Vol.J67-D,No.4, PP, 1379～1383,1984.
[35]J. Tsuktumo, H. Tanaks, "Classification of handprinted Chinese characters using nonlinear normalization and correlation methods, Proc. 9th Int. Conf.. Pattern Recogn, PP,168～171, 1988.
[36]H. Yamada, K. Yamamoto, T.Saito, "a nonlinear normalization method for handprinted Kanji character recognition—line density equalization", Pattern Recogn., pp,1023～1029,1990.
[37]S.W. Lee, J. S. Park, "Nonfinear shape normnliztion methods for the recognition of large-set handwritten characters", Pattem Recogn, Vol.27, pp,895～902,1994
[38]边肈祺，张学工等．模式识别(第二版)，北京：清华大学出版社，2000．
[39]吕风军，数字图像处理编程入门，北京：金华大学出版社，1999．9
[40]胡正平，卡片自动录入系统算法的研究．燕山大学硕士学位论文．1999．
[41]王煦法，庄镇泉，王东升．C语言图像处理程序设计．安徽：中国科学技术大学出版社，1994．
[42]C.H. Leung. etc. A Knowledge—Based stroke--Matching Method for Chinese Character Recognition. IEEE Trans. On SMC, Vol. 21, No.1,1987:993～1003.
[43]Cheng, Fang—Hsuan. Multi-stroke relaxation matching method for handwritten Chinese Character recognition. Pattern Recogniton. 1998 Vol. 31, No.4 Elsevier Sci Ltd 401～410.
[44]Gaader P. Recognition of handwritten digits using template and model matching[J]. Pattern recognition, 1991,24(5): 421～431
[45]Mori S. Historieal review of theory and practicee of handwritten character recognition[A]. In: Sebastian, Impedovo. Fundamentals in Handwritten Recognition. Berlin: Springer--eflag, 1994 : 43～69
[46]Suen C Y, Legault R, Nadal Cetal. Building a mew generation of handwriting recognition system[J]. Pattern Recogniton Letters, 1993, 14(4): 303～315
[47]Weidenmen W E. A comparison of a nearest neighbor elassifyer and a neural network for numeric handprint character recognition[A]. In: Proc UCNN, 1989,117～120
[48]Almallin H, Yamaguchi S.Amethod of recognition of arabic cursive handwriting[J], IEEE Trans Pattern and Machine Intelligence, 1987, PAMI-9(5): 715～733
[49]赵学军．手写数学表达式自动识别的研究[D]．重庆：重庆大学光电信息学院，1998
[50]Richard G.Casey and Erie Lecolinet, "A Survey of Methods and Strategies in Character Segmentation", IEEE Trans on Pattern Analysis and Machine Intelligence , Vol. 18, No.7,July,1998
[51]Secong, WhanLee, "A new Methodology for Gray-Scale Character Segmentation and Recognition", IEEE Trans on Pattern Analysis and Machine Intelligence, Vol. 18,No. 10,1996
[52]M.H. ter Brugge etc Lieense Platc Recognition Using DTCNNS, 1998 Fifth IEEE, international Workshop Cellular Neural Networks and their Application, London, England, April 1998:14～17
[53]Shridhar M. Badreeldin A," Context-directed segmentation algodthrn for handwritten numeral strings",Image Vision Compute. 1987,5:3--8
[54]Suters M., Yan H., "Connected handwritten digit separation using external boundary curvature:, Joural of Elechtronic Imaging, 1994, 3(3):251～256
[55]Fenrich R., "Segmentation of automatically located handwritten numeric strings", Forontiers in
Handwriting Recognition, 1992, 47～59
[56] Fujisawa H.,Naknamo Y., Kurina K., "Segmentation of automatically located handwritten numeric strings", Frontiers in Handwriting recognition, 1992,47～59
[57] Nishida H., Moil S. "Model-based split and merge strings". Adv. Structure Syntactic Pattern Recognition 1992,5:301～309
[58] Zhao Z., Suters M., Yan H., Connected handwritten digit separation by optimal contour partition. Proc. ConfDigit Image Computing Techniques and Applications, 786～793,1993
[59] Westall J. M. ,Narasimha M. S.,"Vertex directed segmentation ofhandwritten numerals", Pattern Recognition, 1993,26(10):1473～1486
[60] Strathy N. W., Suen C. Y., Krzyzk A. "Segmentation of handwritten digits using contour features". Proc. 2nd Int't. ConfDoeument Analysis and Recognition, 1993,577～780
[61] KirnuraF,Shridhar M. "Segmentation-recognition algorithm for Zip code field recognition",Mach. Vis. Appl. 1992, 5:199～210
[62] Lu Z., Chi Z., Siu W. C., etc. "A background-thinning-based approach for separating and Recognizing connected handwritten digit strings",Pattern Recognition, 1999,32(6): 921～933
[63] 董林，陈锡先，唐远炎，吴善培．一种新的手写体数字识别方法．北京邮电大学学报．1997．3
[64] 赵健龙．基于神经网络的集装箱字符识别．北京理工大学硕士学位论文．2002．2：32～38
[65] 周春光等．一种改进的ART1算法及其在人脸识别中的应用．小型微型计算机系统．1999．10
[66] 林桦，王正光．ART网在地图彩色分类中的应用．西安电子科技大学学报．1994．12
[67] 史永平等．ART1神经网络模型在成组技术中的应用．数据采集与处理．1995．3
[68] Battiti R, Colla A, "Democracy in Neural Nets Voting Schemes for Classification", Neural Networks, 1994, 7
© 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 |