Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227828
M. Fairhurst
Document security is an increasingly importantelement in the multi-faceted discipline ofdocument processing, and authentication ofindividual identity will play an increasinglyimportant future role in relation to questions ofdocument ownership, identity andconfidentiality. Biometrics-based techniques areemerging as key elements in the drive to addresssecurity and confidentiality in an effective way,yet past experience suggests that there are manypractical issues yet to be resolved if biometrictechnologies are to fulfill their potential in thedocument processing field. This paper addressessome aspects of biometric processing which arebecoming increasing priorities, and suggestshow a greater engagement of the documentprocessing community can help to bring aboutrefinements to existing approaches to biometricidentity checking.
{"title":"Document identity, authentication and ownership: the future of biometric verification","authors":"M. Fairhurst","doi":"10.1109/ICDAR.2003.1227828","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227828","url":null,"abstract":"Document security is an increasingly importantelement in the multi-faceted discipline ofdocument processing, and authentication ofindividual identity will play an increasinglyimportant future role in relation to questions ofdocument ownership, identity andconfidentiality. Biometrics-based techniques areemerging as key elements in the drive to addresssecurity and confidentiality in an effective way,yet past experience suggests that there are manypractical issues yet to be resolved if biometrictechnologies are to fulfill their potential in thedocument processing field. This paper addressessome aspects of biometric processing which arebecoming increasing priorities, and suggestshow a greater engagement of the documentprocessing community can help to bring aboutrefinements to existing approaches to biometricidentity checking.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133550053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227776
H. Legal-Ayala, J. Facon
This article describes a new segmentation bythresholding approach based on learning. The methodconsists in learning to threshold correctly submitting bothan image and its ideal thresholded version. From thisstage it is generated a decision matrix for each pixel andeach gray level that is re-utilized at the moment of thenew images segmentation. The new image is thresholdedby means of a new strategy based on the nearestneighbors, that seeks, for each pixel of this new image,the best solution in the decision matrix. Performed testson handwritten documents showed promising results. Interms of quality of the results, the developed technique isequal or superior to the traditional segmentation bythresholding techniques, with the advantage that the onediscussed here does not requires the use of heuristicparameters.
{"title":"Image segmentation by learning approach","authors":"H. Legal-Ayala, J. Facon","doi":"10.1109/ICDAR.2003.1227776","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227776","url":null,"abstract":"This article describes a new segmentation bythresholding approach based on learning. The methodconsists in learning to threshold correctly submitting bothan image and its ideal thresholded version. From thisstage it is generated a decision matrix for each pixel andeach gray level that is re-utilized at the moment of thenew images segmentation. The new image is thresholdedby means of a new strategy based on the nearestneighbors, that seeks, for each pixel of this new image,the best solution in the decision matrix. Performed testson handwritten documents showed promising results. Interms of quality of the results, the developed technique isequal or superior to the traditional segmentation bythresholding techniques, with the advantage that the onediscussed here does not requires the use of heuristicparameters.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117259280","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227850
K. Kise, Yasuo Miki, Keinosuke Matsumoto
In order to realize seamless integration of paper andelectronic documents, it is at least necessary to assure errorfree conversion from one to the other. In general, theconversion from paper to electronic documents is the taskof document image understanding. Although its researchhas made remarkable progress, it is still a hard task withoutlimiting the type of documents. This paper presents acompletely different approach to this task on condition thatprinted documents have their originals in electronic form.The proposed method employs fine dots to represent dataof electronic documents and places the dots on white space(backgrounds) of pages. Since the data is encoded with anerror correcting code, it is guaranteed to be correctly recoveredfrom the scanned images of documents. Experimentalresults show that a page with normal foreground objects(characters and other things) can contain more than 4KB ofdata, even when errors up to 20% of the data are permitted.
{"title":"Stippling data on backgrounds of pages-toward seamless integration of paper and electronic documents","authors":"K. Kise, Yasuo Miki, Keinosuke Matsumoto","doi":"10.1109/ICDAR.2003.1227850","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227850","url":null,"abstract":"In order to realize seamless integration of paper andelectronic documents, it is at least necessary to assure errorfree conversion from one to the other. In general, theconversion from paper to electronic documents is the taskof document image understanding. Although its researchhas made remarkable progress, it is still a hard task withoutlimiting the type of documents. This paper presents acompletely different approach to this task on condition thatprinted documents have their originals in electronic form.The proposed method employs fine dots to represent dataof electronic documents and places the dots on white space(backgrounds) of pages. Since the data is encoded with anerror correcting code, it is guaranteed to be correctly recoveredfrom the scanned images of documents. Experimentalresults show that a page with normal foreground objects(characters and other things) can contain more than 4KB ofdata, even when errors up to 20% of the data are permitted.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116721495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227822
Xiaofan Lin
This paper introduces a novel journal splittingalgorithm. It takes full advantage of various kinds ofinformation such as text match, layout and page numbers.The core procedure is a highly efficient text-miningalgorithm, which detects the matched phrases between thecontent pages and the title pages of individual articles.Experiments show that this algorithm is robust and ableto split a wide range of journals, magazines and books.
{"title":"Text-mining based journal splitting","authors":"Xiaofan Lin","doi":"10.1109/ICDAR.2003.1227822","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227822","url":null,"abstract":"This paper introduces a novel journal splittingalgorithm. It takes full advantage of various kinds ofinformation such as text match, layout and page numbers.The core procedure is a highly efficient text-miningalgorithm, which detects the matched phrases between thecontent pages and the title pages of individual articles.Experiments show that this algorithm is robust and ableto split a wide range of journals, magazines and books.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116961984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227805
E. Tapia, R. Rojas
In this article, we present a system for the recognition ofon-line handwritten mathematical formulas which is usedin the electronic chalkboard (E-chalk), a multimedia systemfor distance-teaching. We discuss the classification of symbolsand the construction of the tree of spatial relationshipsamong them. The classification is based on support vectormachines and the construction of formulas is based onbaseline structure analysis.
{"title":"Recognition of on-line handwritten mathematical formulas in the E-chalk system","authors":"E. Tapia, R. Rojas","doi":"10.1109/ICDAR.2003.1227805","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227805","url":null,"abstract":"In this article, we present a system for the recognition ofon-line handwritten mathematical formulas which is usedin the electronic chalkboard (E-chalk), a multimedia systemfor distance-teaching. We discuss the classification of symbolsand the construction of the tree of spatial relationshipsamong them. The classification is based on support vectormachines and the construction of formulas is based onbaseline structure analysis.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116525650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227669
Sriram Ramachandran, R. Kashi
There have been recent improvements in document technologies like the standardization of object interfaces to access and manipulate the properties of Web documents. There has also been significant progress in pen based computing for recognition of digital ink in desktops, tablets and handheld devices. These have necessitated a need for further research on annotation architectures for digital documents, specifically pen-based annotation systems. This paper presents an attempt to leverage the new standards of DHTML and W3C DOM that are being gradually implemented by popular browsers, to build a prototype of an ink annotation system with common components across browsers. One of the primary goals in this study is to semantically link ink data with underlying document elements like text and images. The system has three components: a) ink capture and rendering b) Ink Understanding, which recognizes and associates ink with the underlying document; and c) Ink storage and retrieval.
{"title":"An architecture for ink annotations on Web documents","authors":"Sriram Ramachandran, R. Kashi","doi":"10.1109/ICDAR.2003.1227669","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227669","url":null,"abstract":"There have been recent improvements in document technologies like the standardization of object interfaces to access and manipulate the properties of Web documents. There has also been significant progress in pen based computing for recognition of digital ink in desktops, tablets and handheld devices. These have necessitated a need for further research on annotation architectures for digital documents, specifically pen-based annotation systems. This paper presents an attempt to leverage the new standards of DHTML and W3C DOM that are being gradually implemented by popular browsers, to build a prototype of an ink annotation system with common components across browsers. One of the primary goals in this study is to semantically link ink data with underlying document elements like text and images. The system has three components: a) ink capture and rendering b) Ink Understanding, which recognizes and associates ink with the underlying document; and c) Ink storage and retrieval.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115432751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227778
Stefano Baldi, S. Marinai, G. Soda
In this paper we describe a method for the expansionof training sets made by XY trees representing page layout.This approach is appropriate when dealing with page classificationbased on MXY tree page representations. The basicidea is the use of tree grammars to model the variationsin the tree which are caused by segmentation algorithms.A set of general grammatical rules are defined and used toexpand the training set. Pages are classified with a k - nnapproach where the distance between pages is computed bymeans of tree-edit distance.
{"title":"Using tree-grammars for training set expansion in page classi .cation","authors":"Stefano Baldi, S. Marinai, G. Soda","doi":"10.1109/ICDAR.2003.1227778","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227778","url":null,"abstract":"In this paper we describe a method for the expansionof training sets made by XY trees representing page layout.This approach is appropriate when dealing with page classificationbased on MXY tree page representations. The basicidea is the use of tree grammars to model the variationsin the tree which are caused by segmentation algorithms.A set of general grammatical rules are defined and used toexpand the training set. Pages are classified with a k - nnapproach where the distance between pages is computed bymeans of tree-edit distance.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114690657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227774
Tomoyuki Hamamura, H. Mizutani, Bunpei Irie
In this paper, a new method of composing a multi-classclassifier using pairwise classifiers is proposed. A"Resemblance Model" is exploited to calculate aposteriori probability for combining pairwise classifiers.We proved the validity of this model by usingapproximation of a posteriori probability formula. Usingthis theory, we can obtain the optimal decision. Anexperimental result of handwritten numeral recognition ispresented, supporting the effectiveness of our method.
{"title":"A multiclass classification method based on multiple pairwise classifiers","authors":"Tomoyuki Hamamura, H. Mizutani, Bunpei Irie","doi":"10.1109/ICDAR.2003.1227774","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227774","url":null,"abstract":"In this paper, a new method of composing a multi-classclassifier using pairwise classifiers is proposed. A\"Resemblance Model\" is exploited to calculate aposteriori probability for combining pairwise classifiers.We proved the validity of this model by usingapproximation of a posteriori probability formula. Usingthis theory, we can obtain the optimal decision. Anexperimental result of handwritten numeral recognition ispresented, supporting the effectiveness of our method.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114852357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227666
A. Schenker, Mark Last, H. Bunke, A. Kandel
In this paper we describe work relating to classification of Web documents using a graph-based model instead of the traditional vector-based model for document representation. We compare the classification accuracy of the vector model approach using the k-nearest neighbor (k-NN) algorithm to a novel approach which allows the use of graphs for document representation in the k-NN algorithm. The proposed method is evaluated on three different Web document collections using the leave-one-out approach for measuring classification accuracy. The results show that the graph-based k-NN approach can outperform traditional vector-based k-NN methods in terms of both accuracy and execution time.
{"title":"Classification of Web documents using a graph model","authors":"A. Schenker, Mark Last, H. Bunke, A. Kandel","doi":"10.1109/ICDAR.2003.1227666","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227666","url":null,"abstract":"In this paper we describe work relating to classification of Web documents using a graph-based model instead of the traditional vector-based model for document representation. We compare the classification accuracy of the vector model approach using the k-nearest neighbor (k-NN) algorithm to a novel approach which allows the use of graphs for document representation in the k-NN algorithm. The proposed method is evaluated on three different Web document collections using the leave-one-out approach for measuring classification accuracy. The results show that the graph-based k-NN approach can outperform traditional vector-based k-NN methods in terms of both accuracy and execution time.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"2009 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128232333","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227859
Sanaul Hoque, H. Selim, G. Howells, M. Fairhurst, F. Deravi
A novel strategy for the representation and manipulationof distributed documents, potentially complex andheterogeneous, is presented in this paper. The documentunder the proposed model is represented in a hierarchicalstructure. Associated metadata' describes the flexiblehierarchy with the scope of dynamically restructuring thetree at runtime. All useful functionals can also be includedwithin the hierarchy to minimize reliance on externalprograms in manipulating sensitive data. Thisgives the proposed model two key properties: generality(capable of representing any document format includingfuture innovations) and autonomy (non-reliance on externalprograms). The model also allows incorporation ofadditional features for security and access control. Biometricperson authentication measures are introduced. Abrief example illustrates the key ideas.
{"title":"SAGENT: a novel technique for document modeling for secure access and distribution","authors":"Sanaul Hoque, H. Selim, G. Howells, M. Fairhurst, F. Deravi","doi":"10.1109/ICDAR.2003.1227859","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227859","url":null,"abstract":"A novel strategy for the representation and manipulationof distributed documents, potentially complex andheterogeneous, is presented in this paper. The documentunder the proposed model is represented in a hierarchicalstructure. Associated metadata' describes the flexiblehierarchy with the scope of dynamically restructuring thetree at runtime. All useful functionals can also be includedwithin the hierarchy to minimize reliance on externalprograms in manipulating sensitive data. Thisgives the proposed model two key properties: generality(capable of representing any document format includingfuture innovations) and autonomy (non-reliance on externalprograms). The model also allows incorporation ofadditional features for security and access control. Biometricperson authentication measures are introduced. Abrief example illustrates the key ideas.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129488369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：