Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227677
L. Wendling, S. Tabbone
A new way to detect arrows in line drawings is proposed in this paper. Our approach is based on the definition of the structure of such a symbol. Signatures of angular areas are computed and axiomatic properties and geometric characteristics are checked using the Choquet integral. Finally an experimental application on line-drawing documents shows the interest of our approach.
{"title":"Recognition of arrows in line drawings based on the aggregation of geometric criteria using the Choquet integral","authors":"L. Wendling, S. Tabbone","doi":"10.1109/ICDAR.2003.1227677","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227677","url":null,"abstract":"A new way to detect arrows in line drawings is proposed in this paper. Our approach is based on the definition of the structure of such a symbol. Signatures of angular areas are computed and axiomatic properties and geometric characteristics are checked using the Choquet integral. Finally an experimental application on line-drawing documents shows the interest of our approach.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"22 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":"121894015","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.2003.1227819
S. Veeramachaneni, G. Nagy
In style-constrained classification often there are onlya few samples of each style and class, and the correspondencesbetween styles in the training set and the test setare unknown. To avoid gross misestimates of the classifierparameters it is therefore important to model the patterndistributions accurately. We offer empirical evidence for intuitivelyappealing assumptions, in feature spaces appropriatefor symbolic patterns, for (1) tetrahedral configurationsof class means that suggests linear style-adaptive classification,(2) improved estimates of classification boundariesby taking into account the asymmetric configuration of thepatterns with respect to the directions toward other classes,and (3) pattern-correlated style variability.
{"title":"Towards a ptolemaic model for OCR","authors":"S. Veeramachaneni, G. Nagy","doi":"10.1109/ICDAR.2003.1227819","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227819","url":null,"abstract":"In style-constrained classification often there are onlya few samples of each style and class, and the correspondencesbetween styles in the training set and the test setare unknown. To avoid gross misestimates of the classifierparameters it is therefore important to model the patterndistributions accurately. We offer empirical evidence for intuitivelyappealing assumptions, in feature spaces appropriatefor symbolic patterns, for (1) tetrahedral configurationsof class means that suggests linear style-adaptive classification,(2) improved estimates of classification boundariesby taking into account the asymmetric configuration of thepatterns with respect to the directions toward other classes,and (3) pattern-correlated style variability.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"167 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":"124680431","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.2003.1227797
M. Bulacu, Lambert Schomaker, L. Vuurpijl
This paper evaluates the performance of edge-based directionalprobability distributions as features in writer identificationin comparison to a number of non-angular features.It is noted that the joint probability distribution of theangle combination of two "hinged" edge fragments outperformsall other individual features. Combining features mayimprove the performance. Limitations of the method pertainto the amount of handwritten material needed in orderto obtain reliable distribution estimates. The global featurestreated in this study are sensitive to major style variation(upper- vs lower case), slant, and forged styles, whichnecessitates the use of other features in realistic forensicwriter identification procedures.
{"title":"Writer identification using edge-based directional features","authors":"M. Bulacu, Lambert Schomaker, L. Vuurpijl","doi":"10.1109/ICDAR.2003.1227797","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227797","url":null,"abstract":"This paper evaluates the performance of edge-based directionalprobability distributions as features in writer identificationin comparison to a number of non-angular features.It is noted that the joint probability distribution of theangle combination of two \"hinged\" edge fragments outperformsall other individual features. Combining features mayimprove the performance. Limitations of the method pertainto the amount of handwritten material needed in orderto obtain reliable distribution estimates. The global featurestreated in this study are sensitive to major style variation(upper- vs lower case), slant, and forged styles, whichnecessitates the use of other features in realistic forensicwriter identification procedures.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"34 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":"123096484","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.2003.1227697
Sekhar Mandal, S. Chowdhury, A. Das, B. Chanda
With an aim to extract the structural information from the table of contents (TOC) to help develop a digital document library, the requirement of identifying/segmenting the TOC page is obvious. The objective to create a digital document library is to provide a non-labour intensive, cheap and flexible way of storing, representing and managing the paper document in electronic form to facilitate indexing, viewing, printing and extracting the intended portions. Information from the TOC pages is to be extracted for use in a document database for effective retrieval of the required pages. We present a fully automatic identification and segmentation of a table of contents (TOC) page from a scanned document.
{"title":"Automated detection and segmentation of table of contents page from document images","authors":"Sekhar Mandal, S. Chowdhury, A. Das, B. Chanda","doi":"10.1109/ICDAR.2003.1227697","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227697","url":null,"abstract":"With an aim to extract the structural information from the table of contents (TOC) to help develop a digital document library, the requirement of identifying/segmenting the TOC page is obvious. The objective to create a digital document library is to provide a non-labour intensive, cheap and flexible way of storing, representing and managing the paper document in electronic form to facilitate indexing, viewing, printing and extracting the intended portions. Information from the TOC pages is to be extracted for use in a document database for effective retrieval of the required pages. We present a fully automatic identification and segmentation of a table of contents (TOC) page from a scanned document.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"14 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":"127609309","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.2003.1227741
M. Mori
When recognizing multiple fonts, geometric features,such as the directional information of strokes, are generallyrobust against deformation but are weak against degradation.This paper describes a category-dependent feature extractionmethod that uses a feature compensation techniqueto overcome this weakness. Our proposed method estimatesthe degree of degradation of an input pattern by comparingthe input pattern and the template of each category. Thisestimation enables us to compensate the degradation in featurevalues. We apply the proposed method to the recognitionof video text suffering from degradation and deformation.Recognition experiments using characters extractedfrom videos show that the proposed method is superior tothe conventional alternatives in resisting degradation.
{"title":"Video text recognition using feature compensation as category-dependent feature extraction","authors":"M. Mori","doi":"10.1109/ICDAR.2003.1227741","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227741","url":null,"abstract":"When recognizing multiple fonts, geometric features,such as the directional information of strokes, are generallyrobust against deformation but are weak against degradation.This paper describes a category-dependent feature extractionmethod that uses a feature compensation techniqueto overcome this weakness. Our proposed method estimatesthe degree of degradation of an input pattern by comparingthe input pattern and the template of each category. Thisestimation enables us to compensate the degradation in featurevalues. We apply the proposed method to the recognitionof video text suffering from degradation and deformation.Recognition experiments using characters extractedfrom videos show that the proposed method is superior tothe conventional alternatives in resisting degradation.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"20 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":"133930550","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.2003.1227662
T. Rath, R. Manmatha
For the transition from traditional to digital libraries, the large number of handwritten manuscripts that exist pose a great challenge. Easy access to such collections requires an index, which is currently created manually at great cost. Because automatic handwriting recognizers fail on historical manuscripts, the word spotting technique has been developed: the words in a collection are matched as images and grouped into clusters which contain all instances of the same word. By annotating "interesting" clusters, an index that links words to the locations where they occur can be built automatically. Due to the noise in historical documents, selecting the right features for matching words is crucial. We analyzed a range of features suitable for matching words using dynamic time warping (DTW), which aligns and compares sets of features extracted from two images. Each feature's individual performance was measured on a test set. With an average precision of 72%, a combination of features outperforms competing techniques in speed and precision.
{"title":"Features for word spotting in historical manuscripts","authors":"T. Rath, R. Manmatha","doi":"10.1109/ICDAR.2003.1227662","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227662","url":null,"abstract":"For the transition from traditional to digital libraries, the large number of handwritten manuscripts that exist pose a great challenge. Easy access to such collections requires an index, which is currently created manually at great cost. Because automatic handwriting recognizers fail on historical manuscripts, the word spotting technique has been developed: the words in a collection are matched as images and grouped into clusters which contain all instances of the same word. By annotating \"interesting\" clusters, an index that links words to the locations where they occur can be built automatically. Due to the noise in historical documents, selecting the right features for matching words is crucial. We analyzed a range of features suitable for matching words using dynamic time warping (DTW), which aligns and compares sets of features extracted from two images. Each feature's individual performance was measured on a test set. With an average precision of 72%, a combination of features outperforms competing techniques in speed and precision.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"12 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":"133341477","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.2003.1227749
S. Lucas, A. Panaretos, Luis Sosa, Anthony Tang, Shirley Wong, Robert Young
This paper describes the robust reading competitions forICDAR 2003. With the rapid growth in research over thelast few years on recognizing text in natural scenes, thereis an urgent need to establish some common benchmarkdatasets, and gain a clear understanding of the current stateof the art. We use the term robust reading to refer to text imagesthat are beyond the capabilities of current commercialOCR packages. We chose to break down the robust readingproblem into three sub-problems, and run competitionsfor each stage, and also a competition for the best overallsystem. The sub-problems we chose were text locating,character recognition and word recognition.By breaking down the problem in this way, we hope togain a better understanding of the state of the art in eachof the sub-problems. Furthermore, our methodology involvesstoring detailed results of applying each algorithm toeach image in the data sets, allowing researchers to study indepth the strengths and weaknesses of each algorithm. Thetext locating contest was the only one to have any entries.We report the results of this contest, and show cases wherethe leading algorithms succeed and fail.
{"title":"ICDAR 2003 robust reading competitions","authors":"S. Lucas, A. Panaretos, Luis Sosa, Anthony Tang, Shirley Wong, Robert Young","doi":"10.1109/ICDAR.2003.1227749","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227749","url":null,"abstract":"This paper describes the robust reading competitions forICDAR 2003. With the rapid growth in research over thelast few years on recognizing text in natural scenes, thereis an urgent need to establish some common benchmarkdatasets, and gain a clear understanding of the current stateof the art. We use the term robust reading to refer to text imagesthat are beyond the capabilities of current commercialOCR packages. We chose to break down the robust readingproblem into three sub-problems, and run competitionsfor each stage, and also a competition for the best overallsystem. The sub-problems we chose were text locating,character recognition and word recognition.By breaking down the problem in this way, we hope togain a better understanding of the state of the art in eachof the sub-problems. Furthermore, our methodology involvesstoring detailed results of applying each algorithm toeach image in the data sets, allowing researchers to study indepth the strengths and weaknesses of each algorithm. Thetext locating contest was the only one to have any entries.We report the results of this contest, and show cases wherethe leading algorithms succeed and fail.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"56 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":"132157086","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.2003.1227711
S. Carbonnel, É. Anquetil
This paper presents a lexical post-processing optimization for handwritten word recognition. The aim of this work is to explore the combination of different lexical post-processing approaches in order to optimize the recognition rate, the recognition time and memory requirements. The present method focuses on the following tasks: a lexicon organization with word filtering, based on holistic word features to deal with large vocabulary (creation of static sublexicon compressed in a tree structure); a dedicated string matching algorithm for online handwriting (to compensate for the recognition and the segmentation errors); and a specific exploration strategy of the results provided by the analytical word recognition process. Experimental results are reported using several lexicon sizes (about 1000, 7000 and 25000 entries) to evaluate different optimization strategies according to the recognition rate, computational cost and memory requirements.
{"title":"Lexical post-processing optimization for handwritten word recognition","authors":"S. Carbonnel, É. Anquetil","doi":"10.1109/ICDAR.2003.1227711","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227711","url":null,"abstract":"This paper presents a lexical post-processing optimization for handwritten word recognition. The aim of this work is to explore the combination of different lexical post-processing approaches in order to optimize the recognition rate, the recognition time and memory requirements. The present method focuses on the following tasks: a lexicon organization with word filtering, based on holistic word features to deal with large vocabulary (creation of static sublexicon compressed in a tree structure); a dedicated string matching algorithm for online handwriting (to compensate for the recognition and the segmentation errors); and a specific exploration strategy of the results provided by the analytical word recognition process. Experimental results are reported using several lexicon sizes (about 1000, 7000 and 25000 entries) to evaluate different optimization strategies according to the recognition rate, computational cost and memory requirements.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"10 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":"132096354","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.2003.1227756
R. Srihari, Cheng Niu, W. Li, Jihong Ding
This paper describes a novel approach to namedentity (NE) tagging on degraded documents. NE taggingis the process of identifying salient text strings inunstructured text, corresponding to names of people,places, organizations, times/dates, etc. Although NEtagging is typically part of a larger informationextraction process, it has other applications, such asimproving search in an information retrieval system, andpost-processing the results of an OCR system. We focuson degraded documents, i.e. case insensitive documentsthat lack orthographic information. Examples includeoutput of speech recognition systems, as well as e-mail.The traditional approach involves retraining an NEtagger on degraded text, a cumbersome operation. Thispaper describes an approach whereby text is first"restored" to its implicit case sensitive form, andsubsequently processed by the original NE tagger.Results show that this new approach leads to far lessprecision loss in NE tagging of degraded documents.
{"title":"A case restoration approach to named entity tagging in degraded documents","authors":"R. Srihari, Cheng Niu, W. Li, Jihong Ding","doi":"10.1109/ICDAR.2003.1227756","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227756","url":null,"abstract":"This paper describes a novel approach to namedentity (NE) tagging on degraded documents. NE taggingis the process of identifying salient text strings inunstructured text, corresponding to names of people,places, organizations, times/dates, etc. Although NEtagging is typically part of a larger informationextraction process, it has other applications, such asimproving search in an information retrieval system, andpost-processing the results of an OCR system. We focuson degraded documents, i.e. case insensitive documentsthat lack orthographic information. Examples includeoutput of speech recognition systems, as well as e-mail.The traditional approach involves retraining an NEtagger on degraded text, a cumbersome operation. Thispaper describes an approach whereby text is first\"restored\" to its implicit case sensitive form, andsubsequently processed by the original NE tagger.Results show that this new approach leads to far lessprecision loss in NE tagging of degraded documents.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"10 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":"132811435","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.2003.1227785
C. Suen, S. Mori, Soohyung Kim, C. Leung
This paper summarizes the research activities of the pastdecade on the recognition of handwritten scripts used inChina, Japan, and Korea. It presents the recognitionmethodologies, features explored, databases used, andclassification schemes investigated. In addition, it includes adescription of the performance of numerous recognitionsystems found in both academic and industrial researchlaboratories. Recent achievements and applications are alsopresented. A list of relevant references is attached togetherwith our remarks on this subject.
{"title":"Analysis and recognition of Asian scripts-the state of the art","authors":"C. Suen, S. Mori, Soohyung Kim, C. Leung","doi":"10.1109/ICDAR.2003.1227785","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227785","url":null,"abstract":"This paper summarizes the research activities of the pastdecade on the recognition of handwritten scripts used inChina, Japan, and Korea. It presents the recognitionmethodologies, features explored, databases used, andclassification schemes investigated. In addition, it includes adescription of the performance of numerous recognitionsystems found in both academic and industrial researchlaboratories. Recent achievements and applications are alsopresented. A list of relevant references is attached togetherwith our remarks on this subject.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"106 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":"132518751","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：