Pub Date : 2003-08-03DOI: 10.1109/ICDAR.2003.1227743
Anil K. Jain, A. Namboodiri
Recent advances in on-line data capturing technologiesand its widespread deployment in devices like PDAsand notebook PCs is creating large amounts of handwrittendata that need to be archived and retrieved efficiently.Word-spotting, which is based on a direct comparison ofa handwritten keyword to words in the document, is commonlyused for indexing and retrieval. We propose a stringmatching-based method for word-spotting in on-line documents.The retrieval algorithm achieves a precision of92.3% at a recall rate of 90% on a database of 6,672 wordswritten by 10 different writers. Indexing experiments showan accuracy of 87.5% using a database of 3,872 on-linewords.
{"title":"Indexing and retrieval of on-line handwritten documents","authors":"Anil K. Jain, A. Namboodiri","doi":"10.1109/ICDAR.2003.1227743","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227743","url":null,"abstract":"Recent advances in on-line data capturing technologiesand its widespread deployment in devices like PDAsand notebook PCs is creating large amounts of handwrittendata that need to be archived and retrieved efficiently.Word-spotting, which is based on a direct comparison ofa handwritten keyword to words in the document, is commonlyused for indexing and retrieval. We propose a stringmatching-based method for word-spotting in on-line documents.The retrieval algorithm achieves a precision of92.3% at a recall rate of 90% on a database of 6,672 wordswritten by 10 different writers. Indexing experiments showan accuracy of 87.5% using a database of 3,872 on-linewords.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"142 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":"125766997","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.2003.1227733
Poh Kok Loo, C. Tan
Compared to binary images that most text extraction methods work on, gray scale images provide much more information for the extraction task. On the other hand complication also arises in determining the subject textual content from its background region (i.e. thresholding) before the actual text extraction process can begin. Differing from the usual sequence of processes where document images are binarized before the actual text extraction, this paper proposes a new method by first segmenting individual subject areas with the help of an irregular pyramid to be followed by the binarization process. This permits the focus of attention only on the appropriate subject areas for the binarization process before text recognition. Our method overcomes the difficulty in global binarization to find a single value to fit all. It also avoids the common problem in most local thresholding technique of finding a suitable window size. As shown in our experimented result, our method performed well in both text segmentation and binarization by varying the sequence of processing.
{"title":"Using irregular pyramid for text segmentation and binarization of gray scale images","authors":"Poh Kok Loo, C. Tan","doi":"10.1109/ICDAR.2003.1227733","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227733","url":null,"abstract":"Compared to binary images that most text extraction methods work on, gray scale images provide much more information for the extraction task. On the other hand complication also arises in determining the subject textual content from its background region (i.e. thresholding) before the actual text extraction process can begin. Differing from the usual sequence of processes where document images are binarized before the actual text extraction, this paper proposes a new method by first segmenting individual subject areas with the help of an irregular pyramid to be followed by the binarization process. This permits the focus of attention only on the appropriate subject areas for the binarization process before text recognition. Our method overcomes the difficulty in global binarization to find a single value to fit all. It also avoids the common problem in most local thresholding technique of finding a suitable window size. As shown in our experimented result, our method performed well in both text segmentation and binarization by varying the sequence of processing.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"67 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":"124846021","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.2003.1227727
E. Kavallieratou, K. Sgarbas, N. Fakotakis, G. Kokkinakis
In this paper a handwritten recognition algorithm based on structural characteristics, histograms and profiles, is presented. The well-known horizontal and vertical histograms are used, in combination with the newly introduced radial histogram, out-in radial and in-out radial profiles for representing 32 /spl times/ 32 matrices of characters, as 280-dimension vectors. The recognition process has been supported by a lexical component based on dynamic acyclic FSAs (Finite-State-Automata).
{"title":"Handwritten word recognition based on structural characteristics and lexical support","authors":"E. Kavallieratou, K. Sgarbas, N. Fakotakis, G. Kokkinakis","doi":"10.1109/ICDAR.2003.1227727","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227727","url":null,"abstract":"In this paper a handwritten recognition algorithm based on structural characteristics, histograms and profiles, is presented. The well-known horizontal and vertical histograms are used, in combination with the newly introduced radial histogram, out-in radial and in-out radial profiles for representing 32 /spl times/ 32 matrices of characters, as 280-dimension vectors. The recognition process has been supported by a lexical component based on dynamic acyclic FSAs (Finite-State-Automata).","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"8 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":"128471949","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.2003.1227737
E. Ratzlaff
A framework of data organization methods and corresponding recognition results for UNIPEN databases is presented to enable the comparison of recognition results from different isolated character recognizers. A reproducible method for splitting the Train-R01/V07 data into an array of multi-writer and omni-writer training and testing pairs is proposed. Recognition results and uncertainties are provided for each pair, as well as results for the DevTest-R01/V02 character subsets, using an online scanning n-tuple recognizer. Several other published results are surveyed within this context. In sum, this report provides the reader multiple points of reference useful for comparing a number of published recognition results and a proposed framework that similarly allows private evaluation of unpublished recognition results.
{"title":"Methods, reports and survey for the comparison of diverse isolated character recognition results on the UNIPEN database","authors":"E. Ratzlaff","doi":"10.1109/ICDAR.2003.1227737","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227737","url":null,"abstract":"A framework of data organization methods and corresponding recognition results for UNIPEN databases is presented to enable the comparison of recognition results from different isolated character recognizers. A reproducible method for splitting the Train-R01/V07 data into an array of multi-writer and omni-writer training and testing pairs is proposed. Recognition results and uncertainties are provided for each pair, as well as results for the DevTest-R01/V02 character subsets, using an online scanning n-tuple recognizer. Several other published results are surveyed within this context. In sum, this report provides the reader multiple points of reference useful for comparing a number of published recognition results and a proposed framework that similarly allows private evaluation of unpublished recognition results.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"52 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":"128712365","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.2003.1227836
H. Alam, Aman Kumar, Mikako Nakamura, F. Rahman, Yuliya Tarnikova, C. Wilcox
The process of summarizing documents is becomingincreasingly important in the light of recent advances indocument creation/distribution technology, and theresulting influx of large numbers of documents in everyday life. This paper presents a document summarizer thatcombines document analysis, structural decomposition,XML representation and lexical chain analysis. Theproposed summarizer is compared to three commerciallyavailable summarizers and it is shown that it produceseither comparable or better summaries overall.
{"title":"Structured and unstructured document summarization:design of a commercial summarizer using Lexical chains","authors":"H. Alam, Aman Kumar, Mikako Nakamura, F. Rahman, Yuliya Tarnikova, C. Wilcox","doi":"10.1109/ICDAR.2003.1227836","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227836","url":null,"abstract":"The process of summarizing documents is becomingincreasingly important in the light of recent advances indocument creation/distribution technology, and theresulting influx of large numbers of documents in everyday life. This paper presents a document summarizer thatcombines document analysis, structural decomposition,XML representation and lexical chain analysis. Theproposed summarizer is compared to three commerciallyavailable summarizers and it is shown that it produceseither comparable or better summaries overall.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"1 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":"129072626","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.2003.1227810
Mathieu Delalandre, Stéphane Nicolas, É. Trupin, J. Ogier
This paper deals with the structural recognition ofsymbols on the documents. We have based our system ona combination of local and global structural approaches.The global approach groups the connected componentstogether according to some closeness and connectionconstraints. The local approach splits up each connectedcomponent into a graph of geometrical objects (vectors,arcs, curves). The extracted graphs are matched thanks toa structural classifier, which permits graph-subgraph andexact-inexact matching. The system adaptability isobtained thanks to the scenarios use. A XML datarepresentation is used, allowing the data manipulationsand the graphic representations of results.
{"title":"Symbols recognition by global-local structural approaches, based on the scenarios use,and with a XML representation of data","authors":"Mathieu Delalandre, Stéphane Nicolas, É. Trupin, J. Ogier","doi":"10.1109/ICDAR.2003.1227810","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227810","url":null,"abstract":"This paper deals with the structural recognition ofsymbols on the documents. We have based our system ona combination of local and global structural approaches.The global approach groups the connected componentstogether according to some closeness and connectionconstraints. The local approach splits up each connectedcomponent into a graph of geometrical objects (vectors,arcs, curves). The extracted graphs are matched thanks toa structural classifier, which permits graph-subgraph andexact-inexact matching. The system adaptability isobtained thanks to the scenarios use. A XML datarepresentation is used, allowing the data manipulationsand the graphic representations of results.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"1 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":"130727456","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.2003.1227719
M. Nakagawa, M. Onuma
This paper describes an on-line handwritten Japanese text recognition method that is liberated from constraints on writing direction (line direction) and character orientation. This method estimates the line direction and character orientation using the time sequence information of pen-tip coordinates and employs writing-box-free recognition with context processing combined. The method can cope with a mixture of vertical, horizontal and skewed lines with arbitrary character orientations. It is expected useful for tablet PCs, interactive electronic whiteboards and so on.
{"title":"Online handwritten Japanese text recognition free from constrains on line direction and character orientation","authors":"M. Nakagawa, M. Onuma","doi":"10.1109/ICDAR.2003.1227719","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227719","url":null,"abstract":"This paper describes an on-line handwritten Japanese text recognition method that is liberated from constraints on writing direction (line direction) and character orientation. This method estimates the line direction and character orientation using the time sequence information of pen-tip coordinates and employs writing-box-free recognition with context processing combined. The method can cope with a mixture of vertical, horizontal and skewed lines with arbitrary character orientations. It is expected useful for tablet PCs, interactive electronic whiteboards and so on.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"17 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":"132883380","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.2003.1227766
Jin-Seon Lee, Il-Seok Oh
This paper proposes a binary classification tree aiming atsolving multi-class classification problems using binaryclassifiers. The tree design is achieved in a way that aclass group is partitioned into two distinct subgroups at anode. The node adopts the class-modular scheme toimprove the binary classification capability. Thepartitioning is formulated as an optimization problemand a genetic algorithm is proposed to solve theoptimization problem. The binary classification tree iscompared to the conventional methods in terms ofclassification accuracy and timing efficiency.Experiments were performed with numeral recognitionand touching-numeral pair recognition.
{"title":"Binary classification trees for multi-class classification problems","authors":"Jin-Seon Lee, Il-Seok Oh","doi":"10.1109/ICDAR.2003.1227766","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227766","url":null,"abstract":"This paper proposes a binary classification tree aiming atsolving multi-class classification problems using binaryclassifiers. The tree design is achieved in a way that aclass group is partitioned into two distinct subgroups at anode. The node adopts the class-modular scheme toimprove the binary classification capability. Thepartitioning is formulated as an optimization problemand a genetic algorithm is proposed to solve theoptimization problem. The binary classification tree iscompared to the conventional methods in terms ofclassification accuracy and timing efficiency.Experiments were performed with numeral recognitionand touching-numeral pair recognition.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"59 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":"132006346","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.2003.1227680
M. Zou, Jianjun Tong, Chang-ping Liu, Zhengliang Lou
This paper presents a novel approach to the on-line signature verification using local shape analysis. First, segment the input signature into several segments using HMM (hidden Markov model). Then, combine two adjacent segments to form a long segment and get its spectral and tremor information using FFT (fast Fourier transformation). At last, accept it or reject it based on the similarity between the spectral and its prototype. In addition, we proposed a novel initialization algorithm to avoid the local optimal of the HMM's re-estimation and a novel algorithm to avoid losing the important information at cusps in preprocessing. Combining the local shape analysis with the local time-based comparison, we get promising experimental results.
{"title":"On-line signature verification using local shape analysis","authors":"M. Zou, Jianjun Tong, Chang-ping Liu, Zhengliang Lou","doi":"10.1109/ICDAR.2003.1227680","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227680","url":null,"abstract":"This paper presents a novel approach to the on-line signature verification using local shape analysis. First, segment the input signature into several segments using HMM (hidden Markov model). Then, combine two adjacent segments to form a long segment and get its spectral and tremor information using FFT (fast Fourier transformation). At last, accept it or reject it based on the similarity between the spectral and its prototype. In addition, we proposed a novel initialization algorithm to avoid the local optimal of the HMM's re-estimation and a novel algorithm to avoid losing the important information at cusps in preprocessing. Combining the local shape analysis with the local time-based comparison, we get promising experimental results.","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":"132051081","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.2003.1227731
H. Nishida, Takeshi Suzuki
This paper describes a new approach to restoring scanned color document images where the backside image shows through the paper sheet. A new framework is presented for correcting show-through components using digital image processing techniques. First, the foreground components on the front side are separated from the background and backside components through locally adaptive binarization for each color component and edge magnitude thresholding. Background colors are estimated locally through color thresholding to generate a restored image, and then corrected adaptively through multiscale analysis along with comparison of edge distributions between the original and the restored image. The proposed method does not require specific input devices or the backside to be input; it is able to correct unneeded image components through analysis of the front side image alone. Experimental results are given to verify effectiveness of the proposed method.
{"title":"A multiscale approach to restoring scanned color document images with show-through effects","authors":"H. Nishida, Takeshi Suzuki","doi":"10.1109/ICDAR.2003.1227731","DOIUrl":"https://doi.org/10.1109/ICDAR.2003.1227731","url":null,"abstract":"This paper describes a new approach to restoring scanned color document images where the backside image shows through the paper sheet. A new framework is presented for correcting show-through components using digital image processing techniques. First, the foreground components on the front side are separated from the background and backside components through locally adaptive binarization for each color component and edge magnitude thresholding. Background colors are estimated locally through color thresholding to generate a restored image, and then corrected adaptively through multiscale analysis along with comparison of edge distributions between the original and the restored image. The proposed method does not require specific input devices or the backside to be input; it is able to correct unneeded image components through analysis of the front side image alone. Experimental results are given to verify effectiveness of the proposed method.","PeriodicalId":249193,"journal":{"name":"Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.","volume":"1 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":"130249435","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：