An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition
Identifieur interne : 001D27 ( Istex/Corpus ); précédent : 001D26; suivant : 001D28An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition
Auteurs : Wenwei Wang ; Anja Brakensiek ; Gerhard RigollSource :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2000.
Abstract
Abstract: The cursive handwriting recognition is a challenging task because the recognition system has to handle not only large shape variation of human handwriting, but also character segmentation. Usually the recognition performance depends crucially upon the segmentation process. Hidden Markov Models (HMMs) have the ability to model similarity and variation among samples of a class. In this paper we present an extended sliding window feature extraction method and an HMM based two-pass modeling approach. Whereas our feature extraction method makes the resulting system more robust with word baseline detection, the two-pass recognition approach exploits the segmentation ability of the Viterbi algorithm and creates another HMM set and carries out a second pass recognition. The total performance is enhanced by combination of the two pass results. Experiments of recognizing cursive handwritten words with 30000 words lexicon have been carried out and show that our novel approach can achieve better recognition performance and reduce the relative error rate significantly.
Url:
DOI: 10.1007/3-540-40063-X_51
Links to Exploration step
ISTEX:D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition</title><author><name sortKey="Wang, Wenwei" sort="Wang, Wenwei" uniqKey="Wang W" first="Wenwei" last="Wang">Wenwei Wang</name><affiliation><mods:affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: wwwang@fb9-ti.uni-duisburg.de</mods:affiliation></affiliation></author><author><name sortKey="Brakensiek, Anja" sort="Brakensiek, Anja" uniqKey="Brakensiek A" first="Anja" last="Brakensiek">Anja Brakensiek</name><affiliation><mods:affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: anja@fb9-ti.uni-duisburg.de</mods:affiliation></affiliation></author><author><name sortKey="Rigoll, Gerhard" sort="Rigoll, Gerhard" uniqKey="Rigoll G" first="Gerhard" last="Rigoll">Gerhard Rigoll</name><affiliation><mods:affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: rigoll@fb9-ti.uni-duisburg.de</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852</idno><date when="2000" year="2000">2000</date><idno type="doi">10.1007/3-540-40063-X_51</idno><idno type="url">https://api.istex.fr/document/D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001D27</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition</title><author><name sortKey="Wang, Wenwei" sort="Wang, Wenwei" uniqKey="Wang W" first="Wenwei" last="Wang">Wenwei Wang</name><affiliation><mods:affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: wwwang@fb9-ti.uni-duisburg.de</mods:affiliation></affiliation></author><author><name sortKey="Brakensiek, Anja" sort="Brakensiek, Anja" uniqKey="Brakensiek A" first="Anja" last="Brakensiek">Anja Brakensiek</name><affiliation><mods:affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: anja@fb9-ti.uni-duisburg.de</mods:affiliation></affiliation></author><author><name sortKey="Rigoll, Gerhard" sort="Rigoll, Gerhard" uniqKey="Rigoll G" first="Gerhard" last="Rigoll">Gerhard Rigoll</name><affiliation><mods:affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</mods:affiliation></affiliation><affiliation><mods:affiliation>E-mail: rigoll@fb9-ti.uni-duisburg.de</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>2000</date></imprint><idno type="ISSN">0302-9743</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852</idno><idno type="DOI">10.1007/3-540-40063-X_51</idno><idno type="ChapterID">51</idno><idno type="ChapterID">Chap51</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: The cursive handwriting recognition is a challenging task because the recognition system has to handle not only large shape variation of human handwriting, but also character segmentation. Usually the recognition performance depends crucially upon the segmentation process. Hidden Markov Models (HMMs) have the ability to model similarity and variation among samples of a class. In this paper we present an extended sliding window feature extraction method and an HMM based two-pass modeling approach. Whereas our feature extraction method makes the resulting system more robust with word baseline detection, the two-pass recognition approach exploits the segmentation ability of the Viterbi algorithm and creates another HMM set and carries out a second pass recognition. The total performance is enhanced by combination of the two pass results. Experiments of recognizing cursive handwritten words with 30000 words lexicon have been carried out and show that our novel approach can achieve better recognition performance and reduce the relative error rate significantly.</div></front></TEI><istex><corpusName>springer</corpusName><author><json:item><name>Wenwei Wang</name><affiliations><json:string>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</json:string><json:string>E-mail: wwwang@fb9-ti.uni-duisburg.de</json:string></affiliations></json:item><json:item><name>Anja Brakensiek</name><affiliations><json:string>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</json:string><json:string>E-mail: anja@fb9-ti.uni-duisburg.de</json:string></affiliations></json:item><json:item><name>Gerhard Rigoll</name><affiliations><json:string>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</json:string><json:string>E-mail: rigoll@fb9-ti.uni-duisburg.de</json:string></affiliations></json:item></author><language><json:string>eng</json:string></language><abstract>Abstract: The cursive handwriting recognition is a challenging task because the recognition system has to handle not only large shape variation of human handwriting, but also character segmentation. Usually the recognition performance depends crucially upon the segmentation process. Hidden Markov Models (HMMs) have the ability to model similarity and variation among samples of a class. In this paper we present an extended sliding window feature extraction method and an HMM based two-pass modeling approach. Whereas our feature extraction method makes the resulting system more robust with word baseline detection, the two-pass recognition approach exploits the segmentation ability of the Viterbi algorithm and creates another HMM set and carries out a second pass recognition. The total performance is enhanced by combination of the two pass results. Experiments of recognizing cursive handwritten words with 30000 words lexicon have been carried out and show that our novel approach can achieve better recognition performance and reduce the relative error rate significantly.</abstract><qualityIndicators><score>4.628</score><pdfVersion>1.3</pdfVersion><pdfPageSize>648 x 864 pts</pdfPageSize><refBibsNative>false</refBibsNative><keywordCount>0</keywordCount><abstractCharCount>1082</abstractCharCount><pdfWordCount>2744</pdfWordCount><pdfCharCount>15783</pdfCharCount><pdfPageCount>8</pdfPageCount><abstractWordCount>157</abstractWordCount></qualityIndicators><title>An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition</title><genre.original><json:string>OriginalPaper</json:string></genre.original><chapterId><json:string>51</json:string><json:string>Chap51</json:string></chapterId><genre><json:string>conference [eBooks]</json:string></genre><serie><editor><json:item><name>Gerhard Goos</name><affiliations><json:string>Karlsruhe University, Germany</json:string></affiliations></json:item><json:item><name>Juris Hartmanis</name><affiliations><json:string>Cornell University, NY, USA</json:string></affiliations></json:item><json:item><name>Jan van Leeuwen</name><affiliations><json:string>Utrecht University, The Netherlands</json:string></affiliations></json:item></editor><issn><json:string>0302-9743</json:string></issn><language><json:string>unknown</json:string></language><title>Lecture Notes in Computer Science</title><copyrightDate>2000</copyrightDate></serie><host><editor><json:item><name>Tieniu Tan</name><affiliations><json:string>Institute of Automation, Chinese Academy of Sciences, P.O.Box 2728, 100080, Beijing, China</json:string><json:string>E-mail: tnt@nlpr.ia.ac.cn</json:string></affiliations></json:item><json:item><name>Yuanchun Shi</name><affiliations><json:string>Computer Department, Media Laboratory, Tsinghua University, 100084, Beijing, China</json:string><json:string>E-mail: shiyc@tsinghua.edu.cn</json:string></affiliations></json:item><json:item><name>Wen Gao</name><affiliations><json:string>Institute of Computing Technology, Chinese Academy of Sciences, P.O.Box 2704, 100080, Beijing, China</json:string><json:string>E-mail: wgao@cti.com.cn</json:string></affiliations></json:item></editor><subject><json:item><value>Computer Science</value></json:item><json:item><value>Computer Science</value></json:item><json:item><value>User Interfaces and Human Computer Interaction</value></json:item><json:item><value>Pattern Recognition</value></json:item><json:item><value>Computer Graphics</value></json:item><json:item><value>Artificial Intelligence (incl. Robotics)</value></json:item><json:item><value>Software Engineering</value></json:item></subject><isbn><json:string>978-3-540-41180-2</json:string></isbn><language><json:string>unknown</json:string></language><title>Advances in Multimodal Interfaces — ICMI 2000</title><genre.original><json:string>Proceedings</json:string></genre.original><bookId><json:string>3-540-40063-X</json:string></bookId><volume>1948</volume><pages><last>393</last><first>386</first></pages><issn><json:string>0302-9743</json:string></issn><genre><json:string>Book Series</json:string></genre><eisbn><json:string>978-3-540-40063-9</json:string></eisbn><copyrightDate>2000</copyrightDate><doi><json:string>10.1007/3-540-40063-X</json:string></doi></host><publicationDate>2000</publicationDate><copyrightDate>2000</copyrightDate><doi><json:string>10.1007/3-540-40063-X_51</json:string></doi><id>D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852</id><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852/fulltext/pdf</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition</title><respStmt xml:id="ISTEX-API" resp="Références bibliographiques récupérées via GROBID" name="ISTEX-API (INIST-CNRS)"></respStmt></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>Springer Berlin Heidelberg</publisher><pubPlace>Berlin, Heidelberg</pubPlace><availability><p>SPRINGER</p></availability><date>2000</date></publicationStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a" type="main" xml:lang="en">An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition</title><author><persName><forename type="first">Wenwei</forename><surname>Wang</surname></persName><email>wwwang@fb9-ti.uni-duisburg.de</email><affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</affiliation></author><author><persName><forename type="first">Anja</forename><surname>Brakensiek</surname></persName><email>anja@fb9-ti.uni-duisburg.de</email><affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</affiliation></author><author><persName><forename type="first">Gerhard</forename><surname>Rigoll</surname></persName><email>rigoll@fb9-ti.uni-duisburg.de</email><affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</affiliation></author></analytic><monogr><title level="m">Advances in Multimodal Interfaces — ICMI 2000</title><title level="m" type="sub">Third International Conference Beijing, China, October 14–16, 2000 Proceedings</title><idno type="pISBN">978-3-540-41180-2</idno><idno type="eISBN">978-3-540-40063-9</idno><idno type="pISSN">0302-9743</idno><idno type="DOI">10.1007/3-540-40063-X</idno><idno type="BookID">3-540-40063-X</idno><idno type="BookTitleID">66868</idno><idno type="BookSequenceNumber">1948</idno><idno type="BookVolumeNumber">1948</idno><idno type="BookChapterCount">86</idno><editor><persName><forename type="first">Tieniu</forename><surname>Tan</surname></persName><email>tnt@nlpr.ia.ac.cn</email><affiliation>Institute of Automation, Chinese Academy of Sciences, P.O.Box 2728, 100080, Beijing, China</affiliation></editor><editor><persName><forename type="first">Yuanchun</forename><surname>Shi</surname></persName><email>shiyc@tsinghua.edu.cn</email><affiliation>Computer Department, Media Laboratory, Tsinghua University, 100084, Beijing, China</affiliation></editor><editor><persName><forename type="first">Wen</forename><surname>Gao</surname></persName><email>wgao@cti.com.cn</email><affiliation>Institute of Computing Technology, Chinese Academy of Sciences, P.O.Box 2704, 100080, Beijing, China</affiliation></editor><imprint><publisher>Springer Berlin Heidelberg</publisher><pubPlace>Berlin, Heidelberg</pubPlace><date type="published" when="2000"></date><biblScope unit="volume">1948</biblScope><biblScope unit="page" from="386">386</biblScope><biblScope unit="page" to="393">393</biblScope></imprint></monogr><series><title level="s">Lecture Notes in Computer Science</title><editor><persName><forename type="first">Gerhard</forename><surname>Goos</surname></persName><affiliation>Karlsruhe University, Germany</affiliation></editor><editor><persName><forename type="first">Juris</forename><surname>Hartmanis</surname></persName><affiliation>Cornell University, NY, USA</affiliation></editor><editor><persName><forename type="first">Jan</forename><surname>van Leeuwen</surname></persName><affiliation>Utrecht University, The Netherlands</affiliation></editor><biblScope><date>2000</date></biblScope><idno type="pISSN">0302-9743</idno><idno type="seriesId">558</idno></series><idno type="istex">D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852</idno><idno type="DOI">10.1007/3-540-40063-X_51</idno><idno type="ChapterID">51</idno><idno type="ChapterID">Chap51</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2000</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>Abstract: The cursive handwriting recognition is a challenging task because the recognition system has to handle not only large shape variation of human handwriting, but also character segmentation. Usually the recognition performance depends crucially upon the segmentation process. Hidden Markov Models (HMMs) have the ability to model similarity and variation among samples of a class. In this paper we present an extended sliding window feature extraction method and an HMM based two-pass modeling approach. Whereas our feature extraction method makes the resulting system more robust with word baseline detection, the two-pass recognition approach exploits the segmentation ability of the Viterbi algorithm and creates another HMM set and carries out a second pass recognition. The total performance is enhanced by combination of the two pass results. Experiments of recognizing cursive handwritten words with 30000 words lexicon have been carried out and show that our novel approach can achieve better recognition performance and reduce the relative error rate significantly.</p></abstract><textClass><keywords scheme="Book Subject Collection"><list><label>SUCO11645</label><item><term>Computer Science</term></item></list></keywords></textClass><textClass><keywords scheme="Book Subject Group"><list><label>I</label><label>I18067</label><label>I2203X</label><label>I22013</label><label>I21017</label><label>I14029</label><item><term>Computer Science</term></item><item><term>User Interfaces and Human Computer Interaction</term></item><item><term>Pattern Recognition</term></item><item><term>Computer Graphics</term></item><item><term>Artificial Intelligence (incl. Robotics)</term></item><item><term>Software Engineering</term></item></list></keywords></textClass></profileDesc><revisionDesc><change when="2000">Published</change><change xml:id="refBibs-istex" who="#ISTEX-API" when="2016-3-20">References added</change></revisionDesc></teiHeader></istex:fulltextTEI><json:item><original>false</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852/fulltext/txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="Springer, Publisher found" wicri:toSee="no header"><istex:xmlDeclaration>version="1.0" encoding="UTF-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//Springer-Verlag//DTD A++ V2.4//EN" URI="http://devel.springer.de/A++/V2.4/DTD/A++V2.4.dtd" name="istex:docType"></istex:docType><istex:document><Publisher><PublisherInfo><PublisherName>Springer Berlin Heidelberg</PublisherName><PublisherLocation>Berlin, Heidelberg</PublisherLocation></PublisherInfo><Series><SeriesInfo SeriesType="Series" TocLevels="0"><SeriesID>558</SeriesID><SeriesPrintISSN>0302-9743</SeriesPrintISSN><SeriesTitle Language="En">Lecture Notes in Computer Science</SeriesTitle></SeriesInfo><SeriesHeader><EditorGroup><Editor AffiliationIDS="Aff1"><EditorName DisplayOrder="Western"><GivenName>Gerhard</GivenName><FamilyName>Goos</FamilyName></EditorName></Editor><Editor AffiliationIDS="Aff2"><EditorName DisplayOrder="Western"><GivenName>Juris</GivenName><FamilyName>Hartmanis</FamilyName></EditorName></Editor><Editor AffiliationIDS="Aff3"><EditorName DisplayOrder="Western"><GivenName>Jan</GivenName><Particle>van</Particle><FamilyName>Leeuwen</FamilyName></EditorName></Editor><Affiliation ID="Aff1"><OrgName>Karlsruhe University</OrgName><OrgAddress><Country>Germany</Country></OrgAddress></Affiliation><Affiliation ID="Aff2"><OrgName>Cornell University</OrgName><OrgAddress><City>NY</City><Country>USA</Country></OrgAddress></Affiliation><Affiliation ID="Aff3"><OrgName>Utrecht University</OrgName><OrgAddress><Country>The Netherlands</Country></OrgAddress></Affiliation></EditorGroup></SeriesHeader><Book Language="En"><BookInfo BookProductType="Proceedings" ContainsESM="No" Language="En" MediaType="eBook" NumberingStyle="Unnumbered" TocLevels="0"><BookID>3-540-40063-X</BookID><BookTitle>Advances in Multimodal Interfaces — ICMI 2000</BookTitle><BookSubTitle>Third International Conference Beijing, China, October 14–16, 2000 Proceedings</BookSubTitle><BookVolumeNumber>1948</BookVolumeNumber><BookSequenceNumber>1948</BookSequenceNumber><BookDOI>10.1007/3-540-40063-X</BookDOI><BookTitleID>66868</BookTitleID><BookPrintISBN>978-3-540-41180-2</BookPrintISBN><BookElectronicISBN>978-3-540-40063-9</BookElectronicISBN><BookChapterCount>86</BookChapterCount><BookHistory><OnlineDate><Year>2001</Year><Month>10</Month><Day>26</Day></OnlineDate></BookHistory><BookCopyright><CopyrightHolderName>Springer-Verlag Berlin Heidelberg</CopyrightHolderName><CopyrightYear>2000</CopyrightYear></BookCopyright><BookSubjectGroup><BookSubject Code="I" Type="Primary">Computer Science</BookSubject><BookSubject Code="I18067" Priority="1" Type="Secondary">User Interfaces and Human Computer Interaction</BookSubject><BookSubject Code="I2203X" Priority="2" Type="Secondary">Pattern Recognition</BookSubject><BookSubject Code="I22013" Priority="3" Type="Secondary">Computer Graphics</BookSubject><BookSubject Code="I21017" Priority="4" Type="Secondary">Artificial Intelligence (incl. Robotics)</BookSubject><BookSubject Code="I14029" Priority="5" Type="Secondary">Software Engineering</BookSubject><SubjectCollection Code="SUCO11645">Computer Science</SubjectCollection></BookSubjectGroup><BookContext><SeriesID>558</SeriesID></BookContext></BookInfo><BookHeader><EditorGroup><Editor AffiliationIDS="Aff4"><EditorName DisplayOrder="Western"><GivenName>Tieniu</GivenName><FamilyName>Tan</FamilyName></EditorName><Contact><Email>tnt@nlpr.ia.ac.cn</Email></Contact></Editor><Editor AffiliationIDS="Aff5"><EditorName DisplayOrder="Western"><GivenName>Yuanchun</GivenName><FamilyName>Shi</FamilyName></EditorName><Contact><Email>shiyc@tsinghua.edu.cn</Email></Contact></Editor><Editor AffiliationIDS="Aff6"><EditorName DisplayOrder="Western"><GivenName>Wen</GivenName><FamilyName>Gao</FamilyName></EditorName><Contact><Email>wgao@cti.com.cn</Email></Contact></Editor><Affiliation ID="Aff4"><OrgDivision>Institute of Automation</OrgDivision><OrgName>Chinese Academy of Sciences</OrgName><OrgAddress><Postbox>P.O.Box 2728</Postbox><Postcode>100080</Postcode><City>Beijing</City><Country>China</Country></OrgAddress></Affiliation><Affiliation ID="Aff5"><OrgDivision>Computer Department, Media Laboratory</OrgDivision><OrgName>Tsinghua University</OrgName><OrgAddress><Postcode>100084</Postcode><City>Beijing</City><Country>China</Country></OrgAddress></Affiliation><Affiliation ID="Aff6"><OrgDivision>Institute of Computing Technology</OrgDivision><OrgName>Chinese Academy of Sciences</OrgName><OrgAddress><Postbox>P.O.Box 2704</Postbox><Postcode>100080</Postcode><City>Beijing</City><Country>China</Country></OrgAddress></Affiliation></EditorGroup></BookHeader><Part ID="Part7"><PartInfo TocLevels="0"><PartID>7</PartID><PartSequenceNumber>7</PartSequenceNumber><PartTitle>Handwriting Recognition</PartTitle><PartChapterCount>14</PartChapterCount><PartContext><SeriesID>558</SeriesID><BookID>3-540-40063-X</BookID><BookTitle>Advances in Multimodal Interfaces — ICMI 2000</BookTitle></PartContext></PartInfo><Chapter ID="Chap51" Language="En"><ChapterInfo ChapterType="OriginalPaper" ContainsESM="No" Language="En" NumberingStyle="Unnumbered" TocLevels="0"><ChapterID>51</ChapterID><ChapterDOI>10.1007/3-540-40063-X_51</ChapterDOI><ChapterSequenceNumber>51</ChapterSequenceNumber><ChapterTitle Language="En">An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition</ChapterTitle><ChapterFirstPage>386</ChapterFirstPage><ChapterLastPage>393</ChapterLastPage><ChapterCopyright><CopyrightHolderName>Springer-Verlag Berlin Heidelberg</CopyrightHolderName><CopyrightYear>2000</CopyrightYear></ChapterCopyright><ChapterHistory><RegistrationDate><Year>2001</Year><Month>10</Month><Day>25</Day></RegistrationDate><OnlineDate><Year>2001</Year><Month>10</Month><Day>26</Day></OnlineDate></ChapterHistory><ChapterGrants Type="Regular"><MetadataGrant Grant="OpenAccess"></MetadataGrant><AbstractGrant Grant="OpenAccess"></AbstractGrant><BodyPDFGrant Grant="Restricted"></BodyPDFGrant><BodyHTMLGrant Grant="Restricted"></BodyHTMLGrant><BibliographyGrant Grant="Restricted"></BibliographyGrant><ESMGrant Grant="Restricted"></ESMGrant></ChapterGrants><ChapterContext><SeriesID>558</SeriesID><PartID>7</PartID><BookID>3-540-40063-X</BookID><BookTitle>Advances in Multimodal Interfaces — ICMI 2000</BookTitle></ChapterContext></ChapterInfo><ChapterHeader><AuthorGroup><Author AffiliationIDS="Aff7"><AuthorName DisplayOrder="Western"><GivenName>Wenwei</GivenName><FamilyName>Wang</FamilyName></AuthorName><Contact><Email>wwwang@fb9-ti.uni-duisburg.de</Email></Contact></Author><Author AffiliationIDS="Aff7"><AuthorName DisplayOrder="Western"><GivenName>Anja</GivenName><FamilyName>Brakensiek</FamilyName></AuthorName><Contact><Email>anja@fb9-ti.uni-duisburg.de</Email></Contact></Author><Author AffiliationIDS="Aff7"><AuthorName DisplayOrder="Western"><GivenName>Gerhard</GivenName><FamilyName>Rigoll</FamilyName></AuthorName><Contact><Email>rigoll@fb9-ti.uni-duisburg.de</Email></Contact></Author><Affiliation ID="Aff7"><OrgDivision>Department of Computer Science, Faculty of Electrical Engineering</OrgDivision><OrgName>Gerhard-Mercator-University Duisburg</OrgName><OrgAddress><Street>Bismarckstrasse 90</Street><Postcode>47057</Postcode><City>Duisburg</City><Country>Germany</Country></OrgAddress></Affiliation></AuthorGroup><Abstract ID="Abs1" Language="En"><Heading>Abstract</Heading><Para>The cursive handwriting recognition is a challenging task because the recognition system has to handle not only large shape variation of human handwriting, but also character segmentation. Usually the recognition performance depends crucially upon the segmentation process. Hidden Markov Models (HMMs) have the ability to model similarity and variation among samples of a class. In this paper we present an extended sliding window feature extraction method and an HMM based two-pass modeling approach. Whereas our feature extraction method makes the resulting system more robust with word baseline detection, the two-pass recognition approach exploits the segmentation ability of the Viterbi algorithm and creates another HMM set and carries out a second pass recognition. The total performance is enhanced by combination of the two pass results. Experiments of recognizing cursive handwritten words with 30000 words lexicon have been carried out and show that our novel approach can achieve better recognition performance and reduce the relative error rate significantly.</Para></Abstract></ChapterHeader><NoBody></NoBody></Chapter></Part></Book></Series></Publisher></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition</title></titleInfo><titleInfo type="alternative" contentType="CDATA" lang="en"><title>An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition</title></titleInfo><name type="personal"><namePart type="given">Wenwei</namePart><namePart type="family">Wang</namePart><affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</affiliation><affiliation>E-mail: wwwang@fb9-ti.uni-duisburg.de</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Anja</namePart><namePart type="family">Brakensiek</namePart><affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</affiliation><affiliation>E-mail: anja@fb9-ti.uni-duisburg.de</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Gerhard</namePart><namePart type="family">Rigoll</namePart><affiliation>Department of Computer Science, Faculty of Electrical Engineering, Gerhard-Mercator-University Duisburg, Bismarckstrasse 90, 47057, Duisburg, Germany</affiliation><affiliation>E-mail: rigoll@fb9-ti.uni-duisburg.de</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="conference [eBooks]" displayLabel="OriginalPaper"></genre><originInfo><publisher>Springer Berlin Heidelberg</publisher><place><placeTerm type="text">Berlin, Heidelberg</placeTerm></place><dateIssued encoding="w3cdtf">2000</dateIssued><copyrightDate encoding="w3cdtf">2000</copyrightDate></originInfo><language><languageTerm type="code" authority="rfc3066">en</languageTerm><languageTerm type="code" authority="iso639-2b">eng</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType></physicalDescription><abstract lang="en">Abstract: The cursive handwriting recognition is a challenging task because the recognition system has to handle not only large shape variation of human handwriting, but also character segmentation. Usually the recognition performance depends crucially upon the segmentation process. Hidden Markov Models (HMMs) have the ability to model similarity and variation among samples of a class. In this paper we present an extended sliding window feature extraction method and an HMM based two-pass modeling approach. Whereas our feature extraction method makes the resulting system more robust with word baseline detection, the two-pass recognition approach exploits the segmentation ability of the Viterbi algorithm and creates another HMM set and carries out a second pass recognition. The total performance is enhanced by combination of the two pass results. Experiments of recognizing cursive handwritten words with 30000 words lexicon have been carried out and show that our novel approach can achieve better recognition performance and reduce the relative error rate significantly.</abstract><relatedItem type="host"><titleInfo><title>Advances in Multimodal Interfaces — ICMI 2000</title><subTitle>Third International Conference Beijing, China, October 14–16, 2000 Proceedings</subTitle></titleInfo><name type="personal"><namePart type="given">Tieniu</namePart><namePart type="family">Tan</namePart><affiliation>Institute of Automation, Chinese Academy of Sciences, P.O.Box 2728, 100080, Beijing, China</affiliation><affiliation>E-mail: tnt@nlpr.ia.ac.cn</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><name type="personal"><namePart type="given">Yuanchun</namePart><namePart type="family">Shi</namePart><affiliation>Computer Department, Media Laboratory, Tsinghua University, 100084, Beijing, China</affiliation><affiliation>E-mail: shiyc@tsinghua.edu.cn</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><name type="personal"><namePart type="given">Wen</namePart><namePart type="family">Gao</namePart><affiliation>Institute of Computing Technology, Chinese Academy of Sciences, P.O.Box 2704, 100080, Beijing, China</affiliation><affiliation>E-mail: wgao@cti.com.cn</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><genre type="Book Series" displayLabel="Proceedings"></genre><originInfo><copyrightDate encoding="w3cdtf">2000</copyrightDate><issuance>monographic</issuance></originInfo><subject><genre>Book Subject Collection</genre><topic authority="SpringerSubjectCodes" authorityURI="SUCO11645">Computer Science</topic></subject><subject><genre>Book Subject Group</genre><topic authority="SpringerSubjectCodes" authorityURI="I">Computer Science</topic><topic authority="SpringerSubjectCodes" authorityURI="I18067">User Interfaces and Human Computer Interaction</topic><topic authority="SpringerSubjectCodes" authorityURI="I2203X">Pattern Recognition</topic><topic authority="SpringerSubjectCodes" authorityURI="I22013">Computer Graphics</topic><topic authority="SpringerSubjectCodes" authorityURI="I21017">Artificial Intelligence (incl. Robotics)</topic><topic authority="SpringerSubjectCodes" authorityURI="I14029">Software Engineering</topic></subject><identifier type="DOI">10.1007/3-540-40063-X</identifier><identifier type="ISBN">978-3-540-41180-2</identifier><identifier type="eISBN">978-3-540-40063-9</identifier><identifier type="ISSN">0302-9743</identifier><identifier type="BookTitleID">66868</identifier><identifier type="BookID">3-540-40063-X</identifier><identifier type="BookChapterCount">86</identifier><identifier type="BookVolumeNumber">1948</identifier><identifier type="BookSequenceNumber">1948</identifier><identifier type="PartChapterCount">14</identifier><part><date>2000</date><detail type="part"><title>Handwriting Recognition</title></detail><detail type="volume"><number>1948</number><caption>vol.</caption></detail><extent unit="pages"><start>386</start><end>393</end></extent></part><recordInfo><recordOrigin>Springer-Verlag Berlin Heidelberg, 2000</recordOrigin></recordInfo></relatedItem><relatedItem type="series"><titleInfo><title>Lecture Notes in Computer Science</title></titleInfo><name type="personal"><namePart type="given">Gerhard</namePart><namePart type="family">Goos</namePart><affiliation>Karlsruhe University, Germany</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><name type="personal"><namePart type="given">Juris</namePart><namePart type="family">Hartmanis</namePart><affiliation>Cornell University, NY, USA</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><name type="personal"><namePart type="given">Jan</namePart><namePart type="family">van Leeuwen</namePart><affiliation>Utrecht University, The Netherlands</affiliation><role><roleTerm type="text">editor</roleTerm></role></name><originInfo><copyrightDate encoding="w3cdtf">2000</copyrightDate><issuance>serial</issuance></originInfo><identifier type="ISSN">0302-9743</identifier><identifier type="SeriesID">558</identifier><recordInfo><recordOrigin>Springer-Verlag Berlin Heidelberg, 2000</recordOrigin></recordInfo></relatedItem><identifier type="istex">D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852</identifier><identifier type="DOI">10.1007/3-540-40063-X_51</identifier><identifier type="ChapterID">51</identifier><identifier type="ChapterID">Chap51</identifier><accessCondition type="use and reproduction" contentType="copyright">Springer-Verlag Berlin Heidelberg, 2000</accessCondition><recordInfo><recordContentSource>SPRINGER</recordContentSource><recordOrigin>Springer-Verlag Berlin Heidelberg, 2000</recordOrigin></recordInfo></mods></metadata><enrichments><istex:refBibTEI uri="https://api.istex.fr/document/D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852/enrichments/refBib"><teiHeader></teiHeader><text><front></front><body></body><back><listBibl><biblStruct xml:id="b0"><analytic><title level="a" type="main">Performance Evaluation of a New Hybrid Modeling Technique for Handwriting Recognition Using Identical On- Line and Off-Line Data</title><author><persName><forename type="first">A</forename><surname>Brakensiek</surname></persName></author><author><persName><forename type="first">A</forename><surname>Kosmala</surname></persName></author><author><persName><forename type="first">D</forename><surname>Willett</surname></persName></author><author><persName><forename type="first">W</forename><surname>Wang</surname></persName></author><author><persName><forename type="first">G</forename><surname>Rigoll</surname></persName></author></analytic><monogr><title level="m">Proc. International Conference on Document Analysis and Recognition (ICDAR)</title><meeting>. International Conference on Document Analysis and Recognition (ICDAR)<address><addrLine>Bangalore, India</addrLine></address></meeting><imprint><date type="published" when="1999"></date><biblScope unit="page" from="446" to="449"></biblScope></imprint></monogr></biblStruct><biblStruct xml:id="b1"><analytic><title level="a" type="main">Off-line Cursive Handwriting Recognition Using Hidden Markov Models</title><author><persName><forename type="first">H</forename><surname>Bunke</surname></persName></author><author><persName><forename type="first">M</forename><surname>Roth</surname></persName></author><author><persName><forename type="first">E</forename><forename type="middle">G</forename><surname>Schukat-Talamazzini</surname></persName></author></analytic><monogr><title level="j">Pattern Recognition</title><imprint><biblScope unit="volume">28</biblScope><biblScope unit="issue">9</biblScope><biblScope unit="page" from="1399" to="1413"></biblScope><date type="published" when="1995"></date></imprint></monogr></biblStruct><biblStruct xml:id="b2"><analytic><title level="a" type="main">Modeling and Recognition of Cursive Words with Hidden Markov Models</title><author><persName><forename type="first">Wongyu</forename><surname>Cho</surname></persName></author><author><persName><surname>Seong-Whan</surname></persName></author><author><persName><forename type="first">Jin</forename><forename type="middle">H</forename><surname>Lee</surname></persName></author><author><persName><surname>Kim</surname></persName></author></analytic><monogr><title level="j">Pattern Recognition</title><imprint><biblScope unit="volume">28</biblScope><biblScope unit="issue">12</biblScope><biblScope unit="page" from="1941" to="1953"></biblScope><date type="published" when="1995"></date></imprint></monogr></biblStruct><biblStruct xml:id="b3"><analytic><title level="a" type="main">The advantage of using an HMM-based approach for faxed word recognition</title><author><persName><forename type="first">A</forename><forename type="middle">J</forename><surname>Elms</surname></persName></author><author><persName><forename type="first">S</forename><surname>Procter</surname></persName></author><author><persName><forename type="first">J</forename><surname>Illingworth</surname></persName></author></analytic><monogr><title level="j">International Journal on Document Analysis and Recognition</title><imprint><biblScope unit="volume">1</biblScope><biblScope unit="issue">1</biblScope><biblScope unit="page" from="18" to="36"></biblScope><date type="published" when="1998"></date></imprint></monogr></biblStruct><biblStruct xml:id="b4"><analytic><title level="a" type="main">HMM Word Recognition Engine</title><author><persName><forename type="first">D</forename><surname>Guillevic</surname></persName></author><author><persName><forename type="first">Ching</forename><forename type="middle">Y</forename><surname>Suen</surname></persName></author></analytic><monogr><title level="m">Proc International Conference on Document Analysis and Recognition (ICDAR)</title><meeting>International Conference on Document Analysis and Recognition (ICDAR)<address><addrLine>Ulm, Germany</addrLine></address></meeting><imprint><date type="published" when="1997"></date><biblScope unit="page" from="544" to="547"></biblScope></imprint></monogr></biblStruct><biblStruct xml:id="b5"><analytic><title level="a" type="main">An Introduction to Hidden Markov Models</title><author><persName><forename type="first">L</forename><forename type="middle">R</forename><surname>Rabiner</surname></persName></author><author><persName><forename type="first">B</forename><forename type="middle">H</forename><surname>Juang</surname></persName></author></analytic><monogr><title level="j">IEEE ASSP Magazine</title><imprint><biblScope unit="volume">3</biblScope><biblScope unit="issue">1</biblScope><biblScope unit="page" from="4" to="16"></biblScope><date type="published" when="1986-01"></date></imprint></monogr></biblStruct><biblStruct xml:id="b6"><analytic><title level="a" type="main">A New Hybrid Approach to Large Vocabulary Cursive Handwriting Recognition</title><author><persName><forename type="first">Gerhard</forename><surname>Rigoll</surname></persName></author><author><persName><forename type="first">Andreas</forename><surname>Kosmala</surname></persName></author><author><persName><forename type="first">Daniel</forename><surname>Willett</surname></persName></author></analytic><monogr><title level="m">Proc. International Conference on Pattern Recognition (ICPR)</title><meeting>. International Conference on Pattern Recognition (ICPR)<address><addrLine>Brisbane</addrLine></address></meeting><imprint><date type="published" when="1998"></date><biblScope unit="page" from="446" to="449"></biblScope></imprint></monogr></biblStruct><biblStruct xml:id="b7"><analytic><title level="a" type="main">Feature Extraction Methods for Character Recognition--a Survey</title><author><persName><forename type="first">A</forename><forename type="middle">K</forename><surname>Trier</surname></persName></author><author><persName><forename type="first">T</forename><surname>Jain</surname></persName></author><author><persName><surname>Taxt</surname></persName></author></analytic><monogr><title level="j">Pattern Recognition</title><imprint><biblScope unit="volume">29</biblScope><biblScope unit="issue">4</biblScope><biblScope unit="page" from="641" to="662"></biblScope><date type="published" when="1996"></date></imprint></monogr></biblStruct><biblStruct xml:id="b8"><analytic><title level="a" type="main">HMM based High Accuracy Off-line Cursive Handwriting Recognition by a Baseline Detection Error Tolerant Feature Extraction Approach</title><author><persName><forename type="first">Wenwei</forename><surname>Wang</surname></persName></author><author><persName><forename type="first">Anja</forename><surname>Brakensiek</surname></persName></author><author><persName><forename type="first">Andreas</forename><surname>Kosmala</surname></persName></author><author><persName><forename type="first">Gerhard</forename><surname>Rigoll</surname></persName></author></analytic><monogr><title level="m">Proc. 7th International Workshop on Frontiers in Handwriting Recognition (IWFHR)</title><meeting>. 7th International Workshop on Frontiers in Handwriting Recognition (IWFHR)<address><addrLine>Amsterdam, Netherland</addrLine></address></meeting><imprint><date type="published" when="2000-09"></date></imprint></monogr></biblStruct></listBibl></back></text></istex:refBibTEI></enrichments></istex></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Istex/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001D27 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 001D27 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Istex
|étape= Corpus
|type= RBID
|clé= ISTEX:D3F6BBB153C6EEE4F5D887DBF6460D6F48D24852
|texte= An HMM Based Two-Pass Approach for Off-Line Cursive Handwriting Recognition
}}
| This area was generated with Dilib version V0.6.32. |  |