Performance Evaluation of Document Structure Extraction Algorithms
Identifieur interne : 001281 ( Istex/Corpus ); précédent : 001280; suivant : 001282Performance Evaluation of Document Structure Extraction Algorithms
Auteurs : Jisheng Liang ; Ihsin T. Phillips ; Robert M. HaralickSource :
- Computer Vision and Image Understanding [ 1077-3142 ] ; 2001.
Abstract
This paper presents a performance metric for the document structure extraction algorithms by finding the correspondences between detected entities and ground truth. We describe a method for determining an algorithm's optimal tuning parameters. We evaluate a group of document layout analysis algorithms on 1600 images from the UW-III Document Image Database, and the quantitative performance measures in terms of the rates of correct, miss, false, merging, splitting, and spurious detections are reported.
Url:
DOI: 10.1006/cviu.2001.0933
Links to Exploration step
ISTEX:6D95DE6FDA572CD6B6664F645C6E2FCB4A12889ELe document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Performance Evaluation of Document Structure Extraction Algorithms</title><author><name sortKey="Liang, Jisheng" sort="Liang, Jisheng" uniqKey="Liang J" first="Jisheng" last="Liang">Jisheng Liang</name><affiliation><mods:affiliation>Insightful Corporation, 1700 Westlake Avenue N. Suite 500, Seattle, Washington, 98109, f1 jliang@insightful.comf1</mods:affiliation></affiliation></author><author><name sortKey="Phillips, Ihsin T" sort="Phillips, Ihsin T" uniqKey="Phillips I" first="Ihsin T" last="Phillips">Ihsin T. Phillips</name><affiliation><mods:affiliation>Department of Computer Science, Queens College, City University of New York, 65-30 Kissena Boulevard, Flushing, New York, 11367, f2 yun@image.cs.qc.eduf2</mods:affiliation></affiliation></author><author><name sortKey="Haralick, Robert M" sort="Haralick, Robert M" uniqKey="Haralick R" first="Robert M" last="Haralick">Robert M. Haralick</name><affiliation><mods:affiliation>Department of Computer Science, Graduate Center, City University of New York, 365 Fifth Avenue, New York, New York, 10016, f3 haralick@gc.cuny.eduf3</mods:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E</idno><date when="2001" year="2001">2001</date><idno type="doi">10.1006/cviu.2001.0933</idno><idno type="url">https://api.istex.fr/document/6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001281</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Performance Evaluation of Document Structure Extraction Algorithms</title><author><name sortKey="Liang, Jisheng" sort="Liang, Jisheng" uniqKey="Liang J" first="Jisheng" last="Liang">Jisheng Liang</name><affiliation><mods:affiliation>Insightful Corporation, 1700 Westlake Avenue N. Suite 500, Seattle, Washington, 98109, f1 jliang@insightful.comf1</mods:affiliation></affiliation></author><author><name sortKey="Phillips, Ihsin T" sort="Phillips, Ihsin T" uniqKey="Phillips I" first="Ihsin T" last="Phillips">Ihsin T. Phillips</name><affiliation><mods:affiliation>Department of Computer Science, Queens College, City University of New York, 65-30 Kissena Boulevard, Flushing, New York, 11367, f2 yun@image.cs.qc.eduf2</mods:affiliation></affiliation></author><author><name sortKey="Haralick, Robert M" sort="Haralick, Robert M" uniqKey="Haralick R" first="Robert M" last="Haralick">Robert M. Haralick</name><affiliation><mods:affiliation>Department of Computer Science, Graduate Center, City University of New York, 365 Fifth Avenue, New York, New York, 10016, f3 haralick@gc.cuny.eduf3</mods:affiliation></affiliation></author></analytic><monogr></monogr><series><title level="j">Computer Vision and Image Understanding</title><title level="j" type="abbrev">YCVIU</title><idno type="ISSN">1077-3142</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="2001">2001</date><biblScope unit="volume">84</biblScope><biblScope unit="issue">1</biblScope><biblScope unit="page" from="144">144</biblScope><biblScope unit="page" to="159">159</biblScope></imprint><idno type="ISSN">1077-3142</idno></series><idno type="istex">6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E</idno><idno type="DOI">10.1006/cviu.2001.0933</idno><idno type="PII">S1077-3142(01)90933-6</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1077-3142</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This paper presents a performance metric for the document structure extraction algorithms by finding the correspondences between detected entities and ground truth. We describe a method for determining an algorithm's optimal tuning parameters. We evaluate a group of document layout analysis algorithms on 1600 images from the UW-III Document Image Database, and the quantitative performance measures in terms of the rates of correct, miss, false, merging, splitting, and spurious detections are reported.</div></front></TEI><istex><corpusName>elsevier</corpusName><author><json:item><name>Jisheng Liang</name><affiliations><json:string>Insightful Corporation, 1700 Westlake Avenue N. Suite 500, Seattle, Washington, 98109, f1 jliang@insightful.comf1</json:string></affiliations></json:item><json:item><name>Ihsin T Phillips</name><affiliations><json:string>Department of Computer Science, Queens College, City University of New York, 65-30 Kissena Boulevard, Flushing, New York, 11367, f2 yun@image.cs.qc.eduf2</json:string></affiliations></json:item><json:item><name>Robert M Haralick</name><affiliations><json:string>Department of Computer Science, Graduate Center, City University of New York, 365 Fifth Avenue, New York, New York, 10016, f3 haralick@gc.cuny.eduf3</json:string></affiliations></json:item></author><language><json:string>eng</json:string></language><abstract>This paper presents a performance metric for the document structure extraction algorithms by finding the correspondences between detected entities and ground truth. We describe a method for determining an algorithm's optimal tuning parameters. We evaluate a group of document layout analysis algorithms on 1600 images from the UW-III Document Image Database, and the quantitative performance measures in terms of the rates of correct, miss, false, merging, splitting, and spurious detections are reported.</abstract><qualityIndicators><score>5.864</score><pdfVersion>1.3</pdfVersion><pdfPageSize>393.732 x 667.276 pts</pdfPageSize><refBibsNative>true</refBibsNative><keywordCount>0</keywordCount><abstractCharCount>505</abstractCharCount><pdfWordCount>5550</pdfWordCount><pdfCharCount>31350</pdfCharCount><pdfPageCount>16</pdfPageCount><abstractWordCount>72</abstractWordCount></qualityIndicators><title>Performance Evaluation of Document Structure Extraction Algorithms</title><pii><json:string>S1077-3142(01)90933-6</json:string></pii><genre><json:string>research-article</json:string></genre><host><volume>84</volume><pii><json:string>S1077-3142(00)X0001-X</json:string></pii><pages><last>159</last><first>144</first></pages><issn><json:string>1077-3142</json:string></issn><issue>1</issue><genre><json:string>Journal</json:string></genre><language><json:string>unknown</json:string></language><title>Computer Vision and Image Understanding</title><publicationDate>2001</publicationDate></host><categories><wos><json:string>COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</json:string><json:string>COMPUTER SCIENCE, SOFTWARE ENGINEERING</json:string><json:string>ENGINEERING, ELECTRICAL & ELECTRONIC</json:string></wos></categories><publicationDate>2001</publicationDate><copyrightDate>2001</copyrightDate><doi><json:string>10.1006/cviu.2001.0933</json:string></doi><id>6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E</id><fulltext><json:item><original>true</original><mimetype>application/pdf</mimetype><extension>pdf</extension><uri>https://api.istex.fr/document/6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E/fulltext/pdf</uri></json:item><json:item><original>false</original><mimetype>application/zip</mimetype><extension>zip</extension><uri>https://api.istex.fr/document/6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E/fulltext/zip</uri></json:item><istex:fulltextTEI uri="https://api.istex.fr/document/6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a" type="main" xml:lang="en">Performance Evaluation of Document Structure Extraction Algorithms</title></titleStmt><publicationStmt><authority>ISTEX</authority><publisher>ELSEVIER</publisher><availability><p>ELSEVIER</p></availability><date>2001</date></publicationStmt><notesStmt><note type="content">Section title: Regular Article</note></notesStmt><sourceDesc><biblStruct type="inbook"><analytic><title level="a" type="main" xml:lang="en">Performance Evaluation of Document Structure Extraction Algorithms</title><author><persName><forename type="first">Jisheng</forename><surname>Liang</surname></persName><affiliation>Insightful Corporation, 1700 Westlake Avenue N. Suite 500, Seattle, Washington, 98109, f1 jliang@insightful.comf1</affiliation></author><author><persName><forename type="first">Ihsin T</forename><surname>Phillips</surname></persName><affiliation>Department of Computer Science, Queens College, City University of New York, 65-30 Kissena Boulevard, Flushing, New York, 11367, f2 yun@image.cs.qc.eduf2</affiliation></author><author><persName><forename type="first">Robert M</forename><surname>Haralick</surname></persName><affiliation>Department of Computer Science, Graduate Center, City University of New York, 365 Fifth Avenue, New York, New York, 10016, f3 haralick@gc.cuny.eduf3</affiliation></author></analytic><monogr><title level="j">Computer Vision and Image Understanding</title><title level="j" type="abbrev">YCVIU</title><idno type="pISSN">1077-3142</idno><idno type="PII">S1077-3142(00)X0001-X</idno><imprint><publisher>ELSEVIER</publisher><date type="published" when="2001"></date><biblScope unit="volume">84</biblScope><biblScope unit="issue">1</biblScope><biblScope unit="page" from="144">144</biblScope><biblScope unit="page" to="159">159</biblScope></imprint></monogr><idno type="istex">6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E</idno><idno type="DOI">10.1006/cviu.2001.0933</idno><idno type="PII">S1077-3142(01)90933-6</idno></biblStruct></sourceDesc></fileDesc><profileDesc><creation><date>2001</date></creation><langUsage><language ident="en">en</language></langUsage><abstract xml:lang="en"><p>This paper presents a performance metric for the document structure extraction algorithms by finding the correspondences between detected entities and ground truth. We describe a method for determining an algorithm's optimal tuning parameters. We evaluate a group of document layout analysis algorithms on 1600 images from the UW-III Document Image Database, and the quantitative performance measures in terms of the rates of correct, miss, false, merging, splitting, and spurious detections are reported.</p></abstract></profileDesc><revisionDesc><change when="2001-08-08">Registration</change><change when="2001">Published</change></revisionDesc></teiHeader></istex:fulltextTEI><json:item><original>false</original><mimetype>text/plain</mimetype><extension>txt</extension><uri>https://api.istex.fr/document/6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E/fulltext/txt</uri></json:item></fulltext><metadata><istex:metadataXml wicri:clean="Elsevier, elements deleted: tail"><istex:xmlDeclaration>version="1.0" encoding="utf-8"</istex:xmlDeclaration><istex:docType PUBLIC="-//ES//DTD journal article DTD version 4.5.2//EN//XML" URI="art452.dtd" name="istex:docType"></istex:docType><istex:document><converted-article version="4.5.2" docsubtype="fla" xml:lang="en"><item-info><jid>YCVIU</jid><aid>90933</aid><ce:pii>S1077-3142(01)90933-6</ce:pii><ce:doi>10.1006/cviu.2001.0933</ce:doi><ce:copyright type="full-transfer" year="2001">Elsevier Science (USA)</ce:copyright></item-info><head><ce:dochead><ce:textfn>Regular Article</ce:textfn></ce:dochead><ce:title>Performance Evaluation of Document Structure Extraction Algorithms</ce:title><ce:author-group><ce:author><ce:given-name>Jisheng</ce:given-name><ce:surname>Liang</ce:surname><ce:cross-ref refid="A0"><ce:sup>a</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Ihsin T</ce:given-name><ce:surname>Phillips</ce:surname><ce:cross-ref refid="A1"><ce:sup>b</ce:sup></ce:cross-ref></ce:author><ce:author><ce:given-name>Robert M</ce:given-name><ce:surname>Haralick</ce:surname><ce:cross-ref refid="A2"><ce:sup>c</ce:sup></ce:cross-ref></ce:author><ce:affiliation id="A0"><ce:label>a</ce:label><ce:textfn>Insightful Corporation, 1700 Westlake Avenue N. Suite 500, Seattle, Washington, 98109, <ce:footnote id="F1"><ce:label>f1</ce:label><ce:note-para>jliang@insightful.com</ce:note-para></ce:footnote><ce:cross-ref refid="F1"><ce:sup>f1</ce:sup></ce:cross-ref></ce:textfn></ce:affiliation><ce:affiliation id="A1"><ce:label>b</ce:label><ce:textfn>Department of Computer Science, Queens College, City University of New York, 65-30 Kissena Boulevard, Flushing, New York, 11367, <ce:footnote id="F2"><ce:label>f2</ce:label><ce:note-para>yun@image.cs.qc.edu</ce:note-para></ce:footnote><ce:cross-ref refid="F2"><ce:sup>f2</ce:sup></ce:cross-ref></ce:textfn></ce:affiliation><ce:affiliation id="A2"><ce:label>c</ce:label><ce:textfn>Department of Computer Science, Graduate Center, City University of New York, 365 Fifth Avenue, New York, New York, 10016, <ce:footnote id="F3"><ce:label>f3</ce:label><ce:note-para>haralick@gc.cuny.edu</ce:note-para></ce:footnote><ce:cross-ref refid="F3"><ce:sup>f3</ce:sup></ce:cross-ref></ce:textfn></ce:affiliation></ce:author-group><ce:date-received day="15" month="9" year="1999"></ce:date-received><ce:date-accepted day="8" month="8" year="2001"></ce:date-accepted><ce:abstract><ce:section-title>Abstract</ce:section-title><ce:abstract-sec><ce:simple-para>This paper presents a performance metric for the document structure extraction algorithms by finding the correspondences between detected entities and ground truth. We describe a method for determining an algorithm's optimal tuning parameters. We evaluate a group of document layout analysis algorithms on 1600 images from the UW-III Document Image Database, and the quantitative performance measures in terms of the rates of correct, miss, false, merging, splitting, and spurious detections are reported.</ce:simple-para></ce:abstract-sec></ce:abstract></head></converted-article></istex:document></istex:metadataXml><mods version="3.6"><titleInfo lang="en"><title>Performance Evaluation of Document Structure Extraction Algorithms</title></titleInfo><titleInfo type="alternative" lang="en" contentType="CDATA"><title>Performance Evaluation of Document Structure Extraction Algorithms</title></titleInfo><name type="personal"><namePart type="given">Jisheng</namePart><namePart type="family">Liang</namePart><affiliation>Insightful Corporation, 1700 Westlake Avenue N. Suite 500, Seattle, Washington, 98109, f1 jliang@insightful.comf1</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Ihsin T</namePart><namePart type="family">Phillips</namePart><affiliation>Department of Computer Science, Queens College, City University of New York, 65-30 Kissena Boulevard, Flushing, New York, 11367, f2 yun@image.cs.qc.eduf2</affiliation><role><roleTerm type="text">author</roleTerm></role></name><name type="personal"><namePart type="given">Robert M</namePart><namePart type="family">Haralick</namePart><affiliation>Department of Computer Science, Graduate Center, City University of New York, 365 Fifth Avenue, New York, New York, 10016, f3 haralick@gc.cuny.eduf3</affiliation><role><roleTerm type="text">author</roleTerm></role></name><typeOfResource>text</typeOfResource><genre type="research-article" displayLabel="Full-length article"></genre><originInfo><publisher>ELSEVIER</publisher><dateIssued encoding="w3cdtf">2001</dateIssued><dateValid encoding="w3cdtf">2001-08-08</dateValid><copyrightDate encoding="w3cdtf">2001</copyrightDate></originInfo><language><languageTerm type="code" authority="iso639-2b">eng</languageTerm><languageTerm type="code" authority="rfc3066">en</languageTerm></language><physicalDescription><internetMediaType>text/html</internetMediaType></physicalDescription><abstract lang="en">This paper presents a performance metric for the document structure extraction algorithms by finding the correspondences between detected entities and ground truth. We describe a method for determining an algorithm's optimal tuning parameters. We evaluate a group of document layout analysis algorithms on 1600 images from the UW-III Document Image Database, and the quantitative performance measures in terms of the rates of correct, miss, false, merging, splitting, and spurious detections are reported.</abstract><note type="content">Section title: Regular Article</note><relatedItem type="host"><titleInfo><title>Computer Vision and Image Understanding</title></titleInfo><titleInfo type="abbreviated"><title>YCVIU</title></titleInfo><genre type="Journal">journal</genre><originInfo><dateIssued encoding="w3cdtf">200110</dateIssued></originInfo><identifier type="ISSN">1077-3142</identifier><identifier type="PII">S1077-3142(00)X0001-X</identifier><part><date>200110</date><detail type="volume"><number>84</number><caption>vol.</caption></detail><detail type="issue"><number>1</number><caption>no.</caption></detail><extent unit="issue pages"><start>1</start><end>199</end></extent><extent unit="pages"><start>144</start><end>159</end></extent></part></relatedItem><identifier type="istex">6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E</identifier><identifier type="DOI">10.1006/cviu.2001.0933</identifier><identifier type="PII">S1077-3142(01)90933-6</identifier><accessCondition type="use and reproduction" contentType="">© 2001Elsevier Science (USA)</accessCondition><recordInfo><recordContentSource>ELSEVIER</recordContentSource><recordOrigin>Elsevier Science (USA), ©2001</recordOrigin></recordInfo></mods></metadata><enrichments><istex:catWosTEI uri="https://api.istex.fr/document/6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E/enrichments/catWos"><teiHeader><profileDesc><textClass><classCode scheme="WOS">COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</classCode><classCode scheme="WOS">COMPUTER SCIENCE, SOFTWARE ENGINEERING</classCode><classCode scheme="WOS">ENGINEERING, ELECTRICAL & ELECTRONIC</classCode></textClass></profileDesc></teiHeader></istex:catWosTEI></enrichments><serie></serie></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 001281 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 001281 | 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:6D95DE6FDA572CD6B6664F645C6E2FCB4A12889E
|texte= Performance Evaluation of Document Structure Extraction Algorithms
}}
| This area was generated with Dilib version V0.6.32. |  |