Learning Visual Shape Lexicon for Document Image Content Recognition
Identifieur interne : 000C18 ( Main/Exploration ); précédent : 000C17; suivant : 000C19Learning Visual Shape Lexicon for Document Image Content Recognition
Auteurs : Guangyu Zhu [États-Unis] ; Xiaodong Yu [États-Unis] ; Yi Li [États-Unis] ; David Doermann [États-Unis]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2008.
Abstract
Abstract: Developing effective content recognition methods for diverse imagery continues to challenge computer vision researchers. We present a new approach for document image content categorization using a lexicon of shape features. Each lexical word corresponds to a scale and rotation invariant shape feature that is generic enough to be detected repeatably and segmentation free. We learn a concise, structurally indexed shape lexicon from training by clustering and partitioning feature types through graph cuts. We demonstrate our approach on two challenging document image content recognition problems: 1) The classification of 4,500 Web images crawled from Google Image Search into three content categories — pure image, image with text, and document image, and 2) Language identification of 8 languages (Arabic, Chinese, English, Hindi, Japanese, Korean, Russian, and Thai) on a 1,512 complex document image database composed of mixed machine printed text and handwriting. Our approach is capable to handle high intra-class variability and shows results that exceed other state-of-the-art approaches, allowing it to be used as a content recognizer in image indexing and retrieval systems.
Url:
DOI: 10.1007/978-3-540-88688-4_55
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000C96
- to stream Istex, to step Curation: 000C73
- to stream Istex, to step Checkpoint: 000685
- to stream Main, to step Merge: 000C30
- to stream Main, to step Curation: 000C18
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Learning Visual Shape Lexicon for Document Image Content Recognition</title>
<author><name sortKey="Zhu, Guangyu" sort="Zhu, Guangyu" uniqKey="Zhu G" first="Guangyu" last="Zhu">Guangyu Zhu</name>
</author>
<author><name sortKey="Yu, Xiaodong" sort="Yu, Xiaodong" uniqKey="Yu X" first="Xiaodong" last="Yu">Xiaodong Yu</name>
</author>
<author><name sortKey="Li, Yi" sort="Li, Yi" uniqKey="Li Y" first="Yi" last="Li">Yi Li</name>
</author>
<author><name sortKey="Doermann, David" sort="Doermann, David" uniqKey="Doermann D" first="David" last="Doermann">David Doermann</name>
<affiliation><country>États-Unis</country>
<placeName><settlement type="city">College Park (Maryland)</settlement>
<region type="state">Maryland</region>
</placeName>
<orgName type="university" n="3">Université du Maryland</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:000EA72B875137D2E35868AFB5C5FCB5D7A54937</idno>
<date when="2008" year="2008">2008</date>
<idno type="doi">10.1007/978-3-540-88688-4_55</idno>
<idno type="url">https://api.istex.fr/document/000EA72B875137D2E35868AFB5C5FCB5D7A54937/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000C96</idno>
<idno type="wicri:Area/Istex/Curation">000C73</idno>
<idno type="wicri:Area/Istex/Checkpoint">000685</idno>
<idno type="wicri:doubleKey">0302-9743:2008:Zhu G:learning:visual:shape</idno>
<idno type="wicri:Area/Main/Merge">000C30</idno>
<idno type="wicri:Area/Main/Curation">000C18</idno>
<idno type="wicri:Area/Main/Exploration">000C18</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Learning Visual Shape Lexicon for Document Image Content Recognition</title>
<author><name sortKey="Zhu, Guangyu" sort="Zhu, Guangyu" uniqKey="Zhu G" first="Guangyu" last="Zhu">Guangyu Zhu</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>University of Maryland, MD 20742, College Park</wicri:regionArea>
<orgName type="university">Université du Maryland</orgName>
<placeName><settlement type="city">College Park (Maryland)</settlement>
<region type="state">Maryland</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Yu, Xiaodong" sort="Yu, Xiaodong" uniqKey="Yu X" first="Xiaodong" last="Yu">Xiaodong Yu</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>University of Maryland, MD 20742, College Park</wicri:regionArea>
<orgName type="university">Université du Maryland</orgName>
<placeName><settlement type="city">College Park (Maryland)</settlement>
<region type="state">Maryland</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Li, Yi" sort="Li, Yi" uniqKey="Li Y" first="Yi" last="Li">Yi Li</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>University of Maryland, MD 20742, College Park</wicri:regionArea>
<orgName type="university">Université du Maryland</orgName>
<placeName><settlement type="city">College Park (Maryland)</settlement>
<region type="state">Maryland</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Doermann, David" sort="Doermann, David" uniqKey="Doermann D" first="David" last="Doermann">David Doermann</name>
<affiliation wicri:level="4"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>University of Maryland, MD 20742, College Park</wicri:regionArea>
<orgName type="university">Université du Maryland</orgName>
<placeName><settlement type="city">College Park (Maryland)</settlement>
<region type="state">Maryland</region>
</placeName>
<placeName><settlement type="city">College Park (Maryland)</settlement>
<region type="state">Maryland</region>
</placeName>
<orgName type="university" n="3">Université du Maryland</orgName>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2008</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">000EA72B875137D2E35868AFB5C5FCB5D7A54937</idno>
<idno type="DOI">10.1007/978-3-540-88688-4_55</idno>
<idno type="ChapterID">55</idno>
<idno type="ChapterID">Chap55</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: Developing effective content recognition methods for diverse imagery continues to challenge computer vision researchers. We present a new approach for document image content categorization using a lexicon of shape features. Each lexical word corresponds to a scale and rotation invariant shape feature that is generic enough to be detected repeatably and segmentation free. We learn a concise, structurally indexed shape lexicon from training by clustering and partitioning feature types through graph cuts. We demonstrate our approach on two challenging document image content recognition problems: 1) The classification of 4,500 Web images crawled from Google Image Search into three content categories — pure image, image with text, and document image, and 2) Language identification of 8 languages (Arabic, Chinese, English, Hindi, Japanese, Korean, Russian, and Thai) on a 1,512 complex document image database composed of mixed machine printed text and handwriting. Our approach is capable to handle high intra-class variability and shows results that exceed other state-of-the-art approaches, allowing it to be used as a content recognizer in image indexing and retrieval systems.</div>
</front>
</TEI>
<affiliations><list><country><li>États-Unis</li>
</country>
<region><li>Maryland</li>
</region>
<settlement><li>College Park (Maryland)</li>
</settlement>
<orgName><li>Université du Maryland</li>
</orgName>
</list>
<tree><country name="États-Unis"><region name="Maryland"><name sortKey="Zhu, Guangyu" sort="Zhu, Guangyu" uniqKey="Zhu G" first="Guangyu" last="Zhu">Guangyu Zhu</name>
</region>
<name sortKey="Doermann, David" sort="Doermann, David" uniqKey="Doermann D" first="David" last="Doermann">David Doermann</name>
<name sortKey="Li, Yi" sort="Li, Yi" uniqKey="Li Y" first="Yi" last="Li">Yi Li</name>
<name sortKey="Yu, Xiaodong" sort="Yu, Xiaodong" uniqKey="Yu X" first="Xiaodong" last="Yu">Xiaodong Yu</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000C18 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000C18 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:000EA72B875137D2E35868AFB5C5FCB5D7A54937 |texte= Learning Visual Shape Lexicon for Document Image Content Recognition }}
This area was generated with Dilib version V0.6.32. |