Efficient OCR Post-Processing Combining Language, Hypothesis and Error Models
Identifieur interne : 000723 ( Main/Exploration ); précédent : 000722; suivant : 000724Efficient OCR Post-Processing Combining Language, Hypothesis and Error Models
Auteurs : Rafael Llobet [Espagne] ; Ramon Navarro-Cerdan [Espagne] ; Juan-Carlos Perez-Cortes [Espagne] ; Joaquim Arlandis [Espagne]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2010.
Abstract
Abstract: In this paper, an OCR post-processing method that combines a language model, OCR hypothesis information and an error model is proposed. The approach can be seen as a flexible and efficient way to perform Stochastic Error-Correcting Language Modeling. We use Weighted Finite-State Transducers (WFSTs) to represent the language model, the complete set of OCR hypotheses interpreted as a sequence of vectors of a posteriori class probabilities, and an error model with symbol substitutions, insertions and deletions. This approach combines the practical advantages of a de-coupled (OCR + post-processor) model with the error-recovery power of a integrated model.
Url:
DOI: 10.1007/978-3-642-14980-1_72
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000055
- to stream Istex, to step Curation: 000054
- to stream Istex, to step Checkpoint: 000303
- to stream Main, to step Merge: 000728
- to stream Main, to step Curation: 000723
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Efficient OCR Post-Processing Combining Language, Hypothesis and Error Models</title>
<author><name sortKey="Llobet, Rafael" sort="Llobet, Rafael" uniqKey="Llobet R" first="Rafael" last="Llobet">Rafael Llobet</name>
</author>
<author><name sortKey="Navarro Cerdan, Ramon" sort="Navarro Cerdan, Ramon" uniqKey="Navarro Cerdan R" first="Ramon" last="Navarro-Cerdan">Ramon Navarro-Cerdan</name>
</author>
<author><name sortKey="Perez Cortes, Juan Carlos" sort="Perez Cortes, Juan Carlos" uniqKey="Perez Cortes J" first="Juan-Carlos" last="Perez-Cortes">Juan-Carlos Perez-Cortes</name>
</author>
<author><name sortKey="Arlandis, Joaquim" sort="Arlandis, Joaquim" uniqKey="Arlandis J" first="Joaquim" last="Arlandis">Joaquim Arlandis</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:E70F75E4C62E23F0E8A52968C3BABCB12585910A</idno>
<date when="2010" year="2010">2010</date>
<idno type="doi">10.1007/978-3-642-14980-1_72</idno>
<idno type="url">https://api.istex.fr/document/E70F75E4C62E23F0E8A52968C3BABCB12585910A/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000055</idno>
<idno type="wicri:Area/Istex/Curation">000054</idno>
<idno type="wicri:Area/Istex/Checkpoint">000303</idno>
<idno type="wicri:doubleKey">0302-9743:2010:Llobet R:efficient:ocr:post</idno>
<idno type="wicri:Area/Main/Merge">000728</idno>
<idno type="wicri:Area/Main/Curation">000723</idno>
<idno type="wicri:Area/Main/Exploration">000723</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Efficient OCR Post-Processing Combining Language, Hypothesis and Error Models</title>
<author><name sortKey="Llobet, Rafael" sort="Llobet, Rafael" uniqKey="Llobet R" first="Rafael" last="Llobet">Rafael Llobet</name>
<affiliation wicri:level="1"><country xml:lang="fr">Espagne</country>
<wicri:regionArea>Instituto Tecnologico de Informatica, Universidad Politecnica de Valencia, Camino de Vera s/n, 46071, Valencia</wicri:regionArea>
<wicri:noRegion>Valencia</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Espagne</country>
</affiliation>
</author>
<author><name sortKey="Navarro Cerdan, Ramon" sort="Navarro Cerdan, Ramon" uniqKey="Navarro Cerdan R" first="Ramon" last="Navarro-Cerdan">Ramon Navarro-Cerdan</name>
<affiliation wicri:level="1"><country xml:lang="fr">Espagne</country>
<wicri:regionArea>Instituto Tecnologico de Informatica, Universidad Politecnica de Valencia, Camino de Vera s/n, 46071, Valencia</wicri:regionArea>
<wicri:noRegion>Valencia</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Espagne</country>
</affiliation>
</author>
<author><name sortKey="Perez Cortes, Juan Carlos" sort="Perez Cortes, Juan Carlos" uniqKey="Perez Cortes J" first="Juan-Carlos" last="Perez-Cortes">Juan-Carlos Perez-Cortes</name>
<affiliation wicri:level="1"><country xml:lang="fr">Espagne</country>
<wicri:regionArea>Instituto Tecnologico de Informatica, Universidad Politecnica de Valencia, Camino de Vera s/n, 46071, Valencia</wicri:regionArea>
<wicri:noRegion>Valencia</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Espagne</country>
</affiliation>
</author>
<author><name sortKey="Arlandis, Joaquim" sort="Arlandis, Joaquim" uniqKey="Arlandis J" first="Joaquim" last="Arlandis">Joaquim Arlandis</name>
<affiliation wicri:level="1"><country xml:lang="fr">Espagne</country>
<wicri:regionArea>Instituto Tecnologico de Informatica, Universidad Politecnica de Valencia, Camino de Vera s/n, 46071, Valencia</wicri:regionArea>
<wicri:noRegion>Valencia</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Espagne</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2010</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">E70F75E4C62E23F0E8A52968C3BABCB12585910A</idno>
<idno type="DOI">10.1007/978-3-642-14980-1_72</idno>
<idno type="ChapterID">72</idno>
<idno type="ChapterID">Chap72</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: In this paper, an OCR post-processing method that combines a language model, OCR hypothesis information and an error model is proposed. The approach can be seen as a flexible and efficient way to perform Stochastic Error-Correcting Language Modeling. We use Weighted Finite-State Transducers (WFSTs) to represent the language model, the complete set of OCR hypotheses interpreted as a sequence of vectors of a posteriori class probabilities, and an error model with symbol substitutions, insertions and deletions. This approach combines the practical advantages of a de-coupled (OCR + post-processor) model with the error-recovery power of a integrated model.</div>
</front>
</TEI>
<affiliations><list><country><li>Espagne</li>
</country>
</list>
<tree><country name="Espagne"><noRegion><name sortKey="Llobet, Rafael" sort="Llobet, Rafael" uniqKey="Llobet R" first="Rafael" last="Llobet">Rafael Llobet</name>
</noRegion>
<name sortKey="Arlandis, Joaquim" sort="Arlandis, Joaquim" uniqKey="Arlandis J" first="Joaquim" last="Arlandis">Joaquim Arlandis</name>
<name sortKey="Arlandis, Joaquim" sort="Arlandis, Joaquim" uniqKey="Arlandis J" first="Joaquim" last="Arlandis">Joaquim Arlandis</name>
<name sortKey="Llobet, Rafael" sort="Llobet, Rafael" uniqKey="Llobet R" first="Rafael" last="Llobet">Rafael Llobet</name>
<name sortKey="Navarro Cerdan, Ramon" sort="Navarro Cerdan, Ramon" uniqKey="Navarro Cerdan R" first="Ramon" last="Navarro-Cerdan">Ramon Navarro-Cerdan</name>
<name sortKey="Navarro Cerdan, Ramon" sort="Navarro Cerdan, Ramon" uniqKey="Navarro Cerdan R" first="Ramon" last="Navarro-Cerdan">Ramon Navarro-Cerdan</name>
<name sortKey="Perez Cortes, Juan Carlos" sort="Perez Cortes, Juan Carlos" uniqKey="Perez Cortes J" first="Juan-Carlos" last="Perez-Cortes">Juan-Carlos Perez-Cortes</name>
<name sortKey="Perez Cortes, Juan Carlos" sort="Perez Cortes, Juan Carlos" uniqKey="Perez Cortes J" first="Juan-Carlos" last="Perez-Cortes">Juan-Carlos Perez-Cortes</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 000723 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000723 | 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:E70F75E4C62E23F0E8A52968C3BABCB12585910A |texte= Efficient OCR Post-Processing Combining Language, Hypothesis and Error Models }}
This area was generated with Dilib version V0.6.32. |