A HMM-Based Approach to Recognize Ultra Low Resolution Anti-Aliased Words
Identifieur interne : 000F10 ( Main/Exploration ); précédent : 000F09; suivant : 000F11A HMM-Based Approach to Recognize Ultra Low Resolution Anti-Aliased Words
Auteurs : Farshideh Einsele [Suisse] ; Rolf Ingold [Suisse] ; Jean Hennebert [Suisse]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2007.
Abstract
Abstract: In this paper, we present a HMM based system that is used to recognize ultra low resolution text such as those frequently embedded in images available on the web. We propose a system that takes specifically the challenges of recognizing text in ultra low resolution images into account. In addition to this, we show in this paper that word models can be advantageously built connecting together sub-HMM-character models and inter-character state. Finally we report on the promising performance of the system using HMM topologies which have been improved to take into account the presupposed minimum length of each character.
Url:
DOI: 10.1007/978-3-540-77046-6_63
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000631
- to stream Istex, to step Curation: 000623
- to stream Istex, to step Checkpoint: 000925
- to stream Main, to step Merge: 000F23
- to stream Main, to step Curation: 000F10
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A HMM-Based Approach to Recognize Ultra Low Resolution Anti-Aliased Words</title>
<author><name sortKey="Einsele, Farshideh" sort="Einsele, Farshideh" uniqKey="Einsele F" first="Farshideh" last="Einsele">Farshideh Einsele</name>
</author>
<author><name sortKey="Ingold, Rolf" sort="Ingold, Rolf" uniqKey="Ingold R" first="Rolf" last="Ingold">Rolf Ingold</name>
</author>
<author><name sortKey="Hennebert, Jean" sort="Hennebert, Jean" uniqKey="Hennebert J" first="Jean" last="Hennebert">Jean Hennebert</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:8736746BFF748D608EA398BED3ED9DAA21A88C91</idno>
<date when="2007" year="2007">2007</date>
<idno type="doi">10.1007/978-3-540-77046-6_63</idno>
<idno type="url">https://api.istex.fr/document/8736746BFF748D608EA398BED3ED9DAA21A88C91/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000631</idno>
<idno type="wicri:Area/Istex/Curation">000623</idno>
<idno type="wicri:Area/Istex/Checkpoint">000925</idno>
<idno type="wicri:doubleKey">0302-9743:2007:Einsele F:a:hmm:based</idno>
<idno type="wicri:Area/Main/Merge">000F23</idno>
<idno type="wicri:Area/Main/Curation">000F10</idno>
<idno type="wicri:Area/Main/Exploration">000F10</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A HMM-Based Approach to Recognize Ultra Low Resolution Anti-Aliased Words</title>
<author><name sortKey="Einsele, Farshideh" sort="Einsele, Farshideh" uniqKey="Einsele F" first="Farshideh" last="Einsele">Farshideh Einsele</name>
<affiliation wicri:level="1"><country xml:lang="fr">Suisse</country>
<wicri:regionArea>Université de Fribourg, Boulevard de Pérolles 90, 1700 Fribourg</wicri:regionArea>
<wicri:noRegion>1700 Fribourg</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Suisse</country>
</affiliation>
</author>
<author><name sortKey="Ingold, Rolf" sort="Ingold, Rolf" uniqKey="Ingold R" first="Rolf" last="Ingold">Rolf Ingold</name>
<affiliation wicri:level="1"><country xml:lang="fr">Suisse</country>
<wicri:regionArea>Université de Fribourg, Boulevard de Pérolles 90, 1700 Fribourg</wicri:regionArea>
<wicri:noRegion>1700 Fribourg</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Suisse</country>
</affiliation>
</author>
<author><name sortKey="Hennebert, Jean" sort="Hennebert, Jean" uniqKey="Hennebert J" first="Jean" last="Hennebert">Jean Hennebert</name>
<affiliation wicri:level="1"><country xml:lang="fr">Suisse</country>
<wicri:regionArea>Université de Fribourg, Boulevard de Pérolles 90, 1700 Fribourg</wicri:regionArea>
<wicri:noRegion>1700 Fribourg</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">Suisse</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="s">Lecture Notes in Computer Science</title>
<imprint><date>2007</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">8736746BFF748D608EA398BED3ED9DAA21A88C91</idno>
<idno type="DOI">10.1007/978-3-540-77046-6_63</idno>
<idno type="ChapterID">63</idno>
<idno type="ChapterID">Chap63</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, we present a HMM based system that is used to recognize ultra low resolution text such as those frequently embedded in images available on the web. We propose a system that takes specifically the challenges of recognizing text in ultra low resolution images into account. In addition to this, we show in this paper that word models can be advantageously built connecting together sub-HMM-character models and inter-character state. Finally we report on the promising performance of the system using HMM topologies which have been improved to take into account the presupposed minimum length of each character.</div>
</front>
</TEI>
<affiliations><list><country><li>Suisse</li>
</country>
</list>
<tree><country name="Suisse"><noRegion><name sortKey="Einsele, Farshideh" sort="Einsele, Farshideh" uniqKey="Einsele F" first="Farshideh" last="Einsele">Farshideh Einsele</name>
</noRegion>
<name sortKey="Einsele, Farshideh" sort="Einsele, Farshideh" uniqKey="Einsele F" first="Farshideh" last="Einsele">Farshideh Einsele</name>
<name sortKey="Hennebert, Jean" sort="Hennebert, Jean" uniqKey="Hennebert J" first="Jean" last="Hennebert">Jean Hennebert</name>
<name sortKey="Hennebert, Jean" sort="Hennebert, Jean" uniqKey="Hennebert J" first="Jean" last="Hennebert">Jean Hennebert</name>
<name sortKey="Ingold, Rolf" sort="Ingold, Rolf" uniqKey="Ingold R" first="Rolf" last="Ingold">Rolf Ingold</name>
<name sortKey="Ingold, Rolf" sort="Ingold, Rolf" uniqKey="Ingold R" first="Rolf" last="Ingold">Rolf Ingold</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 000F10 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000F10 | 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:8736746BFF748D608EA398BED3ED9DAA21A88C91 |texte= A HMM-Based Approach to Recognize Ultra Low Resolution Anti-Aliased Words }}
This area was generated with Dilib version V0.6.32. |