A Multiple Classifier Approach for the Recognition of Screen-Rendered Text
Identifieur interne : 000F07 ( Main/Exploration ); précédent : 000F06; suivant : 000F08A Multiple Classifier Approach for the Recognition of Screen-Rendered Text
Auteurs : Steffen Wachenfeld [Allemagne] ; Stefan Fleischer [Allemagne] ; Xiaoyi Jiang [Allemagne]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 2007.
Abstract
Abstract: The lower the resolution of a given text is, the more difficult it becomes to segment and to recognize it. The resolution of screen-rendered text can be very low. With a typical x-height of 4 to 7 pixels it is much lower as in other low resolution OCR situations. Modern OCR approaches for such very low resolution text use a classification-based segmentation where the underlying classifier plays an important role. This paper presents a multiple classifier system for the classification of single characters. This system is used as a subsystem for the classification-based segmentation within a system to read screen-rendered text. The paper shows that the presented multiple classifier system outperforms the best former single classifier system on single characters by far and it shows the impact of using the multiple classifier system on the word reading performance.
Url:
DOI: 10.1007/978-3-540-74272-2_114
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002225
- to stream Istex, to step Curation: 002074
- to stream Istex, to step Checkpoint: 000922
- to stream Main, to step Merge: 000F20
- to stream Main, to step Curation: 000F07
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A Multiple Classifier Approach for the Recognition of Screen-Rendered Text</title><author><name sortKey="Wachenfeld, Steffen" sort="Wachenfeld, Steffen" uniqKey="Wachenfeld S" first="Steffen" last="Wachenfeld">Steffen Wachenfeld</name></author><author><name sortKey="Fleischer, Stefan" sort="Fleischer, Stefan" uniqKey="Fleischer S" first="Stefan" last="Fleischer">Stefan Fleischer</name></author><author><name sortKey="Jiang, Xiaoyi" sort="Jiang, Xiaoyi" uniqKey="Jiang X" first="Xiaoyi" last="Jiang">Xiaoyi Jiang</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:6D57AD90C404764EC8471AE5173E7015AB7FA21A</idno><date when="2007" year="2007">2007</date><idno type="doi">10.1007/978-3-540-74272-2_114</idno><idno type="url">https://api.istex.fr/document/6D57AD90C404764EC8471AE5173E7015AB7FA21A/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">002225</idno><idno type="wicri:Area/Istex/Curation">002074</idno><idno type="wicri:Area/Istex/Checkpoint">000922</idno><idno type="wicri:doubleKey">0302-9743:2007:Wachenfeld S:a:multiple:classifier</idno><idno type="wicri:Area/Main/Merge">000F20</idno><idno type="wicri:Area/Main/Curation">000F07</idno><idno type="wicri:Area/Main/Exploration">000F07</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A Multiple Classifier Approach for the Recognition of Screen-Rendered Text</title><author><name sortKey="Wachenfeld, Steffen" sort="Wachenfeld, Steffen" uniqKey="Wachenfeld S" first="Steffen" last="Wachenfeld">Steffen Wachenfeld</name><affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Department of Computer Science, University of Münster, Einsteinstrasse 62, D-48149 Münster</wicri:regionArea><placeName><region type="land" nuts="1">Rhénanie-du-Nord-Westphalie</region><region type="district" nuts="2">District de Münster</region><settlement type="city">Münster</settlement></placeName></affiliation></author><author><name sortKey="Fleischer, Stefan" sort="Fleischer, Stefan" uniqKey="Fleischer S" first="Stefan" last="Fleischer">Stefan Fleischer</name><affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Department of Computer Science, University of Münster, Einsteinstrasse 62, D-48149 Münster</wicri:regionArea><placeName><region type="land" nuts="1">Rhénanie-du-Nord-Westphalie</region><region type="district" nuts="2">District de Münster</region><settlement type="city">Münster</settlement></placeName></affiliation></author><author><name sortKey="Jiang, Xiaoyi" sort="Jiang, Xiaoyi" uniqKey="Jiang X" first="Xiaoyi" last="Jiang">Xiaoyi Jiang</name><affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Department of Computer Science, University of Münster, Einsteinstrasse 62, D-48149 Münster</wicri:regionArea><placeName><region type="land" nuts="1">Rhénanie-du-Nord-Westphalie</region><region type="district" nuts="2">District de Münster</region><settlement type="city">Münster</settlement></placeName></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">6D57AD90C404764EC8471AE5173E7015AB7FA21A</idno><idno type="DOI">10.1007/978-3-540-74272-2_114</idno><idno type="ChapterID">114</idno><idno type="ChapterID">Chap114</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 lower the resolution of a given text is, the more difficult it becomes to segment and to recognize it. The resolution of screen-rendered text can be very low. With a typical x-height of 4 to 7 pixels it is much lower as in other low resolution OCR situations. Modern OCR approaches for such very low resolution text use a classification-based segmentation where the underlying classifier plays an important role. This paper presents a multiple classifier system for the classification of single characters. This system is used as a subsystem for the classification-based segmentation within a system to read screen-rendered text. The paper shows that the presented multiple classifier system outperforms the best former single classifier system on single characters by far and it shows the impact of using the multiple classifier system on the word reading performance.</div></front></TEI><affiliations><list><country><li>Allemagne</li></country><region><li>District de Münster</li><li>Rhénanie-du-Nord-Westphalie</li></region><settlement><li>Münster</li></settlement></list><tree><country name="Allemagne"><region name="Rhénanie-du-Nord-Westphalie"><name sortKey="Wachenfeld, Steffen" sort="Wachenfeld, Steffen" uniqKey="Wachenfeld S" first="Steffen" last="Wachenfeld">Steffen Wachenfeld</name></region><name sortKey="Fleischer, Stefan" sort="Fleischer, Stefan" uniqKey="Fleischer S" first="Stefan" last="Fleischer">Stefan Fleischer</name><name sortKey="Jiang, Xiaoyi" sort="Jiang, Xiaoyi" uniqKey="Jiang X" first="Xiaoyi" last="Jiang">Xiaoyi Jiang</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 000F07 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000F07 | 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:6D57AD90C404764EC8471AE5173E7015AB7FA21A
|texte= A Multiple Classifier Approach for the Recognition of Screen-Rendered Text
}}
| This area was generated with Dilib version V0.6.32. |  |