Context-based filtering for document image compression
Identifieur interne : 001E40 ( Main/Exploration ); précédent : 001E39; suivant : 001E41Context-based filtering for document image compression
Auteurs : E. Ageenko [Finlande] ; P. Fr Nti [Finlande]Source :
- SPIE proceedings series [ 1017-2653 ] ; 2000.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Méthode statistique, Numérisation, Document électronique.
English descriptors
- KwdEn :
Abstract
Two statistical context-based filters are proposed for the enhancement of the binary document images for compression and recognition. The Simple Context Filter unconditionally changes the uncommon pixels in low information contexts, whereas the Gain-Loss Filter changes the pixels conditionally depending whether the gain in compression outweighs the loss of information. The evaluation methods and results with some traditional filtering methods are presented. The filtering methods alleviate the loss in compression performance caused by digitization noise while preserving the image quality measured as the OCR accuracy. The Gain-Loss Filter reaches approximately the compression limit estimated by the compression of the noiseless digital original.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000747
- to stream PascalFrancis, to step Curation: 000046
- to stream PascalFrancis, to step Checkpoint: 000737
- to stream Main, to step Merge: 001F49
- to stream Main, to step Curation: 001E40
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Context-based filtering for document image compression</title>
<author><name sortKey="Ageenko, E" sort="Ageenko, E" uniqKey="Ageenko E" first="E." last="Ageenko">E. Ageenko</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Dept. of Computer Science, Univ. of Joensuu, Box 111</s1>
<s2>80101 Joensuu</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Finlande</country>
<wicri:noRegion>80101 Joensuu</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Fr Nti, P" sort="Fr Nti, P" uniqKey="Fr Nti P" first="P." last="Fr Nti">P. Fr Nti</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Dept. of Computer Science, Univ. of Joensuu, Box 111</s1>
<s2>80101 Joensuu</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Finlande</country>
<wicri:noRegion>80101 Joensuu</wicri:noRegion>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">01-0027683</idno>
<date when="2000">2000</date>
<idno type="stanalyst">PASCAL 01-0027683 INIST</idno>
<idno type="RBID">Pascal:01-0027683</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000747</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000046</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000737</idno>
<idno type="wicri:doubleKey">1017-2653:2000:Ageenko E:context:based:filtering</idno>
<idno type="wicri:Area/Main/Merge">001F49</idno>
<idno type="wicri:Area/Main/Curation">001E40</idno>
<idno type="wicri:Area/Main/Exploration">001E40</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Context-based filtering for document image compression</title>
<author><name sortKey="Ageenko, E" sort="Ageenko, E" uniqKey="Ageenko E" first="E." last="Ageenko">E. Ageenko</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Dept. of Computer Science, Univ. of Joensuu, Box 111</s1>
<s2>80101 Joensuu</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Finlande</country>
<wicri:noRegion>80101 Joensuu</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Fr Nti, P" sort="Fr Nti, P" uniqKey="Fr Nti P" first="P." last="Fr Nti">P. Fr Nti</name>
<affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Dept. of Computer Science, Univ. of Joensuu, Box 111</s1>
<s2>80101 Joensuu</s2>
<s3>FIN</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
</inist:fA14>
<country>Finlande</country>
<wicri:noRegion>80101 Joensuu</wicri:noRegion>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
<imprint><date when="2000">2000</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Compression</term>
<term>Context</term>
<term>Digitizing</term>
<term>Document image</term>
<term>Electronic document</term>
<term>Electronic document management system</term>
<term>Filtering</term>
<term>Improvement</term>
<term>Optical character recognition</term>
<term>Statistical method</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance optique caractère</term>
<term>Compression</term>
<term>Filtrage</term>
<term>Méthode statistique</term>
<term>Contexte</term>
<term>Amélioration</term>
<term>Numérisation</term>
<term>Système gestion électronique document</term>
<term>Document électronique</term>
<term>Document image</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Méthode statistique</term>
<term>Numérisation</term>
<term>Document électronique</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Two statistical context-based filters are proposed for the enhancement of the binary document images for compression and recognition. The Simple Context Filter unconditionally changes the uncommon pixels in low information contexts, whereas the Gain-Loss Filter changes the pixels conditionally depending whether the gain in compression outweighs the loss of information. The evaluation methods and results with some traditional filtering methods are presented. The filtering methods alleviate the loss in compression performance caused by digitization noise while preserving the image quality measured as the OCR accuracy. The Gain-Loss Filter reaches approximately the compression limit estimated by the compression of the noiseless digital original.</div>
</front>
</TEI>
<affiliations><list><country><li>Finlande</li>
</country>
</list>
<tree><country name="Finlande"><noRegion><name sortKey="Ageenko, E" sort="Ageenko, E" uniqKey="Ageenko E" first="E." last="Ageenko">E. Ageenko</name>
</noRegion>
<name sortKey="Fr Nti, P" sort="Fr Nti, P" uniqKey="Fr Nti P" first="P." last="Fr Nti">P. Fr Nti</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 001E40 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001E40 | 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= Pascal:01-0027683 |texte= Context-based filtering for document image compression }}
This area was generated with Dilib version V0.6.32. |