Efficient Example-Based Super-Resolution of Single Text Images Based on Selective Patch Processing
Identifieur interne : 000042 ( Hal/Curation ); précédent : 000041; suivant : 000043Efficient Example-Based Super-Resolution of Single Text Images Based on Selective Patch Processing
Auteurs : Nibal Nayef [France] ; Joseph Chazalon [France] ; Petra Gomez-Kr Mer [France] ; Jean-Marc Ogier [France]Source :
Abstract
Example-based super-resolution (SR) methods learn the correspondences between low resolution (LR) and high-resolution (HR) image patches, where the patches are extracted from a training database. To reconstruct a single LR image into a HR one, each LR image patch is processed by the previously trained model to recover its corresponding HR patch. For this reason, they are computationally inefficient. We propose the use of a selective patch processing technique to carry out the super-resolution step more efficiently, while maintaining the output quality. In this technique, only patches of high variance are processed by the costly reconstruction steps, while the rest of the patches are processed by fast bicubic interpolation. We have applied the proposed improvement on representative example-based SR methods to super-resolve text images. The results show a significant speed up for text SR without a drop in the ocr accuracy. In order to carry out an extensive and solid performance evaluation, we also present a public database of text images for training and testing example-based SR methods.
Url:
DOI: 10.1109/DAS.2014.25
Links toward previous steps (curation, corpus...)
- to stream Hal, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000042
Links to Exploration step
Hal:hal-01315686Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Efficient Example-Based Super-Resolution of Single Text Images Based on Selective Patch Processing</title>
<author><name sortKey="Nayef, Nibal" sort="Nayef, Nibal" uniqKey="Nayef N" first="Nibal" last="Nayef">Nibal Nayef</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName>
<orgName type="acronym">L3I</orgName>
<desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lr.fr/l3i</ref>
</desc>
<listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation>
</listRelation>
<tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">La Rochelle</settlement>
<region type="region" nuts="2">Poitou-Charentes</region>
</placeName>
<orgName type="university">Université de La Rochelle</orgName>
</affiliation>
</author>
<author><name sortKey="Chazalon, Joseph" sort="Chazalon, Joseph" uniqKey="Chazalon J" first="Joseph" last="Chazalon">Joseph Chazalon</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName>
<orgName type="acronym">L3I</orgName>
<desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lr.fr/l3i</ref>
</desc>
<listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation>
</listRelation>
<tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">La Rochelle</settlement>
<region type="region" nuts="2">Poitou-Charentes</region>
</placeName>
<orgName type="university">Université de La Rochelle</orgName>
</affiliation>
</author>
<author><name sortKey="Gomez Kr Mer, Petra" sort="Gomez Kr Mer, Petra" uniqKey="Gomez Kr Mer P" first="Petra" last="Gomez-Kr Mer">Petra Gomez-Kr Mer</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName>
<orgName type="acronym">L3I</orgName>
<desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lr.fr/l3i</ref>
</desc>
<listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation>
</listRelation>
<tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">La Rochelle</settlement>
<region type="region" nuts="2">Poitou-Charentes</region>
</placeName>
<orgName type="university">Université de La Rochelle</orgName>
</affiliation>
</author>
<author><name sortKey="Ogier, Jean Marc" sort="Ogier, Jean Marc" uniqKey="Ogier J" first="Jean-Marc" last="Ogier">Jean-Marc Ogier</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName>
<orgName type="acronym">L3I</orgName>
<desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lr.fr/l3i</ref>
</desc>
<listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation>
</listRelation>
<tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">La Rochelle</settlement>
<region type="region" nuts="2">Poitou-Charentes</region>
</placeName>
<orgName type="university">Université de La Rochelle</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">HAL</idno>
<idno type="RBID">Hal:hal-01315686</idno>
<idno type="halId">hal-01315686</idno>
<idno type="halUri">https://hal.archives-ouvertes.fr/hal-01315686</idno>
<idno type="url">https://hal.archives-ouvertes.fr/hal-01315686</idno>
<idno type="doi">10.1109/DAS.2014.25</idno>
<date when="2014-04-07">2014-04-07</date>
<idno type="wicri:Area/Hal/Corpus">000042</idno>
<idno type="wicri:Area/Hal/Curation">000042</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Efficient Example-Based Super-Resolution of Single Text Images Based on Selective Patch Processing</title>
<author><name sortKey="Nayef, Nibal" sort="Nayef, Nibal" uniqKey="Nayef N" first="Nibal" last="Nayef">Nibal Nayef</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName>
<orgName type="acronym">L3I</orgName>
<desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lr.fr/l3i</ref>
</desc>
<listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation>
</listRelation>
<tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">La Rochelle</settlement>
<region type="region" nuts="2">Poitou-Charentes</region>
</placeName>
<orgName type="university">Université de La Rochelle</orgName>
</affiliation>
</author>
<author><name sortKey="Chazalon, Joseph" sort="Chazalon, Joseph" uniqKey="Chazalon J" first="Joseph" last="Chazalon">Joseph Chazalon</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName>
<orgName type="acronym">L3I</orgName>
<desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lr.fr/l3i</ref>
</desc>
<listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation>
</listRelation>
<tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">La Rochelle</settlement>
<region type="region" nuts="2">Poitou-Charentes</region>
</placeName>
<orgName type="university">Université de La Rochelle</orgName>
</affiliation>
</author>
<author><name sortKey="Gomez Kr Mer, Petra" sort="Gomez Kr Mer, Petra" uniqKey="Gomez Kr Mer P" first="Petra" last="Gomez-Kr Mer">Petra Gomez-Kr Mer</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName>
<orgName type="acronym">L3I</orgName>
<desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lr.fr/l3i</ref>
</desc>
<listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation>
</listRelation>
<tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">La Rochelle</settlement>
<region type="region" nuts="2">Poitou-Charentes</region>
</placeName>
<orgName type="university">Université de La Rochelle</orgName>
</affiliation>
</author>
<author><name sortKey="Ogier, Jean Marc" sort="Ogier, Jean Marc" uniqKey="Ogier J" first="Jean-Marc" last="Ogier">Jean-Marc Ogier</name>
<affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-40831" status="VALID"><orgName>Laboratoire Informatique, Image et Interaction</orgName>
<orgName type="acronym">L3I</orgName>
<desc><address><addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
<country key="FR"></country>
</address>
<ref type="url">http://www.univ-lr.fr/l3i</ref>
</desc>
<listRelation><relation name="EA2118" active="#struct-300311" type="direct"></relation>
</listRelation>
<tutelles><tutelle name="EA2118" active="#struct-300311" type="direct"><org type="institution" xml:id="struct-300311" status="VALID"><orgName>Université de La Rochelle</orgName>
<desc><address><country key="FR"></country>
</address>
</desc>
</org>
</tutelle>
</tutelles>
</hal:affiliation>
<country>France</country>
<placeName><settlement type="city">La Rochelle</settlement>
<region type="region" nuts="2">Poitou-Charentes</region>
</placeName>
<orgName type="university">Université de La Rochelle</orgName>
</affiliation>
</author>
</analytic>
<idno type="DOI">10.1109/DAS.2014.25</idno>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass></textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Example-based super-resolution (SR) methods learn the correspondences between low resolution (LR) and high-resolution (HR) image patches, where the patches are extracted from a training database. To reconstruct a single LR image into a HR one, each LR image patch is processed by the previously trained model to recover its corresponding HR patch. For this reason, they are computationally inefficient. We propose the use of a selective patch processing technique to carry out the super-resolution step more efficiently, while maintaining the output quality. In this technique, only patches of high variance are processed by the costly reconstruction steps, while the rest of the patches are processed by fast bicubic interpolation. We have applied the proposed improvement on representative example-based SR methods to super-resolve text images. The results show a significant speed up for text SR without a drop in the ocr accuracy. In order to carry out an extensive and solid performance evaluation, we also present a public database of text images for training and testing example-based SR methods.</div>
</front>
</TEI>
<hal api="V3"><titleStmt><title xml:lang="en">Efficient Example-Based Super-Resolution of Single Text Images Based on Selective Patch Processing</title>
<author role="aut"><persName><forename type="first">Nibal</forename>
<surname>Nayef</surname>
</persName>
<email>nibal.nayef@univ-lr.fr</email>
<idno type="idhal">nibal-nayef</idno>
<idno type="halauthor">1253082</idno>
<affiliation ref="#struct-40831"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Joseph</forename>
<surname>Chazalon</surname>
</persName>
<email>joseph.chazalon@univ-lr.fr</email>
<idno type="halauthor">1264955</idno>
<affiliation ref="#struct-40831"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Petra</forename>
<surname>Gomez-Krämer</surname>
</persName>
<email>petra.gomez@univ-lr.fr</email>
<idno type="halauthor">742421</idno>
<affiliation ref="#struct-40831"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Jean-Marc</forename>
<surname>Ogier</surname>
</persName>
<email>jean-marc.ogier@univ-lr.fr</email>
<idno type="halauthor">363882</idno>
<affiliation ref="#struct-40831"></affiliation>
</author>
<editor role="depositor"><persName><forename>Nibal</forename>
<surname>Nayef</surname>
</persName>
<email>n.nayef@gmail.com</email>
</editor>
</titleStmt>
<editionStmt><edition n="v1" type="current"><date type="whenSubmitted">2016-05-13 15:52:39</date>
<date type="whenModified">2016-05-24 10:56:35</date>
<date type="whenReleased">2016-05-13 15:52:39</date>
<date type="whenProduced">2014-04-07</date>
</edition>
<respStmt><resp>contributor</resp>
<name key="427482"><persName><forename>Nibal</forename>
<surname>Nayef</surname>
</persName>
<email>n.nayef@gmail.com</email>
</name>
</respStmt>
</editionStmt>
<publicationStmt><distributor>CCSD</distributor>
<idno type="halId">hal-01315686</idno>
<idno type="halUri">https://hal.archives-ouvertes.fr/hal-01315686</idno>
<idno type="halBibtex">nayef:hal-01315686</idno>
<idno type="halRefHtml">11th IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS), Apr 2014, Tours, France. pp.227 - 231, <10.1109/DAS.2014.25></idno>
<idno type="halRef">11th IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS), Apr 2014, Tours, France. pp.227 - 231, <10.1109/DAS.2014.25></idno>
</publicationStmt>
<seriesStmt><idno type="stamp" n="UNIV-ROCHELLE">Université de la Rochelle</idno>
<idno type="stamp" n="L3I">Laboratoire Informatique, Image et Interaction</idno>
</seriesStmt>
<notesStmt><note type="audience" n="2">International</note>
<note type="invited" n="0">No</note>
<note type="popular" n="0">No</note>
<note type="peer" n="1">Yes</note>
<note type="proceedings" n="0">No</note>
</notesStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Efficient Example-Based Super-Resolution of Single Text Images Based on Selective Patch Processing</title>
<author role="aut"><persName><forename type="first">Nibal</forename>
<surname>Nayef</surname>
</persName>
<email>nibal.nayef@univ-lr.fr</email>
<idno type="idHal">nibal-nayef</idno>
<idno type="halAuthorId">1253082</idno>
<affiliation ref="#struct-40831"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Joseph</forename>
<surname>Chazalon</surname>
</persName>
<email>joseph.chazalon@univ-lr.fr</email>
<idno type="halAuthorId">1264955</idno>
<affiliation ref="#struct-40831"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Petra</forename>
<surname>Gomez-Krämer</surname>
</persName>
<email>petra.gomez@univ-lr.fr</email>
<idno type="halAuthorId">742421</idno>
<affiliation ref="#struct-40831"></affiliation>
</author>
<author role="aut"><persName><forename type="first">Jean-Marc</forename>
<surname>Ogier</surname>
</persName>
<email>jean-marc.ogier@univ-lr.fr</email>
<idno type="halAuthorId">363882</idno>
<affiliation ref="#struct-40831"></affiliation>
</author>
</analytic>
<monogr><meeting><title>11th IAPR INTERNATIONAL WORKSHOP ON DOCUMENT ANALYSIS SYSTEMS (DAS)</title>
<date type="start">2014-04-07</date>
<settlement>Tours</settlement>
<country key="FR">France</country>
</meeting>
<imprint><biblScope unit="pp">227 - 231</biblScope>
</imprint>
</monogr>
<idno type="doi">10.1109/DAS.2014.25</idno>
</biblStruct>
</sourceDesc>
<profileDesc><langUsage><language ident="en">English</language>
</langUsage>
<textClass><classCode scheme="halDomain" n="info.info-ts">Computer Science [cs]/Signal and Image Processing</classCode>
<classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
<classCode scheme="halTypology" n="COMM">Conference papers</classCode>
</textClass>
<abstract xml:lang="en">Example-based super-resolution (SR) methods learn the correspondences between low resolution (LR) and high-resolution (HR) image patches, where the patches are extracted from a training database. To reconstruct a single LR image into a HR one, each LR image patch is processed by the previously trained model to recover its corresponding HR patch. For this reason, they are computationally inefficient. We propose the use of a selective patch processing technique to carry out the super-resolution step more efficiently, while maintaining the output quality. In this technique, only patches of high variance are processed by the costly reconstruction steps, while the rest of the patches are processed by fast bicubic interpolation. We have applied the proposed improvement on representative example-based SR methods to super-resolve text images. The results show a significant speed up for text SR without a drop in the ocr accuracy. In order to carry out an extensive and solid performance evaluation, we also present a public database of text images for training and testing example-based SR methods.</abstract>
</profileDesc>
</hal>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Hal/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000042 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Hal/Curation/biblio.hfd -nk 000042 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Hal |étape= Curation |type= RBID |clé= Hal:hal-01315686 |texte= Efficient Example-Based Super-Resolution of Single Text Images Based on Selective Patch Processing }}
This area was generated with Dilib version V0.6.32. |