Efficient super-resolution via image warping
Identifieur interne : 000731 ( PascalFrancis/Checkpoint ); précédent : 000730; suivant : 000732Efficient super-resolution via image warping
Auteurs : M. C. Chiang [États-Unis] ; T. E. BoultSource :
- Image and Vision Computing [ 0262-8856 ] ; 2000.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
This paper introduces a new algorithm for enhancing image resolution from an image sequence. The approach we propose herein uses the integrating resampler for warping. The method is a direct computation, which is fundamentally different from the iterative back-projection approaches proposed in previous work. This paper shows that image-warping techniques may have a strong impact on the quality of image resolution enhancement. By coupling the degradation model of the imaging system directly into the integrating resampler, we can better approximate the warping characteristics of real sensors, which also significantly improve the quality of super-resolution images. Examples of super-resolutions are given for gray-scale images. Evaluations are made visually by comparing the resulting images and those using bi-linear resampling and back-projection and quantitatively using OCR as a fundamental measure. The paper shows that even when the images are qualitatively similar, quantitative differences appear in machine processing.
Affiliations:
Links toward previous steps (curation, corpus...)
Links to Exploration step
Pascal:00-0310193Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Efficient super-resolution via image warping</title><author><name sortKey="Chiang, M C" sort="Chiang, M C" uniqKey="Chiang M" first="M. C." last="Chiang">M. C. Chiang</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Columbia Univ</s1><s2>New York NY</s2><s3>USA</s3><sZ>1 aut.</sZ></inist:fA14><country>États-Unis</country><wicri:noRegion>Columbia Univ</wicri:noRegion></affiliation></author><author><name sortKey="Boult, T E" sort="Boult, T E" uniqKey="Boult T" first="T. E." last="Boult">T. E. Boult</name></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">00-0310193</idno><date when="2000">2000</date><idno type="stanalyst">PASCAL 00-0310193 EI</idno><idno type="RBID">Pascal:00-0310193</idno><idno type="wicri:Area/PascalFrancis/Corpus">000776</idno><idno type="wicri:Area/PascalFrancis/Curation">000018</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000731</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Efficient super-resolution via image warping</title><author><name sortKey="Chiang, M C" sort="Chiang, M C" uniqKey="Chiang M" first="M. C." last="Chiang">M. C. Chiang</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Columbia Univ</s1><s2>New York NY</s2><s3>USA</s3><sZ>1 aut.</sZ></inist:fA14><country>États-Unis</country><wicri:noRegion>Columbia Univ</wicri:noRegion></affiliation></author><author><name sortKey="Boult, T E" sort="Boult, T E" uniqKey="Boult T" first="T. E." last="Boult">T. E. Boult</name></author></analytic><series><title level="j" type="main">Image and Vision Computing</title><title level="j" type="abbreviated">Image Vision Comput</title><idno type="ISSN">0262-8856</idno><imprint><date when="2000">2000</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Image and Vision Computing</title><title level="j" type="abbreviated">Image Vision Comput</title><idno type="ISSN">0262-8856</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Approximation theory</term><term>Computational methods</term><term>Image analysis</term><term>Image quality</term><term>Image reconstruction</term><term>Image warping</term><term>Imaging systems</term><term>Imaging techniques</term><term>Iterative methods</term><term>Mathematical models</term><term>Optical character recognition</term><term>Theory</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Théorie</term><term>Analyse image</term><term>Qualité image</term><term>Reconstruction image</term><term>Méthode calcul</term><term>Méthode itérative</term><term>Modèle mathématique</term><term>Théorie approximation</term><term>Reconnaissance optique caractère</term><term>Système imagerie</term><term>Imagerie</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This paper introduces a new algorithm for enhancing image resolution from an image sequence. The approach we propose herein uses the integrating resampler for warping. The method is a direct computation, which is fundamentally different from the iterative back-projection approaches proposed in previous work. This paper shows that image-warping techniques may have a strong impact on the quality of image resolution enhancement. By coupling the degradation model of the imaging system directly into the integrating resampler, we can better approximate the warping characteristics of real sensors, which also significantly improve the quality of super-resolution images. Examples of super-resolutions are given for gray-scale images. Evaluations are made visually by comparing the resulting images and those using bi-linear resampling and back-projection and quantitatively using OCR as a fundamental measure. The paper shows that even when the images are qualitatively similar, quantitative differences appear in machine processing.</div></front></TEI><inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0262-8856</s0></fA01><fA03 i2="1"><s0>Image Vision Comput</s0></fA03><fA05><s2>18</s2></fA05><fA06><s2>10</s2></fA06><fA08 i1="01" i2="1" l="ENG"><s1>Efficient super-resolution via image warping</s1></fA08><fA11 i1="01" i2="1"><s1>CHIANG (M. C.)</s1></fA11><fA11 i1="02" i2="1"><s1>BOULT (T. E.)</s1></fA11><fA14 i1="01"><s1>Columbia Univ</s1><s2>New York NY</s2><s3>USA</s3><sZ>1 aut.</sZ></fA14><fA20><s1>761-771</s1></fA20><fA21><s1>2000</s1></fA21><fA23 i1="01"><s0>ENG</s0></fA23><fA43 i1="01"><s1>INIST</s1><s2>22084</s2></fA43><fA44><s0>A100</s0></fA44><fA45><s0>17 Refs.</s0></fA45><fA47 i1="01" i2="1"><s0>00-0310193</s0></fA47><fA60><s1>P</s1></fA60><fA61><s0>A</s0></fA61><fA64 i1="01" i2="1"><s0>Image and Vision Computing</s0></fA64><fA66 i1="01"><s0>GBR</s0></fA66><fC01 i1="01" l="ENG"><s0>This paper introduces a new algorithm for enhancing image resolution from an image sequence. The approach we propose herein uses the integrating resampler for warping. The method is a direct computation, which is fundamentally different from the iterative back-projection approaches proposed in previous work. This paper shows that image-warping techniques may have a strong impact on the quality of image resolution enhancement. By coupling the degradation model of the imaging system directly into the integrating resampler, we can better approximate the warping characteristics of real sensors, which also significantly improve the quality of super-resolution images. Examples of super-resolutions are given for gray-scale images. Evaluations are made visually by comparing the resulting images and those using bi-linear resampling and back-projection and quantitatively using OCR as a fundamental measure. The paper shows that even when the images are qualitatively similar, quantitative differences appear in machine processing.</s0></fC01><fC02 i1="01" i2="3"><s0>001B40B</s0></fC02><fC02 i1="02" i2="X"><s0>001A02</s0></fC02><fC02 i1="03" i2="X"><s0>001A02I01</s0></fC02><fC03 i1="01" i2="1" l="ENG"><s0>Image warping</s0><s4>INC</s4></fC03><fC03 i1="02" i2="1" l="FRE"><s0>Théorie</s0></fC03><fC03 i1="02" i2="1" l="ENG"><s0>Theory</s0></fC03><fC03 i1="03" i2="1" l="FRE"><s0>Analyse image</s0></fC03><fC03 i1="03" i2="1" l="ENG"><s0>Image analysis</s0></fC03><fC03 i1="04" i2="1" l="FRE"><s0>Qualité image</s0></fC03><fC03 i1="04" i2="1" l="ENG"><s0>Image quality</s0></fC03><fC03 i1="05" i2="1" l="FRE"><s0>Reconstruction image</s0></fC03><fC03 i1="05" i2="1" l="ENG"><s0>Image reconstruction</s0></fC03><fC03 i1="06" i2="1" l="FRE"><s0>Méthode calcul</s0></fC03><fC03 i1="06" i2="1" l="ENG"><s0>Computational methods</s0></fC03><fC03 i1="07" i2="1" l="FRE"><s0>Méthode itérative</s0></fC03><fC03 i1="07" i2="1" l="ENG"><s0>Iterative methods</s0></fC03><fC03 i1="08" i2="1" l="FRE"><s0>Modèle mathématique</s0></fC03><fC03 i1="08" i2="1" l="ENG"><s0>Mathematical models</s0></fC03><fC03 i1="09" i2="1" l="FRE"><s0>Théorie approximation</s0></fC03><fC03 i1="09" i2="1" l="ENG"><s0>Approximation theory</s0></fC03><fC03 i1="10" i2="1" l="FRE"><s0>Reconnaissance optique caractère</s0></fC03><fC03 i1="10" i2="1" l="ENG"><s0>Optical character recognition</s0></fC03><fC03 i1="11" i2="1" l="FRE"><s0>Système imagerie</s0></fC03><fC03 i1="11" i2="1" l="ENG"><s0>Imaging systems</s0></fC03><fC03 i1="12" i2="1" l="FRE"><s0>Imagerie</s0><s3>P</s3></fC03><fC03 i1="12" i2="1" l="ENG"><s0>Imaging techniques</s0><s3>P</s3></fC03><fN21><s1>213</s1></fN21></pA></standard></inist><affiliations><list><country><li>États-Unis</li></country></list><tree><noCountry><name sortKey="Boult, T E" sort="Boult, T E" uniqKey="Boult T" first="T. E." last="Boult">T. E. Boult</name></noCountry><country name="États-Unis"><noRegion><name sortKey="Chiang, M C" sort="Chiang, M C" uniqKey="Chiang M" first="M. C." last="Chiang">M. C. Chiang</name></noRegion></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/PascalFrancis/Checkpoint
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000731 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Checkpoint/biblio.hfd -nk 000731 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= PascalFrancis
|étape= Checkpoint
|type= RBID
|clé= Pascal:00-0310193
|texte= Efficient super-resolution via image warping
}}
| This area was generated with Dilib version V0.6.32. |  |