Publikation: Initial Image Selection and its Influence on Super-Resolution Reconstruction
Lade...
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2007
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
IEEE, , ed.. 2007 IEEE Workshop on Signal Processing Systems : SiPS 2007 ; October 17-19, 2007, Shanghai, China ; proceedings; Vol. 1. Piscataway, NJ: IEEE, 2007, pp. 86-89. ISBN 978-1-4244-1222-8. Available under: doi: 10.1109/SIPS.2007.4387523
Zusammenfassung
Super-resolution (SR) reconstruction is a technique to yield a higher resolution (HR) image from aliasing low resolution (LR) ones. An LR image is upsampled as the initialization, and then iteratively corrected in comparison with the other LR images. As the solution satisfying the SR constraints is non-unique, it is impossible to recover the original HR details completely by SR techniques. The solution reconstructed is sensitive to the starting point, especially when LR observations are insufficient, and may converge to a local optimum point. SR images reconstructed with different initializations may diverge in different ways from the true HR image. The influence of the initial HR estimate has not been sufficiently addressed so far by existing SR methods. We will explore this initial image selection issue to improve the performance of SR reconstruction.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
2007 IEEE Workshop on Signal Processing Systems, 17. Okt. 2007 - 19. Okt. 2007, Shanghai
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690
SHEN, Minmin, Ci WANG, Ping XUE, Weisi LIN, 2007. Initial Image Selection and its Influence on Super-Resolution Reconstruction. 2007 IEEE Workshop on Signal Processing Systems. Shanghai, 17. Okt. 2007 - 19. Okt. 2007. In: IEEE, , ed.. 2007 IEEE Workshop on Signal Processing Systems : SiPS 2007 ; October 17-19, 2007, Shanghai, China ; proceedings; Vol. 1. Piscataway, NJ: IEEE, 2007, pp. 86-89. ISBN 978-1-4244-1222-8. Available under: doi: 10.1109/SIPS.2007.4387523BibTex
@inproceedings{Shen2007Initi-30834,
year={2007},
doi={10.1109/SIPS.2007.4387523},
title={Initial Image Selection and its Influence on Super-Resolution Reconstruction},
isbn={978-1-4244-1222-8},
publisher={IEEE},
address={Piscataway, NJ},
booktitle={2007 IEEE Workshop on Signal Processing Systems : SiPS 2007 ; October 17-19, 2007, Shanghai, China ; proceedings; Vol. 1},
pages={86--89},
editor={IEEE},
author={Shen, Minmin and Wang, Ci and Xue, Ping and Lin, Weisi}
}RDF
<rdf:RDF
xmlns:dcterms="http://purl.org/dc/terms/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:bibo="http://purl.org/ontology/bibo/"
xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
xmlns:foaf="http://xmlns.com/foaf/0.1/"
xmlns:void="http://rdfs.org/ns/void#"
xmlns:xsd="http://www.w3.org/2001/XMLSchema#" >
<rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/30834">
<dc:creator>Shen, Minmin</dc:creator>
<dc:language>eng</dc:language>
<foaf:homepage rdf:resource="http://localhost:8080/"/>
<dcterms:issued>2007</dcterms:issued>
<bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/30834"/>
<dcterms:abstract xml:lang="eng">Super-resolution (SR) reconstruction is a technique to yield a higher resolution (HR) image from aliasing low resolution (LR) ones. An LR image is upsampled as the initialization, and then iteratively corrected in comparison with the other LR images. As the solution satisfying the SR constraints is non-unique, it is impossible to recover the original HR details completely by SR techniques. The solution reconstructed is sensitive to the starting point, especially when LR observations are insufficient, and may converge to a local optimum point. SR images reconstructed with different initializations may diverge in different ways from the true HR image. The influence of the initial HR estimate has not been sufficiently addressed so far by existing SR methods. We will explore this initial image selection issue to improve the performance of SR reconstruction.</dcterms:abstract>
<dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2015-04-29T09:11:26Z</dcterms:available>
<dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2015-04-29T09:11:26Z</dc:date>
<dc:creator>Wang, Ci</dc:creator>
<dc:contributor>Wang, Ci</dc:contributor>
<dc:contributor>Shen, Minmin</dc:contributor>
<void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
<dc:creator>Lin, Weisi</dc:creator>
<dc:creator>Xue, Ping</dc:creator>
<dc:contributor>Xue, Ping</dc:contributor>
<dc:contributor>Lin, Weisi</dc:contributor>
<dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
<dcterms:title>Initial Image Selection and its Influence on Super-Resolution Reconstruction</dcterms:title>
</rdf:Description>
</rdf:RDF>Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Nein
