KonIQ-10k : An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment

Lade...
Vorschaubild
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2020
Autor:innen
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
IEEE Transactions on Image Processing. IEEE. 2020, 29, pp. 4041-4056. ISSN 1057-7149. eISSN 1941-0042. Available under: doi: 10.1109/TIP.2020.2967829
Zusammenfassung

Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets. Extensive datasets require substantial resources both for generating publishable content and annotating it accurately. We present a systematic and scalable approach to creating KonIQ-10k, the largest IQA dataset to date, consisting of 10,073 quality scored images. It is the first in-the-wild database aiming for ecological validity, concerning the authenticity of distortions, the diversity of content, and quality-related indicators. Through the use of crowdsourcing, we obtained 1.2 million reliable quality ratings from 1,459 crowd workers, paving the way for more general IQA models. We propose a novel, deep learning model (KonCept512), to show an excellent generalization beyond the test set (0.921 SROCC), to the current state-of-the-art database LIVE-in-the-Wild (0.825 SROCC). The model derives its core performance from the InceptionResNet architecture, being trained at a higher resolution than previous models (512 × 384 ). Correlation analysis shows that KonCept512 performs similar to having 9 subjective scores for each test image.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690HOSU, Vlad, Hanhe LIN, Tamas SZIRANYI, Dietmar SAUPE, 2020. KonIQ-10k : An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment. In: IEEE Transactions on Image Processing. IEEE. 2020, 29, pp. 4041-4056. ISSN 1057-7149. eISSN 1941-0042. Available under: doi: 10.1109/TIP.2020.2967829
BibTex
@article{Hosu2020-01-24KonIQ-53065,
  year={2020},
  doi={10.1109/TIP.2020.2967829},
  title={KonIQ-10k : An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment},
  volume={29},
  issn={1057-7149},
  journal={IEEE Transactions on Image Processing},
  pages={4041--4056},
  author={Hosu, Vlad and Lin, Hanhe and Sziranyi, Tamas and Saupe, Dietmar}
}
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/123456789/53065">
    <dcterms:abstract xml:lang="eng">Deep learning methods for image quality assessment (IQA) are limited due to the small size of existing datasets. Extensive datasets require substantial resources both for generating publishable content and annotating it accurately. We present a systematic and scalable approach to creating KonIQ-10k, the largest IQA dataset to date, consisting of 10,073 quality scored images. It is the first in-the-wild database aiming for ecological validity, concerning the authenticity of distortions, the diversity of content, and quality-related indicators. Through the use of crowdsourcing, we obtained 1.2 million reliable quality ratings from 1,459 crowd workers, paving the way for more general IQA models. We propose a novel, deep learning model (KonCept512), to show an excellent generalization beyond the test set (0.921 SROCC), to the current state-of-the-art database LIVE-in-the-Wild (0.825 SROCC). The model derives its core performance from the InceptionResNet architecture, being trained at a higher resolution than previous models (512 × 384 ). Correlation analysis shows that KonCept512 performs similar to having 9 subjective scores for each test image.</dcterms:abstract>
    <dc:creator>Hosu, Vlad</dc:creator>
    <dcterms:issued>2020-01-24</dcterms:issued>
    <dcterms:title>KonIQ-10k : An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment</dcterms:title>
    <dc:creator>Lin, Hanhe</dc:creator>
    <dc:contributor>Sziranyi, Tamas</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-03-03T10:36:55Z</dc:date>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-03-03T10:36:55Z</dcterms:available>
    <dc:contributor>Hosu, Vlad</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Lin, Hanhe</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/53065"/>
    <dc:creator>Sziranyi, Tamas</dc:creator>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:language>eng</dc:language>
    <dc:creator>Saupe, Dietmar</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Saupe, Dietmar</dc:contributor>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Ja
Diese Publikation teilen