Publikation:

Empirical evaluation of dissimilarity measures for 3D object retrieval with application to multi-feature retrieval

Lade...
Vorschaubild

Dateien

Zu diesem Dokument gibt es keine Dateien.

Datum

2015

Herausgeber:innen

Kontakt

ISSN der Zeitschrift

Electronic ISSN

ISBN

Bibliografische Daten

Verlag

Schriftenreihe

Auflagebezeichnung

URI (zitierfähiger Link)
ArXiv-ID

Internationale Patentnummer

Angaben zur Forschungsförderung

Projekt

Open Access-Veröffentlichung
Core Facility der Universität Konstanz

Gesperrt bis

Titel in einer weiteren Sprache

Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published

Erschienen in

13th International Workshop on Content-Based Multimedia Indexing (CBMI) 2015. IEEE, 2015, pp. 1-6. ISBN 978-1-4673-6870-4. Available under: doi: 10.1109/CBMI.2015.7153629

Zusammenfassung

A common approach for implementing content-based multimedia retrieval tasks resorts to extracting high-dimensional feature vectors from the multimedia objects. In combination with an appropriate dissimilarity function, such as the well-known Lp functions or statistical measures like χ2, one can rank objects by dissimilarity with respect to a query. For many multimedia retrieval problems, a large number of feature extraction methods have been proposed and experimentally evaluated for their effectiveness. Much less work has been done to systematically study the impact of the choice of dissimilarity function on the retrieval effectiveness. Inspired by previous work which compared dissimilarity functions for image retrieval, we provide an extensive comparison of dissimilarity measures for 3D object retrieval. Our study is based on an encompassing set of feature extractors, dissimilarity measures and benchmark data sets. We identify the best performing dissimilarity measures and in turn identify dependencies between well-performing dissimilarity measures and types of 3D features. Based on these findings, we show that the effectiveness of 3D retrieval can be improved by a feature-dependent measure choice. In addition, we apply different normalization schemes to the dissimilarity distributions in order to show improved retrieval effectiveness for late fusion of multi-feature combination. Finally, we present preliminary findings on the correlation of rankings for dissimilarity measures, which could be exploited for further improvement of retrieval effectiveness for single features as well as combinations.

Zusammenfassung in einer weiteren Sprache

Fachgebiet (DDC)
004 Informatik

Schlagwörter

Konferenz

13th International Workshop on Content-Based Multimedia Indexing (CBMI) 2015, 10. Juni 2015 - 12. Juni 2015, Prague, Czech Republic
Rezension
undefined / . - undefined, undefined

Forschungsvorhaben

Organisationseinheiten

Zeitschriftenheft

Zugehörige Datensätze in KOPS

Zitieren

ISO 690GREGOR, Robert, Andreas LAMPRECHT, Ivan SIPIRAN, Tobias SCHRECK, Benjamin BUSTOS, 2015. Empirical evaluation of dissimilarity measures for 3D object retrieval with application to multi-feature retrieval. 13th International Workshop on Content-Based Multimedia Indexing (CBMI) 2015. Prague, Czech Republic, 10. Juni 2015 - 12. Juni 2015. In: 13th International Workshop on Content-Based Multimedia Indexing (CBMI) 2015. IEEE, 2015, pp. 1-6. ISBN 978-1-4673-6870-4. Available under: doi: 10.1109/CBMI.2015.7153629
BibTex
@inproceedings{Gregor2015Empir-33034,
  year={2015},
  doi={10.1109/CBMI.2015.7153629},
  title={Empirical evaluation of dissimilarity measures for 3D object retrieval with application to multi-feature retrieval},
  isbn={978-1-4673-6870-4},
  publisher={IEEE},
  booktitle={13th International Workshop on Content-Based Multimedia Indexing (CBMI) 2015},
  pages={1--6},
  author={Gregor, Robert and Lamprecht, Andreas and Sipiran, Ivan and Schreck, Tobias and Bustos, Benjamin}
}
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/123456789/33034">
    <dc:language>eng</dc:language>
    <dcterms:abstract xml:lang="eng">A common approach for implementing content-based multimedia retrieval tasks resorts to extracting high-dimensional feature vectors from the multimedia objects. In combination with an appropriate dissimilarity function, such as the well-known L&lt;sub&gt;p&lt;/sub&gt; functions or statistical measures like χ&lt;sup&gt;2&lt;/sup&gt;, one can rank objects by dissimilarity with respect to a query. For many multimedia retrieval problems, a large number of feature extraction methods have been proposed and experimentally evaluated for their effectiveness. Much less work has been done to systematically study the impact of the choice of dissimilarity function on the retrieval effectiveness. Inspired by previous work which compared dissimilarity functions for image retrieval, we provide an extensive comparison of dissimilarity measures for 3D object retrieval. Our study is based on an encompassing set of feature extractors, dissimilarity measures and benchmark data sets. We identify the best performing dissimilarity measures and in turn identify dependencies between well-performing dissimilarity measures and types of 3D features. Based on these findings, we show that the effectiveness of 3D retrieval can be improved by a feature-dependent measure choice. In addition, we apply different normalization schemes to the dissimilarity distributions in order to show improved retrieval effectiveness for late fusion of multi-feature combination. Finally, we present preliminary findings on the correlation of rankings for dissimilarity measures, which could be exploited for further improvement of retrieval effectiveness for single features as well as combinations.</dcterms:abstract>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Lamprecht, Andreas</dc:creator>
    <dc:creator>Schreck, Tobias</dc:creator>
    <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">2016-02-18T10:54:26Z</dc:date>
    <dcterms:title>Empirical evaluation of dissimilarity measures for 3D object retrieval with application to multi-feature retrieval</dcterms:title>
    <dc:contributor>Bustos, Benjamin</dc:contributor>
    <dc:contributor>Schreck, Tobias</dc:contributor>
    <dc:contributor>Gregor, Robert</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2016-02-18T10:54:26Z</dcterms:available>
    <dc:contributor>Lamprecht, Andreas</dc:contributor>
    <dc:creator>Bustos, Benjamin</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Sipiran, Ivan</dc:creator>
    <dcterms:issued>2015</dcterms:issued>
    <dc:creator>Gregor, Robert</dc:creator>
    <dc:contributor>Sipiran, Ivan</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/33034"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
  </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
Diese Publikation teilen