Semiautomatic benchmarking of feature vectors for multimedia retrieval

Schreck, Tobias; Schneidewind, Jörn; Keim, Daniel A.; Ward, Matthew O.; Tatu, Andrada

Semiautomatic benchmarking of feature vectors for multimedia retrieval

Dateien

DELOS07.pdfGröße: 1.08 MBDownloads: 85

Datum

2007

Autor:innen

Schreck, Tobias

Schneidewind, Jörn

Keim, Daniel A.

Ward, Matthew O.

Tatu, Andrada

Publikationstyp

Beitrag zu einem Konferenzband

unikn.publication.listelement.citation.prefix.version.undefined

Second Delos Conference On Digital Libraries 5 - 7 December 2007, Tirrenia, Pisa. 2007

Zusammenfassung

Modern Digital Library applications store and process massive amounts of information. Usually, this data is not limited to raw textual or numeric data - typical applications also deal with multimedia data such as images, audio, video, or 3D geometric models. For providing effective retrieval functionality, appropriate meta data descriptors that allow calculation of similarity scores between data instances are requires. Feature vectors are a generic way for describing multimedia data by vectors formed from numerically captured object features. They are used in similarity search, but also, can be used for clustering and wider multimedia analysis applications. Extracting effective feature vectors for a given data type is a challenging task. Determining good feature vector extractors usually involves experimentation and application of supervised information. However, such experimentation usually is expensive, and supervised information often is data dependent. We address the feature selection problem by a novel approach based on analysis of certain feature space images. We develop two image-based analysis techniques for the automatic discrimination power analysis of feature spaces. We evaluate the techniques on a comprehensive feature selection benchmark, demonstrating the effectiveness of our analysis and its potential toward automatically addressing the feature selection problem.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

Visual Analytics, Feature Vectors, Automatic Feature Selection, Self-Organizing Maps

Konferenz

Second Delos, 5. Dez. 2007 - 7. Dez. 2007, Tirrenia, Pisa

Zitieren

ISO 690

SCHRECK, Tobias, Jörn SCHNEIDEWIND, Daniel A. KEIM, Matthew O. WARD, Andrada TATU, 2007. Semiautomatic benchmarking of feature vectors for multimedia retrieval. Second Delos. Tirrenia, Pisa, 5. Dez. 2007 - 7. Dez. 2007. In: Second Delos Conference On Digital Libraries 5 - 7 December 2007, Tirrenia, Pisa. 2007

BibTex

@inproceedings{Schreck2007Semia-5568,
  year={2007},
  title={Semiautomatic benchmarking of feature vectors for multimedia retrieval},
  booktitle={Second Delos Conference On Digital Libraries 5 - 7 December 2007, Tirrenia, Pisa},
  author={Schreck, Tobias and Schneidewind, Jörn and Keim, Daniel A. and Ward, Matthew O. and Tatu, Andrada}
}

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/123456789/5568">
    <dcterms:issued>2007</dcterms:issued>
    <dc:creator>Tatu, Andrada</dc:creator>
    <dcterms:title>Semiautomatic benchmarking of feature vectors for multimedia retrieval</dcterms:title>
    <dc:contributor>Schneidewind, Jörn</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:language>eng</dc:language>
    <dc:contributor>Schreck, Tobias</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-03-24T15:56:29Z</dc:date>
    <dc:rights>Attribution-NonCommercial-NoDerivs 2.0 Generic</dc:rights>
    <dc:creator>Schneidewind, Jörn</dc:creator>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dc:format>application/pdf</dc:format>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/5568"/>
    <dc:creator>Schreck, Tobias</dc:creator>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:bibliographicCitation>First publ. in: Second Delos Conference On Digital Libraries 5-7 December 2007, Tirrenia, Pisa</dcterms:bibliographicCitation>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/5568/1/DELOS07.pdf"/>
    <dc:contributor>Tatu, Andrada</dc:contributor>
    <dcterms:abstract xml:lang="eng">Modern Digital Library applications store and process massive amounts of information. Usually, this data is not limited to raw textual or numeric data - typical applications also deal with multimedia data such as images, audio, video, or 3D geometric models. For providing effective retrieval functionality, appropriate meta data descriptors that allow calculation of similarity scores between data instances are requires. Feature vectors are a generic way for describing multimedia data by vectors formed from numerically captured object features. They are used in similarity search, but also, can be used for clustering and wider multimedia analysis applications. Extracting effective feature vectors for a given data type is a challenging task. Determining good feature vector extractors usually involves experimentation and application of supervised information. However, such experimentation usually is expensive, and supervised information often is data dependent. We address the feature selection problem by a novel approach based on analysis of certain feature space images. We develop two image-based analysis techniques for the automatic discrimination power analysis of feature spaces. We evaluate the techniques on a comprehensive feature selection benchmark, demonstrating the effectiveness of our analysis and its potential toward automatically addressing the feature selection problem.</dcterms:abstract>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/5568/1/DELOS07.pdf"/>
    <dc:creator>Ward, Matthew O.</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-03-24T15:56:29Z</dcterms:available>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by-nc-nd/2.0/"/>
    <dc:contributor>Ward, Matthew O.</dc:contributor>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja