hh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Improving Very Low-Resolution Iris Identification Via Super-Resolution Reconstruction of Local Patches
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).ORCID-id: 0000-0002-1400-346X
University of Malta, Msida, Malta.
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).ORCID-id: 0000-0002-4929-1262
2017 (engelsk)Inngår i: 2017 International Conference of the Biometrics Special Interest Group (BIOSIG) / [ed] Arslan Brömme, Christoph Busch, Antitza Dantcheva, Christian Rathgeb & Andreas Uhl, Bonn: Gesellschaft für Informatik, 2017, Vol. P-270, artikkel-id 8053512Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Relaxed acquisition conditions in iris recognition systems have significant effects on the quality and resolution of acquired images, which can severely affect performance if not addressed properly. Here, we evaluate two trained super-resolution algorithms in the context of iris identification. They are based on reconstruction of local image patches, where each patch is reconstructed separately using its own optimal reconstruction function. We employ a database of 1,872 near-infrared iris images (with 163 different identities for identification experiments) and three iris comparators. The trained approaches are substantially superior to bilinear or bicubic interpolations, with one of the comparators providing a Rank-1 performance of ∼88% with images of only 15×15 pixels, and an identification rate of 95% with a hit list size of only 8 identities. © 2017 Gesellschaft fuer Informatik.

sted, utgiver, år, opplag, sider
Bonn: Gesellschaft für Informatik, 2017. Vol. P-270, artikkel-id 8053512
Serie
Lecture Notes in Informatics (LNI) - Proceedings, ISSN 1617-5468 ; P-270
Emneord [en]
Iris, biometrics, super-resolution, low resolution
HSV kategori
Identifikatorer
URN: urn:nbn:se:hh:diva-34738DOI: 10.23919/BIOSIG.2017.8053512Scopus ID: 2-s2.0-85034572701ISBN: 978-3-88579-664-0 (digital)ISBN: 978-1-5386-0396-3 (tryckt)OAI: oai:DiVA.org:hh-34738DiVA, id: diva2:1133802
Konferanse
16th International Conference of the Biometrics Special Interest Group (BIOSIG), Darmstadt, Germany, September 20-22, 2017
Prosjekter
SIDUS-AIR
Forskningsfinansiär
Swedish Research Council, 2012-4313Knowledge Foundation, SIDUS-AIRKnowledge Foundation, CAISRTilgjengelig fra: 2017-08-16 Laget: 2017-08-16 Sist oppdatert: 2017-12-11bibliografisk kontrollert

Open Access i DiVA

fulltext(648 kB)120 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 648 kBChecksum SHA-512
25a7d887080d9967ef089773f6bbf3629ed5319d06317b6b38f403db78bdd858cbae627afc9f9846b14c6cf2b4cd2e142eddccd8dedde740f1da15afb8685013
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Alonso-Fernandez, FernandoBigun, Josef

Søk i DiVA

Av forfatter/redaktør
Alonso-Fernandez, FernandoBigun, Josef
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 120 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 481 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf