hh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • 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
Exploring Deep Learning Image Super-Resolution for Iris Recognition
University of Salzburg, Salzburg, Austria.
University of Salzburg, Salzburg, Austria.
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.
2017 (engelsk)Inngår i: 2017 25th European Signal Processing Conference (EUSIPCO 2017), 2017, s. 2240-2244Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

In this work we test the ability of deep learning methods to provide an end-to-end mapping between low and high resolution images applying it to the iris recognition problem. Here, we propose the use of two deep learning single-image super-resolution approaches: Stacked Auto-Encoders (SAE) and Convolutional Neural Networks (CNN) with the most possible lightweight structure to achieve fast speed, preserve local in-formation and reduce artifacts at the same time. We validate the methods with a database of 1.872 near-infrared iris images with quality assessment and recognition experiments showing the superiority of deep learning approaches over the compared algorithms.  © EURASIP 2017

sted, utgiver, år, opplag, sider
2017. s. 2240-2244
HSV kategori
Identifikatorer
URN: urn:nbn:se:hh:diva-34739ISBN: 978-0-9928626-7-1 (tryckt)OAI: oai:DiVA.org:hh-34739DiVA, id: diva2:1133805
Konferanse
2017 25th European Signal Processing Conference (EUSIPCO 2017), Kos Island, Greece, August 28 - September 2, 2017
Prosjekter
SIDUS-AIR
Forskningsfinansiär
Swedish Research Council, 2012-4313Knowledge Foundation, SIDUS-AIRKnowledge Foundation, CAISR
Merknad

Funding: CNPq-Brazil

Tilgjengelig fra: 2017-08-16 Laget: 2017-08-16 Sist oppdatert: 2017-10-09bibliografisk kontrollert

Open Access i DiVA

fulltext(817 kB)118 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 817 kBChecksum SHA-512
aded49060be42c1c7a233a0622d6b21d3ba13a258a7ef1787f014665dff1b8561d72d2e61cb6c0bd20c2258777fa31006bf58a5e7bb871b4932bdc4de8faa304
Type fulltextMimetype application/pdf

Andre lenker

Full text

Personposter BETA

Alonso-Fernandez, Fernando

Søk i DiVA

Av forfatter/redaktør
Alonso-Fernandez, Fernando
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 118 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

isbn
urn-nbn

Altmetric

isbn
urn-nbn
Totalt: 346 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • 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