hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Log-Likelihood Score Level Fusion for Improved Cross-Sensor Smartphone Periocular Recognition
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.ORCID iD: 0000-0002-1400-346X
Norwegian University of Science and Technology, Gjøvik, Norway.
Norwegian University of Science and Technology, Gjøvik, Norway.
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR - Center for Applied Intelligent Systems Research.ORCID iD: 0000-0002-4929-1262
2017 (English)In: 2017 25th European Signal Processing Conference (EUSIPCO), Piscataway: IEEE, 2017, p. 281-285, article id 8081211Conference paper, Published paper (Refereed)
Abstract [en]

The proliferation of cameras and personal devices results in a wide variability of imaging conditions, producing large intra-class variations and a significant performance drop when images from heterogeneous environments are compared. However, many applications require to deal with data from different sources regularly, thus needing to overcome these interoperability problems. Here, we employ fusion of several comparators to improve periocular performance when images from different smartphones are compared. We use a probabilistic fusion framework based on linear logistic regression, in which fused scores tend to be log-likelihood ratios, obtaining a reduction in cross-sensor EER of up to 40% due to the fusion. Our framework also provides an elegant and simple solution to handle signals from different devices, since same-sensor and crosssensor score distributions are aligned and mapped to a common probabilistic domain. This allows the use of Bayes thresholds for optimal decision making, eliminating the need of sensor-specific thresholds, which is essential in operational conditions because the threshold setting critically determines the accuracy of the authentication process in many applications. © EURASIP 2017

Place, publisher, year, edition, pages
Piscataway: IEEE, 2017. p. 281-285, article id 8081211
Series
European Signal Processing Conference (EUSIPCO), ISSN 2076-1465
National Category
Signal Processing
Identifiers
URN: urn:nbn:se:hh:diva-34740DOI: 10.23919/EUSIPCO.2017.8081211Scopus ID: 2-s2.0-85041546333ISBN: 978-0-9928626-7-1 (print)OAI: oai:DiVA.org:hh-34740DiVA, id: diva2:1133812
Conference
2017 25th European Signal Processing Conference (EUSIPCO 2017), 28 Aug.-2 Sept., 2017, Kos Island, Greece
Projects
SIDUS-AIR
Funder
Swedish Research Council, 2012-4313Knowledge Foundation, SIDUS-AIRKnowledge Foundation, CAISRAvailable from: 2017-08-16 Created: 2017-08-16 Last updated: 2018-03-06Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopusFull Text

Authority records BETA

Alonso-Fernandez, FernandoBigun, Josef

Search in DiVA

By author/editor
Alonso-Fernandez, FernandoBigun, Josef
By organisation
CAISR - Center for Applied Intelligent Systems Research
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 65 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf