View source for Publications:Near-infrared and visible-light periocular recognition with Gabor features using frequency-adaptive automatic eye detection

<div style='display: none'>
== Do not edit this section ==
</div>
{{PublicationSetupTemplate|Author=Fernando Alonso-Fernandez, Josef Bigun
|PID=843044
|Name=Alonso-Fernandez, Fernando [feralo] (Högskolan i Halmstad [2804], Akademin för informationsteknologi [16904], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650]);Bigun, Josef [josef] (Högskolan i Halmstad [2804], Akademin för informationsteknologi [16904], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650])
|Title=Near-infrared and visible-light periocular recognition with Gabor features using frequency-adaptive automatic eye detection
|PublicationType=Journal Paper
|ContentType=Refereegranskat
|Language=eng
|Journal=IET Biometrics
|JournalISSN=2047-4938
|Status=published
|Volume=4
|Issue=2
|HostPublication=
|Conference=
|StartPage=74
|EndPage=89
|Year=2015
|Edition=
|Pages=
|City=Stevenage
|Publisher=Institution of Engineering and Technology
|Series=
|SeriesISSN=
|ISBN=
|Urls=
|ISRN=
|DOI=http://dx.doi.org/10.1049/iet-bmt.2014.0038
|ISI=000355256000005
|PMID=
|ScopusId=2-s2.0-84930350194
|NBN=urn:nbn:se:hh:diva-29054
|LocalId=
|ArchiveNumber=
|Keywords=
|Categories=Signalbehandling (20205)
|ResearchSubjects=
|Projects=EU BBfor2 Marie Curie Initial Training Network "Bayesian Biometrics for Forensics";EU COST Action IC1106 "Integrating Biometrics and Forensics for the Digital Age"
|Notes=<p>F. A.-F. thanks the Swedish Research Council and the EU for funding his postdoctoral research. The authors acknowledge the CAISR programme of the Swedish Knowledge Foundation, the EU BBfor2 project and the EU COST Action IC1106.</p>
|Abstract=<p>Periocular recognition has gained attention recently due to demands of increased robustness of face or iris in less controlled scenarios. We present a new system for eye detection based on complex symmetry filters, which has the advantage of not needing training. Also, separability of the filters allows faster detection via one-dimensional convolutions. This system is used as input to a periocular algorithm based on retinotopic sampling grids and Gabor spectrum decomposition. The evaluation framework is composed of six databases acquired both with near-infrared and visible sensors. The experimental setup is complemented with four iris matchers, used for fusion experiments. The eye detection system presented shows very high accuracy with near-infrared data, and a reasonable good accuracy with one visible database. Regarding the periocular system, it exhibits great robustness to small errors in locating the eye centre, as well as to scale changes of the input image. The density of the sampling grid can also be reduced without sacrificing accuracy. Lastly, despite the poorer performance of the iris matchers with visible data, fusion with the periocular system can provide an improvement of more than 20%. The six databases used have been manually annotated, with the annotation made publicly available. © The Institution of Engineering and Technology 2015.</p>
|Opponents=
|Supervisors=
|Examiners=
|Patent=
|ThesisLevel=
|Credits=
|Programme=
|Subject=
|Uppsok=
|DefencePlace=
|DefenceLanguage=
|DefenceDate=
|CreatedDate=2015-07-24
|PublicationDate=2015-07-24
|LastUpdated=2015-07-28
|diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:843044}}
<div style='display: none'>

== Keep all hand-made modifications below ==
</div>{{PublicationDisplayTemplate}}