Logo des Repositoriums
 

Predicting Dactyloscopic Examiner Fingerprint Image Quality Assessments

dc.contributor.authorOlsen, Martin Aastrup
dc.contributor.authorBöckeler, Martin
dc.contributor.authorBusch, Christoph
dc.contributor.editorBrömme, Arslan
dc.contributor.editorBusch, Christoph
dc.contributor.editorRathgeb, Christian
dc.contributor.editorUhl, Andreas
dc.date.accessioned2017-06-30T08:19:18Z
dc.date.available2017-06-30T08:19:18Z
dc.date.issued2015
dc.description.abstractWe work towards a system which can assist dactyloscopic examiners in assessing the quality and decision value of a fingerprint image and eventually a fingermark. However when quality assessment tasks of datyloscopic examiners are replaced by automatic quality assessment then we need to ensure that the automatic measurement is in agreement with the examiner opinion. Under the assumption of such agreement, we can predict the examiner opinion. We propose a method for determining the examiner agreement on ordinal scales and show that there is a high level of agreement between examiners assessing the ground truth quality of fingerprints. With ground truth quality information on 749 fingerprints and using 10-fold cross validation we construct models using Support Vector Machines and Proportional Odds Logistic Re- gression which predicts median examiner quality assessments 35\% better than when using the prior class distribution.en
dc.identifier.isbn978-3-88579-639-8
dc.identifier.pissn1617-5468
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofBIOSIG 2015
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-245
dc.titlePredicting Dactyloscopic Examiner Fingerprint Image Quality Assessmentsen
dc.typeText/Conference Paper
gi.citation.endPage96
gi.citation.publisherPlaceBonn
gi.citation.startPage85
gi.conference.date9.-11. September 2015
gi.conference.locationDarmstadt

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
85.pdf
Größe:
273.33 KB
Format:
Adobe Portable Document Format