Logo des Repositoriums

Auflistung nach Autor:in "Olsen, Martin Aastrup"

1 - 2 von 2
  • Konferenzbeitrag
    Predicting Dactyloscopic Examiner Fingerprint Image Quality Assessments
    (BIOSIG 2015, 2015) Olsen, Martin Aastrup; Böckeler, Martin; Busch, Christoph
    We 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.
  • Konferenzbeitrag
    A topology based approach to categorization of fingerprint images
    (BIOSIG 2012, 2012) Aabrandt, Andreas; Olsen, Martin Aastrup; Busch, Christoph
    This paper discusses the use of betti numbers to characterize fingerprint and iris images. The goal is to automatically separate fingerprint images from nonfingerprint images; where non-fingerprint images of special interest are biometric samples which are not fingerprints. In this regard, an image is viewed as a triangulated point cloud and the topology associated with this construct is summarized using its first betti number - a number that indicates the number of distinct cycles in the triangulation associated to the particular image. This number is then compared against the first betti numbers of “n” prototype images in order to perform classification (“fingerprint” vs “non-fingerprint”). The proposed method is compared against SIVV (a tool provided by NIST). Experimental results on fingerprint and iris databases demonstrate the potential of the scheme.