Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Demographic Bias in Presentation Attack Detection of Iris Recognition Systems

: Fang, Meiling; Damer, Naser; Kirchbuchner, Florian; Kuijper, Arjan


Heusdens, Richard (Hrsg.) ; European Association for Signal Processing -EURASIP-:
28th European Signal Processing Conference, EUSIPCO 2020. Proceedings : 24-28 August 2020, Amsterdam, the Netherlands
Amsterdam: EURASIP, 2020
ISBN: 978-9-0827-9705-3
ISBN: 978-9-08279-704-6
ISBN: 978-1-7281-5001-7
European Signal Processing Conference (EUSIPCO) <28, 2020, Amsterdam/cancelled>
European Signal Processing Conference (EUSIPCO) <28, 2021, Online>
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
Fraunhofer IGD ()
Lead Topic: Digitized Work; Lead Topic: Smart City; Research Line: Computer vision (CV); biometrics; computer vision; machine learning; ATHENE; CRISP

With the widespread use of biometric systems, the demographic bias problem raises more attention. Although many studies addressed bias issues in biometric verification, there are no works that analyze the bias in presentation attack detection (PAD) decisions. Hence, we investigate and analyze the demographic bias in iris PAD algorithms in this paper. To enable a clear discussion, we adapt the notions of differential performance and differential outcome to the PAD problem. We study the bias in iris PAD using three baselines (hand-crafted, transfer-learning, and training from scratch) using the NDCLD- 2013 [18] database. The experimental results point out that female users will be significantly less protected by the PAD, in comparison to males.