TU Darmstadt / ULB / TUbiblio

Utility-based performance evaluation of biometric sample quality assessment algorithms

Henniger, Olaf ; Fu, Biying ; Chen, Cong
ed.: Gesellschaft für Informatik e.V. (2022)
Utility-based performance evaluation of biometric sample quality assessment algorithms.
21st International Conference of the Biometrics Special Interest Group. Darmstadt, Germany (14.-16.09.2022)
doi: 10.1109/BIOSIG55365.2022.9897037
Conference or Workshop Item, Bibliographie

Abstract

The quality score of a biometric sample is expected to predict the sample’s utility, but a universally valid definition of utility is missing. A harmonized definition of utility would be useful to facilitate the comparison of biometric sample quality assessment algorithms. This paper generalizes the utility of a biometric sample as normalized difference between the means of non-mated and mated comparison scores with respect to this sample. Using a face image data set, we show that discarding samples with low utility scores determined in this way results in a rapidly declining false non-match rate. The obtained utility scores can be used as ground-truth utility labels for training biometric sample quality assessment algorithms and for summarizing their prediction performance in a single plot and in a single Figure of merit based on the proposed utility score definition.

Item Type: Conference or Workshop Item
Erschienen: 2022
Creators: Henniger, Olaf ; Fu, Biying ; Chen, Cong
Type of entry: Bibliographie
Title: Utility-based performance evaluation of biometric sample quality assessment algorithms
Language: English
Date: 27 September 2022
Publisher: Gesellschaft für Informatik e.V.
Book Title: BIOSIG 2022: Proceedings of the 21st International Conference of the Biometrics Special Interest Group
Series: Lecture Notes in Informatics
Series Volume: P329
Event Title: 21st International Conference of the Biometrics Special Interest Group
Event Location: Darmstadt, Germany
Event Dates: 14.-16.09.2022
DOI: 10.1109/BIOSIG55365.2022.9897037
Abstract:

The quality score of a biometric sample is expected to predict the sample’s utility, but a universally valid definition of utility is missing. A harmonized definition of utility would be useful to facilitate the comparison of biometric sample quality assessment algorithms. This paper generalizes the utility of a biometric sample as normalized difference between the means of non-mated and mated comparison scores with respect to this sample. Using a face image data set, we show that discarding samples with low utility scores determined in this way results in a rapidly declining false non-match rate. The obtained utility scores can be used as ground-truth utility labels for training biometric sample quality assessment algorithms and for summarizing their prediction performance in a single plot and in a single Figure of merit based on the proposed utility score definition.

Uncontrolled Keywords: Biometrics, Quality estimation, Performance evaluation, Ground truth
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Date Deposited: 07 Nov 2022 14:59
Last Modified: 23 Mar 2023 08:09
PPN: 506239152
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details