CC BY 4.0Henniger, OlafOlafHennigerFu, BiyingBiyingFuKurz, AlexanderAlexanderKurz2024-09-122024-09-122024https://publica.fraunhofer.de/handle/publica/475153https://doi.org/10.24406/publica-366010.1186/s13640-024-00644-110.24406/publica-3660The quality score of a biometric sample is intended to predict the sample’s degree of utility for biometric recognition. Different authors proposed different definitions for utility. A harmonized definition of utility would be useful to facilitate the comparison of biometric sample quality assessment algorithms. In this article, we compare different definitions of utility and apply them to both face image and fingerprint image data sets containing multiple samples per biometric instance and covering a wide range of potential quality issues. The results differ only slightly. We show that discarding samples with low utility scores results in rapidly declining false non-match rates. The obtained utility scores can be used as target labels for training biometric sample quality assessment algorithms and as baseline when summarizing utility-prediction performance in a single plot or even in a single figure of merit.enBranche: Information TechnologyBranche: BioeconomicsResearch Line: Human computer interaction (HCI)Research Line: Machine learning (ML)LTA: Machine intelligence, algorithms, and data structures (incl. semantics)BiometricsQuality estimationPerformance evaluationATHENEjournal article