Why Temporal Persistence of Biometric Features is so Valuable for Classification Performance
This work addresses a gap in understanding why temporal persistence matters in biometric systems, offering insights for researchers and practitioners in biometrics and pattern recognition, though it is incremental as it builds on prior empirical results.
The paper investigates how the temporal persistence of biometric features affects classification performance, showing that more persistent features improve performance in 12 out of 14 datasets and influence similarity score distributions, with decorrelation steps aligning real data results with synthetic findings.
It is generally accepted that relatively more permanent (i.e., more temporally persistent) traits are more valuable for biometric performance than less permanent traits. Although this finding is intuitive, there is no current work identifying exactly where in the biometric analysis temporal persistence makes a difference. In this paper, we answer this question. In a recent report, we introduced the intraclass correlation coefficient (ICC) as an index of temporal persistence for such features. In that report, we also showed that choosing only the most temporally persistent features yielded superior performance in 12 of 14 datasets. Motivated by those empirical results, we present a novel approach using synthetic features to study which aspects of a biometric identification study are influenced by the temporal persistence of features. What we show is that using more temporally persistent features produces effects on the similarity score distributions that explain why this quality is so key to biometric performance. The results identified with the synthetic data are largely reinforced by an analysis of two datasets, one based on eye-movements and one based on gait. There was one difference between the synthetic and real data: In real data, features are intercorrelated, with the level of intercorrelation increasing with increasing ICC. This increasedhttps://www.overleaf.com/project/5e2b14694c5dc600017292e6 intercorrelation in real data was associated with an increase in the spread of the impostor similarity score distributions. Removing these intercorrelations for real datasets with a decorrelation step produced results which were very similar to that obtained with synthetic features.