Framework for managing ageing effects in signature biometrics

Abstract

This paper investigates and explores the impact of physical ageing in signature biometrics. Experimental performance evaluation, using three different signature databases, is carried out to provide some new insights into the relationship between different practical factors, in particular clarifying the impact on recognition performance of the data collection protocols used and the use of the feature pools underpinning the signature processing. This analysis provides an alternative perspective from which to explore and manage physical ageing effects in signature biometrics. The paper demonstrates that the proposed strategy maximises system accuracy while minimising the performance differential across a population which is heterogeneous with respect to age, and across different databases. The results presented suggest that adoption of the strategy proposed can render a template update procedure less critical than hitherto expected.