Experimental evidence of ageing in hand biometrics

Abstract

Biometric systems build upon the critical property of measuring behavioral, physiological or chemical human properties remaining stable over time. But both, the age of users and ageing of the user's template may affect performance due to the accumulation of personal changes and indirect behavioral effects like less accurate ability to present the biometric to the sensor. This paper compares short-timespan versus longtimespan effects on different hand-based features presenting the first high-resolution hand-ageing database and identifying features resistant and prone to ageing. Ageing goats, i.e. users responsible for low matching scores across features, are investigated and single-sensor multibiometrics is highlighted to target the ageing problem.