Comparing verification performance of kids and adults for Fingerprint, Palmprint, Hand-geometry and Digitprint biometrics

Abstract

With the large scale deployment of biometrics for access control in private and public places, systems are faced the challenge of processing a diverse range of people. Most systems have been well evaluated for adults, however, their application in schools, or for private door access control, raises the question, whether there exists significant difference in performance between age groups in general and between kids and adults in particular. This paper targets an evaluation of the impact of children as biometric users on recognition accuracy for a series of hand-based modalities: Fingerprint, Palmprint, Hand-geometry and Digitprint. Furthermore, we try to analyze reasons for child-aging effects on performance at both feature and instance level using our database of 301 kids and 86 adults.