Personal identification using Eigenfeet, Ballprint and Foot geometry biometrics

This paper presents a new approach for personal identification using foot-biometric features based on eigenfeet, local ridge characteristics and shape geometry. For niche applications, employing footprint-based authentication might bear enough security without the drawback of relying on sensitive data demanded by high-security applications. Credit card numbers can be changed, biometric features can't be changed, thus privacy issues are fundamental. Part one of this paper outlines origins, fields of application and proposed system setup. After an introduction to employed normalization and feature extraction steps we discuss specific characteristics of foot biometrics compared to traditional hand and face-based techniques. Experimental results of all three employed biometric matchers are given and analyzed in part two. Finally, we present a summary of observed results.