HandFootBio

Members

University of Salzburg (Peter Wild, Andreas Uhl)

Summary

This project was my master's thesis project conducted under supervisor Andreas Uhl. The main objective was to develop a single-sensor hand biometric system for authentication tasks based on multiple modalities (hand geometry, fingerprint and palmprint) and to relate these techniques to a new biometric: the human foot. For evaluation purposes, a custom database of 443 right-hand images and 160 right-foot samples was collected at the Department of Computer Sciences, University of Salzburg, Austria. Results indicated, that in verification mode (1:1 comparison with a claimed identity) footprint-based multimodal recognition could achieve recognition rates in the order of unimodal hand-based systems: a minimum half total error rate (MinHTER) of 0.41% was observed. However, fusion techniques on multiple hand-based modalities yielded even lower error rates of 0.003% MinHTER. Whilst for traditional access control, single-sensor hand-based solutions seem to be a highly efficient choice, still foot biometrics provide a useful alternative for selected applications (e.g. in spas or public baths, where footprints may be captured without the need to take off shoes or socks).

Hand: Fingerprint's minutiae Foot: Ballprint's minutiae Hand: Finger lengths Foot: Silhouette
Hand: Fingerprint's minutiae Foot: Ballprint's minutiae Hand: Finger lengths Foot: Silhouette

Downloads

Last modified: 07 November 2015 04:57:31
© Peter Wild. All rights reserved.