Fuzzy face vault: how to implement fuzzy vault with weighted features

Authors:
DaeHun Nyang;KyungHee Lee
Affiliations:
Graduate School of Information Technology and Telecommunications, Inha University, Incheon, Korea;Department of Electrical Engineering, The University of Suwon, Suwon, Korea
Venue:
UAHCI'07 Proceedings of the 4th international conference on Universal access in human computer interaction: coping with diversity
Year:
2007

Citing 3
Cited 1

A fuzzy commitment scheme

CCS '99 Proceedings of the 6th ACM conference on Computer and communications security
How to share a secret

Communications of the ACM
Secure smartcardbased fingerprint authentication

WBMA '03 Proceedings of the 2003 ACM SIGMM workshop on Biometrics methods and applications

A bio-cryptographic system based on offline signature images

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Ari Juel et al from ISIT 2002 presented a fuzzy vault scheme, which is a framework to encrypt a cryptographic key with a fuzzy key[5]. Following their framework, many trials to implement mainly a fuzzy finger vault have been proposed that enables us to keep secretly a key with our finger print. Our work is to focus on instantiating the fuzzy information of the fuzzy vault scheme with human faces instead of fingers. Most of face authentication algorithms are dependent upon weighted features, which are incompatible with the original fuzzy vault scheme. To reflect the level of importance of individual features from feature set, we introduce another layer between captured feature set and points in the polynomial to be interpolated.