University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Algorithm to estimate biometric performance change over time

Poh, N, Kittler, J, Chan, C-H and Pandit, M (2015) Algorithm to estimate biometric performance change over time IET BIOMETRICS, 4 (4). pp. 236-245.

norman_eer_trend_mmbio_journal_v1.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (862kB) | Preview
Text (licence)
Available under License : See the attached licence file.

Download (33kB) | Preview


We present an algorithm that models the rate of change of biometric performance over time on a subject-dependent basis. It is called “homomorphic users grouping algorithm” or HUGA. Although the model is based on very simplistic assumptions that are inherent in linear regression, it has been applied successfully to estimate the performance of talking face and speech identity verification modalities, as well as their fusion, over a period of more than 600 days. Our experiments carried out on the MOBIO database show that subjects exhibit very different performance trends. While the performance of some users degrades over time, which is consistent with the literature, we also found that for a similar proportion of users, their performance actually improves with use. The latter finding has never been reported in the literature. Hence, our findings suggest that the problem of biometric performance degradation may be not as serious as previously thought, and so far, the community has ignored the possibility of improved biometric performance over time. The findings also suggest that adaptive biometric systems, that is, systems that attempt to update biometric templates, should be subject-dependent.

Item Type: Article
Subjects : Computer Science
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
Poh, N
Kittler, J
Chan, C-H
Pandit, M
Date : 1 December 2015
DOI : 10.1049/iet-bmt.2014.0107
Copyright Disclaimer : This paper is a postprint of a paper submitted to and accepted for publication in IET BIOMETRICS and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library
Uncontrolled Keywords : Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, SPEAKER VERIFICATION SYSTEMS, AUTHENTICATION
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 20 Oct 2016 08:30
Last Modified : 31 Oct 2017 18:48

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800