Cohort based approach to multiexpert class verification

Authors:
Josef Kittler;Norman Poh;Amin Merati
Affiliations:
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK;Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK;Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK
Venue:
MCS'11 Proceedings of the 10th international conference on Multiple classifier systems
Year:
2011

Citing 1
Cited 0

A multimodal biometric test bed for quality-dependent, cost-sensitive and client-specific score-level fusion algorithms

Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

We address the problem of cohort based normalisation in multiexpert class verification. We show that there is a relationship between decision templates and cohort based normalisation methods. Thanks to this relationship, some of the recent features of cohort score normalisation techniques can be adopted by decision templates, with the benefit of noise reduction and the ability to compensate for any distribution drift.