Share Email Print
cover

Proceedings Paper

Quality dependent fusion of intramodal and multimodal biometric experts
Author(s): J. Kittler; N. Poh; O. Fatukasi; K. Messer; K. Kryszczuk; J. Richiardi; A. Drygajlo
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We address the problem of score level fusion of intramodal and multimodal experts in the context of biometric identity verification. We investigate the merits of confidence based weighting of component experts. In contrast to the conventional approach where confidence values are derived from scores, we use instead raw measures of biometric data quality to control the influence of each expert on the final fused score. We show that quality based fusion gives better performance than quality free fusion. The use of quality weighted scores as features in the definition of the fusion functions leads to further improvements. We demonstrate that the achievable performance gain is also affected by the choice of fusion architecture. The evaluation of the proposed methodology involves 6 face and one speech verification experts. It is carried out on the XM2VTS data base.

Paper Details

Date Published: 12 April 2007
PDF: 14 pages
Proc. SPIE 6539, Biometric Technology for Human Identification IV, 653903 (12 April 2007); doi: 10.1117/12.724008
Show Author Affiliations
J. Kittler, Univ. of Surrey, Guildford (United Kingdom)
N. Poh, Univ. of Surrey, Guildford (United Kingdom)
O. Fatukasi, Univ. of Surrey, Guildford (United Kingdom)
K. Messer, Univ. of Surrey, Guildford (United Kingdom)
K. Kryszczuk, EPFL (Switzerland)
J. Richiardi, EPFL (Switzerland)
A. Drygajlo, EPFL (Switzerland)


Published in SPIE Proceedings Vol. 6539:
Biometric Technology for Human Identification IV
Salil Prabhakar; Arun A. Ross, Editor(s)

© SPIE. Terms of Use
Back to Top