Quality dependent fusion of intramodal and multimodal biometric experts

J. Kittler; N. Poh; O. Fatukasi; K. Messer; K. Kryszczuk; J. Richiardi; A. Drygajlo

doi:10.1117/12.724008

12 April 2007 Quality dependent fusion of intramodal and multimodal biometric experts

J. Kittler, N. Poh, O. Fatukasi, K. Messer, K. Kryszczuk, J. Richiardi, A. Drygajlo

Author Affiliations +

Proceedings Volume 6539, Biometric Technology for Human Identification IV; 653903 (2007) https://doi.org/10.1117/12.724008
Event: Defense and Security Symposium, 2007, Orlando, Florida, United States

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.

Citation Download Citation

J. Kittler, N. Poh, O. Fatukasi, K. Messer, K. Kryszczuk, J. Richiardi, and A. Drygajlo "Quality dependent fusion of intramodal and multimodal biometric experts", Proc. SPIE 6539, Biometric Technology for Human Identification IV, 653903 (12 April 2007); https://doi.org/10.1117/12.724008

Access the abstract

PROCEEDINGS
14 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

CITATIONS

Cited by 43 scholarly publications and 1 patent.

Explore citations on Lens.org

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Biometrics

Quality measurement

Databases

Lawrencium

Data fusion

Algorithm development

Information fusion

Show All Keywords

RELATED CONTENT

Weighted sparse fusion for FV and FDT identification
Proceedings of SPIE (August 09 2018)

Toward more robust exploitation of the asymmetric threat binary...
Proceedings of SPIE (May 05 2011)

Kernel-based multimodal biometric verification using quality signals
Proceedings of SPIE (August 25 2004)

An ensemble approach to data fusion and its application to...
Proceedings of SPIE (May 07 2007)

Image quality guided approach for adaptive modelling of biometric intra...
Proceedings of SPIE (April 28 2010)

Dealing with sensor interoperability in multi biometrics the UPM...
Proceedings of SPIE (March 17 2008)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years