Skip to main content
EURASIP Journal on Advances in Signal Processing
Download PDF
  • Research Article
  • Open access
  • Published:

Reliability-Based Decision Fusion in Multimodal Biometric Verification Systems

EURASIP Journal on Advances in Signal Processing volume 2007, Article number: 086572 (2007) Cite this article

Abstract

We present a methodology of reliability estimation in the multimodal biometric verification scenario. Reliability estimation has shown to be an efficient and accurate way of predicting and correcting erroneous classification decisions in both unimodal (speech, face, online signature) and multimodal (speech and face) systems. While the initial research results indicate the high potential of the proposed methodology, the performance of the reliability estimation in a multimodal setting has not been sufficiently studied or evaluated. In this paper, we demonstrate the advantages of using the unimodal reliability information in order to perform an efficient biometric fusion of two modalities. We further show the presented method to be superior to state-of-the-art multimodal decision-level fusion schemes. The experimental evaluation presented in this paper is based on the popular benchmarking bimodal BANCA database.

References

  1. Short J, Kittler J, Messer K: A comparison of photometric normalisation algorithms for face verification. Proceedings of the 6th IEEE International Conference on Automatic Face and Gesture Recognition (FGR '04), May 2004, Seoul, South Korea 254–259.

    Google Scholar 

  2. Barras C, Gauvain J-L: Feature and score normalization for speaker verification of cellular data. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '03), April 2003, Hong Kong 2: 49–52.

    Google Scholar 

  3. Ross A, Jain AK, Qian J-Z: Information fusion in biometrics. Proceedings of the 3rd International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA '01), June 2001, Halmstad, Sweden 354–359.

    Chapter  Google Scholar 

  4. Roli F, Kittler J, Fumera G, Muntoni D: An experimental comparison of classifier fusion rules for multimodal personal identity verification systems. Proceedings of the 3rd International Workshop Multiple Classifier Systems (MCS '02), June 2002, Cagliari, Italy 325–336.

    Chapter  Google Scholar 

  5. Bigun J, Fierrez-Aguilar J, Ortega-Garcia J, Gonzalez-Rodriguez J: Multimodal biometric authentication using quality signals in mobile communications. Proceedings of the 12th International Conference on Image Analysis and Processing (ICIAP '03), September 2003, Mantova, Italy 2–11.

    Google Scholar 

  6. Richiardi J, Prodanov P, Drygajlo A: A probabilistic measure of modality reliability in speaker verification. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '05), March 2005, Philadelphia, Pa, USA 1: 709–712.

    Google Scholar 

  7. Kryszczuk K, Richiardi J, Prodanov P, Drygajlo A: Error handling in multimodal biometric systems using reliability measures. Proceedings of the 13th European Signal Processing Conference (EUSIPCO '05), September 2005, Antalya, Turkey

    Google Scholar 

  8. Poh N, Bengio S: Improving fusion with margin-derived confidence in biometric authentication tasks. Proceedings of the 5th International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA '05), July 2005, Hilton Rye Town, NY, USA 474–483.

    Chapter  Google Scholar 

  9. Brümmer N, du Preez J: Application-independent evaluation of speaker detection. Computer Speech & Language 2006,20(2-3):230-275. 10.1016/j.csl.2005.08.001

    Article  Google Scholar 

  10. Fredouille C, Bonastre J-F, Merlin T: Similarity normalization method based on world model and a posteriori probability for speaker verification. Proceedings of the 6th European Conference on Speech Communication and Technology (EUROSPEECH '99), September 1999, Budapest, Hungary 983–986.

    Google Scholar 

  11. Murphy K: Dynamic Bayesian networks: representation, inference and learning, Ph.D. thesis. Computer Science Division, University of California - Berkeley, Berkeley, Calif, USA; 2002.

    Google Scholar 

  12. Richiardi J, Prodanov P, Drygajlo A: Speaker verification with confidence and reliability measures. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '06), May 2006, Toulouse, France 1: 641–644.

    MATH  Google Scholar 

  13. Bailly-Bailliére E, Bengio S, Bimbot F, et al.: The BANCA database and evaluation protocol. In Proceedings of the 4th International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA '03), June 2003, Guildford, UK, Lecture Notes in Computer Science Edited by: Kittler J, Nixon M. 2688: 625–638.

    Chapter  Google Scholar 

  14. Bonastre J-F, Wils F, Meignier S: ALIZE, a free toolkit for speaker recognition. Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '05), March 2005, Philadelphia, Pa, USA 1: 737–740.

    Google Scholar 

  15. Reynolds D: A Gaussian mixture modeling approach to text-independent speaker identification, Ph.D. thesis. Georgia Institute of Technology, Atlanta, Ga, USA; 1992.

    Google Scholar 

  16. Kryszczuk K, Drygajlo A: On face image quality measures. Proceedings of the 2nd Workshop on Multimodal User Authentication, May 2006, Toulouse, France

    Google Scholar 

  17. Messer K, Kittler J, Sadeghi M, et al.: Face authentication competition on the BANCA database. Proceedings of the 1st International Conference on Biometric Authentication (ICBA '04), July 2004, Hong Kong 8–15.

    Chapter  Google Scholar 

  18. Sanderson C, Bengio S: Robust features for frontal face authentication in difficult image conditions. Proceedings of the 4th International Conference on Audio- and Video-Based Biometric Person Authentication (AVBPA '03), June 2003, Guildford, UK 495–504.

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Signal Processing Institute, Swiss Federal Institute of Technology, Lausanne, 1015, Switzerland

    Krzysztof Kryszczuk, Jonas Richiardi, Plamen Prodanov & Andrzej Drygajlo

Authors
  1. Krzysztof Kryszczuk
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jonas Richiardi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Plamen Prodanov
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Andrzej Drygajlo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Krzysztof Kryszczuk.

Rights and permissions

Open Access This article is distributed under the terms of the Creative Commons Attribution 2.0 International License (https://doi.org/creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and permissions

About this article

Cite this article

Kryszczuk, K., Richiardi, J., Prodanov, P. et al. Reliability-Based Decision Fusion in Multimodal Biometric Verification Systems. EURASIP J. Adv. Signal Process. 2007, 086572 (2007). https://doi.org/10.1155/2007/86572

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1155/2007/86572

Keywords