Optimization of Integration Weights for a Multibiometric System with Score Level Fusion

  • S. M. Anzar
  • P. S. Sathidevi
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 177)


The effectiveness of a multibiometric system can be improved by weighting the scores obtained from the degraded modalities in an appropriate manner. In this paper, we propose an integration weight optimization scheme to determine the optimal weight factor for the complementary modalities, under different noise conditions. Instead of treating the weight estimation process from an algebraic point of view, an attempt is made to consider the same from the principles of linear programming techniques. The performance of the proposed technique is analysed in the context of fingerprint and voice biometrics using sum rule of fusion. The weight factor is optimized against the recognition accuracy. The optimizing parameter is estimated in the training/ validation phase using Leave-One-Out Cross Validation (LOOCV) technique. The proposed biometric solution can be be easily integrated into any multibiometric system with score level fusion. More over, it finds extremely useful in applications where there are less number of available training samples.


Gaussian Mixture Model Recognition Accuracy Integration Weight False Rejection Rate Score Level Fusion 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kekre, H.B., Bharadi, V.A.: Ageing Adaptation for Multimodal Biometrics using Adaptive Feature Set Update Algorithm. In: IEEE International Advance Computing Conference (IACC 2009), Patiala, India, March 6-7 (2009)Google Scholar
  2. 2.
    Toh, K.-A.: Fingerprint and speaker verification decisions fusion. In: International Conference on Image Analysis and Processing (ICIAP), Mantova, Italy, pp. 626–631 (September 2003)Google Scholar
  3. 3.
    Rajavel, R., Sathidevi, P.S.: Adaptive Reliability Measure and Optimum Integration Weight for Decision Fusion Audio-visual Speech Recognition. Springer J. Sign. Process. Syst. (February 2011)Google Scholar
  4. 4.
    Rajavel, R., Sathidevi, P.S.: The Effect of Reliability Measure on Integration Weight Estimation in Audio-Visual Speech Recognition. International Journal of Engineering Science and Technology 2(8) (2010)Google Scholar
  5. 5.
    Ross, A., Nandakumar, K., Jain, A.K.: Handbook of Multibiometrics. Springer, New York (2006)Google Scholar
  6. 6.
    Wuzhili: Finger Print Recognition, Honors Thesis (2002)Google Scholar
  7. 7.
    Reynolds, D.: Gaussian Mixture Models* MIT Lincoln Laboratory, 244 Wood St., Lexington, MA 02140, USAGoogle Scholar
  8. 8.
    Kim, J.: Iterated Grid Search Algorithm on Unimodal Criteria. Ph.D. Thesis, Blacksburg, Virginia (1997)Google Scholar
  9. 9.
    Yang, W.Y., Cao, W., Chung, T.-S., Morris, J.: Applied Numerical Methods using Matlab. Wiley, India (2007)Google Scholar
  10. 10.
    FVC 2002, the second International Competition for Fingerprint Verification Algorithms, FVC 2002 (2002),
  11. 11.
    Feng, L.: Speaker Recognition, Informatics and Mathematical Modelling, Technical University of Denmark, DTU (2004)Google Scholar
  12. 12.
    Martin, A., Doddington, G., Kamm, T., Ordowsk, M., Przybocki, M.: The DET Curve in Assessment of Detection Task Performance. In: Proc. Eurospeech 1997, Rhodes, pp. 1895–1898 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.S.M. Anzar, Dept. of Electronics and Communication EngineeringNational Institute of TechnologyCalicutIndia

Personalised recommendations