A Modified Neutral Point Method for Kernel-Based Fusion of Pattern-Recognition Modalities with Incomplete Data Sets

  • Maxim Panov
  • Alexander Tatarchuk
  • Vadim Mottl
  • David Windridge
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6713)


It is commonly the case in multi-modal pattern recognition that certain modality-specific object features are missing in the training set. We address here the missing data problem for kernel-based Support Vector Machines, in which each modality is represented by the respective kernel matrix over the set of training objects, such that the omission of a modality for some object manifests itself as a blank in the modality-specific kernel matrix at the relevant position. We propose to fill the blank positions in the collection of training kernel matrices via a variant of the Neutral Point Substitution (NPS) method, where the term ”neutral point” stands for the locus of points defined by the ”neutral hyperplane” in the hypothetical linear space produced by the respective kernel. The current method crucially differs from the previously developed neutral point approach in that it is capable of treating missing data in the training set on the same basis as missing data in the test set. It is therefore of potentially much wider applicability. We evaluate the method on the Biosecure DS2 data set.


Support Vector Machine Object Representation Neutral Point Equal Error Rate Kernel Trick 
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.
    Ross, A., Jain, A.K.: Multimodal biometrics: An overview. In: Proc. of the 12th European Signal Processing Conference (EUSIPCO), Austria, pp. 1221–1224 (2004)Google Scholar
  2. 2.
    Mottl, V., Tatarchuk, A., Sulimova, V., Krasotkina, O., Seredin, O.: Combining pattern recognition modalities at the sensor level via kernel fusion. In: Haindl, M., Kittler, J., Roli, F. (eds.) MCS 2007. LNCS, vol. 4472, pp. 1–12. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Tatarchuk, A., Sulimova, V., Windridge, D., Mottl, V., Lange, M.: Supervised selective combining pattern recognition modalities and its application to signature verification by fusing on-line and off-line kernels. In: Benediktsson, J.A., Kittler, J., Roli, F. (eds.) MCS 2009. LNCS, vol. 5519, pp. 324–334. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  4. 4.
    Tatarchuk, A., Urlov, E., Mottl, V., Windridge, D.: A support kernel machine for supervised selective combining of diverse pattern-recognition modalities. In: El Gayar, N., Kittler, J., Roli, F. (eds.) MCS 2010. LNCS, vol. 5997, pp. 165–174. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Nandakumar, K., Jain, A.K., Ross, A.: Fusion in multibiometric identification systems: What about the missing data? In: Proc. of the 3rd IAPR/IEEE International Conference on Biometrics, Italy (June 2009)Google Scholar
  6. 6.
    Poh, N., Bourlai, T., Kittler, J., et al.: Benchmarking quality-dependent and cost-sensitive score-level multimodal biometric fusion algorithms. IEEE Trans. on Information Forensics and Security 4(4), 849–866 (2009)CrossRefzbMATHGoogle Scholar
  7. 7.
    Windridge, D., Mottl, V., Tatarchuk, A., Eliseyev, A.: The neutral point method for kernel-based combination of disjoint training data in multi-modal pattern recognition. In: Haindl, M., Kittler, J., Roli, F. (eds.) MCS 2007. LNCS, vol. 4472, pp. 13–21. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Poh, N., Windridge, D., Mottl, V., Tatarchuk, A., Eliseyev, A.: Addressing missing values in kernel-based multimodal biometric fusion using neutral point substitution. IEEE Trans. on Information Forensics and Security 5(3), 461–469 (2010)CrossRefGoogle Scholar
  9. 9.
    Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Trans. on Pattern Analysis and Machine Intelligence 20, 226–239 (1998)CrossRefGoogle Scholar
  10. 10.
    Poh, N., Bourlai, T., Kittler, J.: A multimodal biometric test bed for quality-dependent, cost-sensitive and client-specific score-level fusion algorithms. Pattern Recognition 43(3), 1094–1105 (2010), CrossRefzbMATHGoogle Scholar
  11. 11.
    Vapnik, V.: Statistical Learning Theory. John-Wiley & Sons, Inc, New York (1998)zbMATHGoogle Scholar
  12. 12.
    Mottl, V.: Metric spaces admitting linear operations and inner product. Doklady Mathematics 67(1), 140–143 (2003)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Maxim Panov
    • 1
  • Alexander Tatarchuk
    • 2
  • Vadim Mottl
    • 2
  • David Windridge
    • 3
  1. 1.Moscow Institute of Physics and TechnologyDolgoprudnyRussia
  2. 2.Computing Center of the Russian Academy of SciencesMoscowRussia
  3. 3.Center for Vision, Speech and Signal ProcessingUniversity of SurreyGuildfordUK

Personalised recommendations