Comparison of MLP and GMM Classifiers for Face Verification on XM2VTS

  • Fabien Cardinaux
  • Conrad Sanderson
  • Sébastien Marcel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2688)


We compare two classifier approaches, namely classifiers based on Multi Layer Perceptrons (MLPs) and Gaussian Mixture Models (GMMs), for use in a face verification system. The comparison is carried out in terms of performance, robustness and practicability. Apart from structural differences, the two approaches use different training criteria; the MLP approach uses a discriminative criterion, while the GMM approach uses a combination of Maximum Likelihood (ML) and Maximum a Posteriori (MAP) criteria. Experiments on the XM2VTS database show that for low resolution faces the MLP approach has slightly lower error rates than the GMM approach; however, the GMM approach easily outperforms the MLP approach for high resolution faces and is significantly more robust to imperfectly located faces. The experiments also show that the computational requirements of the GMM approach can be significantly smaller than the MLP approach at a cost of small loss of performance.


Discrete Cosine Transform Face Image Gaussian Mixture Model Equal Error Rate False Rejection 
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]
    Collobert, R., Bengio, S., and Mariéthoz, J.: Torch: a modular machine learning software library. IDIAP Research Report 02-46 (2002), Martigny, Switzerland. (see also 914
  2. [2]
    Dempster, A.P., Laird, N.M., and Rubin, D. B.: Maximum likelihood from incomplete data via the EM algorithm. J. Royal Statistical Soc., Ser. B 39 (1977) 1–38.zbMATHMathSciNetGoogle Scholar
  3. [3]
    Duda, R.O., Hart, P.E., and Stork, D.G.: Pattern Classification. John Wiley & Sons, USA, 2001.zbMATHGoogle Scholar
  4. [4]
    Eickeler, S., Müller, S., Rigoll, G.: Recognition of JPEG Compressed Face Images Based on Statistical Methods. Image and Vision Computing 18 (2000) 279–287.CrossRefGoogle Scholar
  5. [5]
    Féraud, R., Bernier, O., Viallet, J.-E., and Collobert, M.: A Fast and Accurate Face Detector Based on Neural Networks. Trans. Pattern Analysis and Machine Intell. 23 (2001) 42–53.CrossRefGoogle Scholar
  6. [6]
    Gauvain, J-L., and Lee, C-H.: Maximum a Posteriori Estimation for Multivariate Gaussian Mixture Observations of Markov Chains. IEEE Trans. Speech and Audio Processing 2 (1994) 291–298.CrossRefGoogle Scholar
  7. [7]
    Gonzales, R. C., and Woods, R. E.: Digital Image Processing. Addison-Wesley, Reading, Massachusetts, 1993.Google Scholar
  8. [8]
    Kittler, J., Matas, G., Jonsson, K., and Sanchez, M. U. R.: Combining Evidence in Personal Identity Verification Systems. Pattern Recognition Letters 18 (1997) 845–852.CrossRefGoogle Scholar
  9. [9]
    Lüttin, J., and Maître, G.: Evaluation Protocol for the Extended M2VTS Database (XM2VTSDB). IDIAP Communication 98-05 (1998), Martigny, Switzerland.Google Scholar
  10. [10]
    Martin, A., Doddington, G., Kamm, T., Ordowski, M., and Przybocki, M.: The DET Curve in Assessment of Detection Task Performance. Proc. Eurospeech’97, 1997, pp. 1895–1898.Google Scholar
  11. [11]
    Reynolds, D., Quatieri, T., and Dunn, R.: Speaker Verification Using Adapted Gaussian Mixture Models. Digital Signal Processing 10 (2000) 19–41.CrossRefGoogle Scholar
  12. [12]
    Rowley, H.A., Baluja, S., and Kanade, T.: Neural Network-Based Face Detection. Trans. Pattern Analysis and Machine Intelligence 20 (1998) 23–38.CrossRefGoogle Scholar
  13. [13]
    Sanderson, C.: Automatic Person Verification Using Speech and Face Information. PhD Thesis, Griffith University, Brisbane, Australia, 2002.Google Scholar
  14. [14]
    Sanderson, C. and Paliwal, K.K.: Polynomial Features for Robust Face Authentication. Proc. International Conf. on Image Processing, Rochester, New York, 2002, pp. 997–1000 (Vol. 3).Google Scholar
  15. [15]
    Schalko., R. J.: Pattern recognition: statistical, structural and neural approaches. John Wiley & Sons, USA, 1992.Google Scholar
  16. [16]
    Verlinde, P., Chollet, G., and Acheroy, M.: Multi-modal identity verification using expert fusion. Information Fusion 1 (2000) 17–33.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Fabien Cardinaux
    • 1
  • Conrad Sanderson
    • 1
  • Sébastien Marcel
    • 1
  1. 1.Dalle Molle Institute for Perceptual Artificial Intelligence (IDIAP)MartignySwitzerland

Personalised recommendations