Face Recognition Using SVM Combined with CNN for Face Detection

  • Masakazu Matsugu
  • Katsuhiko Mori
  • Takashi Suzuki
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)

Abstract

We propose a model for face recognition using a support vector machine being fed with a feature vector generated from outputs in several modules in bottom as well as intermediate layers of convolutional neural network (CNN) trained for face detection. The feature vector is composed of a set of local output distributions from feature detecting modules in the face detecting CNN. The set of local areas are automatically selected around facial components (e.g., eyes, moth, nose, etc.) detected by the CNN. Local areas for intermediate level features are defined so that information on spatial arrangement of facial components is implicitly included as output distribution from facial component detecting modules. Results demonstrate highly efficient and robust performance both in face recognition and in detection as well.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Belhumeur, P., Hesoanha, P., Kriegman, D.: Eigenfaces vs fisherfaces: recognition using class specific linear projection. IEEE Trans. on Pattern Analysis and Machine Intelligence 19, 711–720 (1997)CrossRefGoogle Scholar
  2. 2.
    Brunelli, R., Poggio, T.: Face recognition: features versus templates. IEEE Trans. on Pattern Analysis and Machine Intelligence 15, 1042–1052 (1993)CrossRefGoogle Scholar
  3. 3.
    Turk, M., Pentland, A.: Face recognition using eigenfaces. In: Proc. IEEE Conf. On Computer Vision and Pattern Recognition, pp. 586–591 (1991)Google Scholar
  4. 4.
    Fukushima, K.: Neocognitron: a self-organizing neural networks for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36, 193–202 (1980)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Guodong, G., Li, S., Kapluk, C.: Face recognition by support vector machines. In: Proc. IEEE International Conf. On Automatic Face and Gesture Recognition, pp. 196–201 (2000)Google Scholar
  6. 6.
    Heisele, B., Ho, P., Poggio, T.: Face recognition with support vector machines: global versus component-based approach. In: Proc. International Conf. on Computer Vision, pp. 688–694 (2001)Google Scholar
  7. 7.
    Heisele, B., Koshizen, T.: Components for Face Recognition. In: Proc. IEEE International Conf. on Automatic Face and Gesture Recognition (2004)Google Scholar
  8. 8.
    Le Cun, Y., Bengio, T.: Convolutional networks for images, speech, and time series. In: Arbib, M.A. (ed.) The handbook of brain theory and neural networks, pp. 255–258. MIT Press, Cambridge (1995)Google Scholar
  9. 9.
    Li, Y., Gong, S., Liddel, H.: Support vector regression and classification based multi-view face detection and recognition. In: Proc. IEEE International Conf. on Automatic Face and Gesture Recognition, pp. 300–305 (2000)Google Scholar
  10. 10.
    Matsugu, M., Mori, K., Ishii, M., Mitarai, Y.: Convolutional spiking neural network model for robust face detection. In: Proc. International Conf. on Neural Information Processing, pp. 660–664 (2002)Google Scholar
  11. 11.
    Mitarai, Y., Mori, K., Matsugu, M.: Robust Face Detection System Based on Convolutional Neural Networks Using Selective Activation of Modules (In Japanese). In: Proc. Forum in Information Technology, pp. 191–193 (2003)Google Scholar
  12. 12.
    Moghaddam, B., Wahid, W., Pentland, A.: Beyond eigenfaces: probabilistic matching for face recognition. In: Proc. IEEE International Conf. on Automatic Face and Gesture Recognition, pp. 30–35 (1998)Google Scholar
  13. 13.
    Pontil, M., Verri, A.: Support vector machines for 3-d object recognition. IEEE Trans.on Pattern Analysis and Machine Intelligence 20, 637–646 (1998)CrossRefGoogle Scholar
  14. 14.
    Wiskott, L., Fellous, J.-M., Krüger, N., von der Malsburg, C.: Face recognition by elastic bunch graph matching. IEEE Trans. on Pattern Analysis and Machine Intelligence 19, 775–779 (1997)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Masakazu Matsugu
    • 1
  • Katsuhiko Mori
    • 1
  • Takashi Suzuki
    • 1
  1. 1.Intelligent I/F Project.Canon Inc.AtsugiJapan

Personalised recommendations