Advertisement

Rotation Invariant Face Detection Using Convolutional Neural Networks

  • Fok Hing Chi Tivive
  • Abdesselam Bouzerdoum
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)

Abstract

This article addresses the problem of rotation invariant face detection using convolutional neural networks. Recently, we developed a new class of convolutional neural networks for visual pattern recognition. These networks have a simple network architecture and use shunting inhibitory neurons as the basic computing elements for feature extraction. Three networks with different connection schemes have been developed for in-plane rotation invariant face detection: fully-connected, toeplitz-connected, and binary-connected networks. The three networks are trained using a variant of Levenberg-Marquardt algorithm and tested on a set of 40,000 rotated face patterns. As a face/non-face classifier, these networks achieve 97.3% classification accuracy for a rotation angle in the range ±900 and 95.9% for full in-plane rotation. The proposed networks have fewer free parameters and better generalization ability than the feedforward neural networks, and outperform the conventional convolutional neural networks.

Keywords

Hide Layer Inhibitory Neuron Convolutional Neural Network Convolutional Layer Face Pattern 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ampazis, N., Perantonis, S.J.: Two highly efficient second-order algorithms for training feedforward networks. IEEE Transactions on Neural Networks 13(5), 1064–1074 (2002)CrossRefGoogle Scholar
  2. 2.
    Arulampalam, G., Bouzerdoum, A.: Application of shunting inhibitory artificial neural networks to medical diagnosis. In: Proc. of the Seventh Australian and New Zealand Intelligent Information Systems Conference, Perth, pp. 89–94 (2001)Google Scholar
  3. 3.
    Barnard, E., Casasent, D.: Invariance and neural nets. IEEE Transactions on Neural Networks 2, 498–508 (1991)CrossRefGoogle Scholar
  4. 4.
    Bouzerdoum, A.: A new class of high-order neural networks with nonlinear decision boundaries. In: Proc. of the Sixth International Conference on Neural Information Processing, Perth, vol. 3, pp. 1004–1009 (1999)Google Scholar
  5. 5.
    Bouzerdoum, A.: Classification and function approximation using feed-forward shunting inhibitory artificial neural networks. In: Proc. of the IEEE-INNS-ENNS International Joint Conference on Neural Networks, pp. 613–618 (2000)Google Scholar
  6. 6.
    Casasent, D., Psaltis, D.: Position, rotation and scale-invariant optical correlation. Applied Optics 15(7), 1795–1799 (1976)CrossRefGoogle Scholar
  7. 7.
    Chong, C.-W., Raveendran, P., Mukundan, R.: Translation invariants of zernike moments. Pattern Recognition 36(8), 1765–1773 (2003)MATHCrossRefGoogle Scholar
  8. 8.
    Fukushima, K., Miyake, S., Ito, T.: Neocognitron: a neural network model for a mechanism of visual pattern recognition. IEEE Transactions Systems, Man, and Cybernetics SMC-13(5), 826–834 (1983)Google Scholar
  9. 9.
    Grossberg, S. (ed.): Neural Networks and Natural Intelligence. MIT Press, Cambridge (1988)Google Scholar
  10. 10.
    Gruber, M., Hsu, K.Y.: Moment-based image normalization with high noise tolerance. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(2), 136–139 (1997)CrossRefGoogle Scholar
  11. 11.
    Hu, M.K.: Visual pattern recognition by moment invariants. IRE Transactions Information Theory IT-8, 179–187 (1962)Google Scholar
  12. 12.
    Khotanzad, A., Lu, J.H.: Classification on invariant image representations using a neural network. IEEE Transactions on Acoustics, Speech, and Signal Processing 38, 1028–1038 (1990)CrossRefGoogle Scholar
  13. 13.
    LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Computation 1(4), 541–551 (1989)CrossRefGoogle Scholar
  14. 14.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. of the IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  15. 15.
    Phung, S.L., Bouzerdoum, A., Chai, D.: Skin segmentation using color pixel classification: analysis and comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(1), 148–154 (2005)CrossRefGoogle Scholar
  16. 16.
    Rodrigues, M.A.: Invariants for pattern recognition and classification. Machine perception and artificial intelligence, vol. 42. World Scientific, Singapore (2000)MATHGoogle Scholar
  17. 17.
    Teague, M.: Image analysis via the general theory of moments. Journal of the Optical Society of America 70(8), 920–930 (1980)CrossRefMathSciNetGoogle Scholar
  18. 18.
    Teh, C.H., Chin, R.T.: On image analysis by the method of moments. IEEE Transactions on Pattern Analysis and Machine Intelligence 10(4), 496–513 (1988)MATHCrossRefGoogle Scholar
  19. 19.
    Tivive, F.H.C., Bouzerdoum, A.: Efficient training algorithms for a class of shunting inhibitory convolutional neural networks. IEEE Transactions on Neural Networks 16(3), 541–556 (2005)CrossRefGoogle Scholar
  20. 20.
    Wood, J.: Invariant pattern recognition: a review. Pattern Recognition 29(1), 1–17 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Fok Hing Chi Tivive
    • 1
  • Abdesselam Bouzerdoum
    • 1
  1. 1.School of Electrical, Computer and Telecommunications EngineeringUniversity of WollongongWollongongAustralia

Personalised recommendations