Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition

  • Dan Zhang
  • Yuan Yan Tang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5558)

Abstract

Two Empirical Mode Decomposition (EMD) based face recognition schemes are proposed in this paper to address variant illumination problem. EMD is a data-driven analysis method for nonlinear and non-stationary signals. It decomposes signals into a set of Intrinsic Mode Functions (IMFs) that containing multiscale features. The features are representative and especially efficient in capturing high-frequency information. The advantages of EMD accord well with the requirements of face recognition under variant illuminations. Earlier studies show that only the low-frequency component is sensitive to illumination changes, it indicates that the corresponding high-frequency components are more robust to the illumination changes. Therefore, two face recognition schemes based on the IMFs are generated. One is using the high-frequency IMFs directly for classification. The other one is based on the synthesized face images fused by high-frequency IMFs. The experimental results on the PIE database verify the efficiency of the proposed methods.

Keywords

Empirical Mode Decomposition Face recognition 

References

  1. 1.
    Huang, N.E., Shen, Z., Long, S.R., et al.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society A 454(1971), 903–995 (1998)Google Scholar
  2. 2.
    Huang, N.E., Shen, S.S.P.: Hilbert-Huang transform and its applications. Book in Interdisciplinary Mathematical Sciences, vol. 5 (2005)Google Scholar
  3. 3.
    Huang, N.E., Wu, M.L.C., Long, S.R., et al.: A confidence limit for the empirical mode decomposition and Hilbert spectral analysis. Proceedings of the Royal Society A 459(2037), 2317–2345 (2003)Google Scholar
  4. 4.
    Long, S.R.: Applications of HHT in image analysis. In: Huang, N.E., Shen, S.S.P. (eds.) Hilbert-Huang Transform and Its Applications. World Scientific, River Edge (2005)Google Scholar
  5. 5.
    Hariharan, H., Gribok, A., Abidi, B., Abidi, M.: Multi-modal Face Image Fusion using Empirical Mode Decomposition. In: The Biometrics Consortium Conference, Crystal City, VA (2005)Google Scholar
  6. 6.
    Hariharan, H., Koschan, A., Abidi, B., Gribok, A., Abidi, M.A.: Fusion of visible and infrared images using empirical mode decomposition to improve face recognition. In: IEEE International Conference on Image Processing, ICIP 2006, Atlanta, GA, pp. 2049–2052 (2006)Google Scholar
  7. 7.
    Bhagavatula, R., Savvides, M., Acoustics, M.: Analyzing Facial Images using Empirical Mode Decomposition for Illumination Artifact Removal and Improved Face Recognition. In: IEEE International Conference on Speech and Signal Processing, 2007 (ICASSP 2007), April 15-20, vol. 1, pp. 505–508 (2007)Google Scholar
  8. 8.
    Nunes, J.C., Bouaoune, Y., Delechelle, E., Niang, O., Bunel, P.: Image analysis by bidimensional empirical mode decomposition. Image and Vision Computing 21(12), 1019–1026 (2003)Google Scholar
  9. 9.
    Nunes, J.C., Guyot, S., Deléchelle, E.: Texture analysis based on local analysis of the Bidimensional Empirical Mode Decomposition. Machine Vision and Applications 16(3), 932–8092 (2005)Google Scholar
  10. 10.
    Linderhed, A.: 2-D empirical mode decompositions in the spirit of image compression. In: Wavelet and Independent Component Analysis Applications IX, Orlando, Fla, USA. Proceedings of SPIE, vol. 4738, pp. 1–8 (2002)Google Scholar
  11. 11.
    Linderhed, A.: Compression by image empirical mode decomposition. In: IEEE International Conference on Image Processing (ICIP 2005), vol. 1, pp. 553–556 (2005)Google Scholar
  12. 12.
    Hariharan, H., Gribok, A., Abidi, M., Koschan, A.: Image Fusion and Enhancement via Empirical Mode Decomposition. Journal of Pattern Recognition Research 1(1), 16–32 (2006)Google Scholar
  13. 13.
    Sinclair, S., Pegram, G.G.S.: Empirical Mode Decomposition in 2-D space and time: a tool for space-time rainfall analysis and nowcasting. Hydrol. Earth Syst. Sci. Discuss. 2, 289–318 (2005)Google Scholar
  14. 14.
    Wan, J., Ren, L., Zhao, C.: Image Feature Extraction Based on the Two-Dimensional Empirical Mode Decomposition. In: 2008 Congress on Image and Signal Processing, vol. 1, pp. 627–631 (2008)Google Scholar
  15. 15.
    Taghia, J., Doostari, M.A., Taghia, J.: An Image Watermarking Method Based on Bidimensional Empirical Mode Decomposition. In: 2008 Congress on Image and Signal Processing, vol. 5, pp. 674–678 (2008)Google Scholar
  16. 16.
    Fauchereau, N., Sinclair, S., Pegram, G.: 2-D Empirical Mode Decomposition on the sphere, application to the spatial scales of surface temperature variations. Hydrol. Earth Syst. Sci. Discuss. 5, 405–435 (2008)Google Scholar
  17. 17.
    Nastar, C.: The image shape spectrum for image retrieval. Technical report, INRIA, No. 3206 (1997)Google Scholar
  18. 18.
    Nastar, C., Moghaddam, B., Pentland, A.: Flexible images: matching and recognition using learned deformations. Computer Vision and Image Understanding 65(2), 179–191 (1997)Google Scholar
  19. 19.
    Zhang, Z.B., Ma, S.L., Wu, D.Y.: The application of neural network and wavelet in human face illumination compensation. In: Wang, J., Liao, X.-F., Yi, Z. (eds.) ISNN 2005. LNCS, vol. 3497, pp. 828–835. Springer, Heidelberg (2005)Google Scholar
  20. 20.
    Feng, G.C., Yuen, P.C., Dai, D.Q.: Human face recognition using PCA on wavelet subband. Journal of Electronic Imaging 9(2), 226–233 (2000)Google Scholar
  21. 21.
    Ekenel, H.K., Sanker, B.: Multiresolution face recognition. Image and Vision Computing 23, 469–477 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Dan Zhang
    • 1
  • Yuan Yan Tang
    • 1
  1. 1.Department of Computer ScienceHong Kong Baptist UniversityHong Kong SARChina

Personalised recommendations