Advertisement

Face Recognition under Variable Illumination by Weighted-Subband Edge Enhancement

  • Zhao-Rong Lai
  • Dao-Qing Dai
  • Chuan-Xian Ren
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 321)

Abstract

This article presents a novel weighted-subband method based on wavelet decomposition for face recognition under variable illumination. Different levels of subbands contain different features of the edge of a human face image. Through assigning a weight to each subband, we can strengthen the features beneficial to recognition, and weaken the features detrimental to recognition. To make the edge of human face stand out, a new histogram equalization and border smoothing method is implemented before weighted-subband edge enhancement. Experiments on the Extended YaleB Database show promising performance.

Keywords

face recognition weighted subbands edge enhancement wavelet decomposition division histogram equalization division border smoothing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chen, T., Zhou, X.S., Comaniciu, D., Huang, T.S.: Total variation models for variable lighting face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 28(9), 1519–1524 (2006)CrossRefGoogle Scholar
  2. 2.
    Chen, W., Er, M.J., Wu, S.: Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain. IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics 36(2), 458–466 (2006)CrossRefGoogle Scholar
  3. 3.
    Dai, D.Q., Yan, H.: Wavelets and face recognition. In: Delac, K., Grgic, M. (eds.) Face Recognition, pp. 59–74. I-Tech Education and Publishing (June 2007)Google Scholar
  4. 4.
    Daubechies, I.: Ten Lectures on Wavelets. Society for Industrial and Applied Mathematics (1992)Google Scholar
  5. 5.
    Ezoji, M., Faez, K.: Use of matrix polar decomposition for illumination-tolerant face recognition in discrete cosine transform domain. IET Image Processing 5, 25–35 (2011)CrossRefGoogle Scholar
  6. 6.
    Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: Illumination cone models for face recognition under variable lighting and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(6), 643–660 (2001)CrossRefGoogle Scholar
  7. 7.
    Lee, K.C., Ho, J., Kriegman, D.J.: Acquiring linear subspaces for face recognition under variable lighting. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(5), 1–14 (2005)CrossRefGoogle Scholar
  8. 8.
    Martínez, A.M., Benavente, R.: The ar face database. CVC Technical Report (24) (June 1998)Google Scholar
  9. 9.
    Pan, H., Xia, S.Y., Jin, L.Z., Xia, L.Z.: Illumination invariant face recognition based on improved local binary pattern. In: Proc. of the 30th Chinese Control Conf., July 2011, pp. 3268–3272 (2011)Google Scholar
  10. 10.
    Perez, C.A., Castillo, L.E.: Illumination compensation for face recognition by genetic optimization of the self-quotient image method. In: International Symposium on Optomechatronic Technologies, pp. 322–327 (2009)Google Scholar
  11. 11.
    Shan, S., Gao, W., Cao, B., Zhao, D.: Illumination normalization for robust face recognition against varying lighting conditions. In: Proc. IEEE Conf. Comput. Vision Pattern Recognit., vol. 1, pp. 19–25 (2003)Google Scholar
  12. 12.
    Shashua, A., Tammy, R.R.: The quotient image: Class-based re-rendering and recognition with varying illuminations. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(2), 129–139 (2001)CrossRefGoogle Scholar
  13. 13.
    Shermina, J.: Illumination invariant face recognition using discrete cosine transform and principal component analysis. In: Proc. of ICETECT, pp. 826–830 (2011)Google Scholar
  14. 14.
    Sim, T., Baker, S., Bsat, M.: The cmu pose, illumination, and expression database. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(12), 1615–1618 (2003)CrossRefGoogle Scholar
  15. 15.
    Wang, H., Li, S.Z., Wang, Y.: Face recognition under varying lighting conditions using self quotient image. In: Proc. of the Sixth IEEE International Conf. on Automatic Face and Gesture Recognit., pp. 819–824 (2004)Google Scholar
  16. 16.
    Xie, X., Zheng, W., Lai, J., Yuen, P.C.: Face illumination normalization on large and small scale features. In: Proc. IEEE Conf. Comput. Vision Pattern Recognit, pp. 1–8 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Zhao-Rong Lai
    • 1
  • Dao-Qing Dai
    • 1
  • Chuan-Xian Ren
    • 1
  1. 1.Center for Computer Vision and Department of MathematicsSun Yat-Sen UniversityGuangzhouChina

Personalised recommendations