A Comparative Study of Linear Discriminant and Linear Regression Based Methods for Expression Invariant Face Recognition

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 264)

Abstract

In the literature, the performance of Fisher’s Linear Discriminant (FLD), Linear Regression (LR) and their variants is found to be satisfactory for face recognition under illumination variation. However, face recognition under expression variation is also a challenging problem and has received little attention. To determine suitable method for expression invariant face recognition, in this paper, we have investigated several methods which are variants of FLD or LR. Extensive experiments are performed on three publicly available datasets namely ORL, JAFFE and FEEDTUM with varying number of training images per person. The performance is evaluated in terms of average classification accuracy. Experimental results demonstrate superior performance of Enhanced FLD (EFLD) method in comparison to other methods on all the three datasets. Statistical ranking used for comparison of methods strengthen the empirical findings.

Keywords

scatter expression comparison ranking 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    An, G.Y., Ruan, Q.Q.: A novel mathematical model for enhanced Fishers linear discriminant and its application to face recognition. In: The 18th Int. Conf. on Patt. Rec (ICPR 2006), pp. 524–527 (2006)Google Scholar
  2. 2.
    An, S., Liu, W., Venkatesh, S.: Face Recognition Using Kernel Ridge Regression. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–7 (2007)Google Scholar
  3. 3.
    Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997)CrossRefGoogle Scholar
  4. 4.
    Chai, X., Shan, S., Chen, X., Gao, W.: Locally linear regression for pose invariant face recognition. IEEE Trans. Image Proc. 16, 1716–1725 (2007)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Cordiner, A.: Illumination invariant face detection. University of Wollongong, MComSc thesis (2009)Google Scholar
  6. 6.
    Eisert, P., Girod, B.: Analysing facial expressions for virtual conferencing. IEEE Trans. Comp. Graph. and Appl. 18, 70–78 (1998)CrossRefGoogle Scholar
  7. 7.
    Fisher, R.A.: The use of multiple measures in taxonomic problems. Ann. Eugenics 7, 179–188 (1936)CrossRefGoogle Scholar
  8. 8.
    Hsieh, C.K., Lai, S.H.: Expression invariant face recognition with constrained optical flow warping. IEEE Trans. Multimedia 11, 600–610 (2009)CrossRefGoogle Scholar
  9. 9.
    Lyons, M.L., Akamatsu, S., Kamachi, M., Gyoba, J.: Coding facial expressions with gabor wavelets. In: IEEE Int. Conf. Auto. Face and Gest. Rec., Japan, pp. 200–205 (1998)Google Scholar
  10. 10.
    Naseem, I., Togneri, I., Bennamoun, M.: Linear regression for face recognition. IEEE Tran. Pattern Anal. Machine Intell. 32, 2106–2112 (2010)CrossRefGoogle Scholar
  11. 11.
    Naseem, I., Togneri, I., Bennamoun, M.: Robust regression for face recognition. Pattern Recognition 45, 104–118 (2012)CrossRefGoogle Scholar
  12. 12.
    Prabhakar, S., Pankanti, S., Jain, A.K.: Biometric recognition: security and privacy concerns. IEEE Security and Privacy 1, 33–42 (2003)CrossRefGoogle Scholar
  13. 13.
    Samaria, F., Harter, A.: Parameterization of a stochastic model for human face identification. In: Proc. 2nd IEEE Workshop on Appl. of Comp. Vision, pp. 138–142 (1994)Google Scholar
  14. 14.
    Tsai, P.H., Jan, T.: Expression-invariant face recognition system using subspace model analysis. IEEE Int. Conf. on Systems, Man and Cyber. 2, 1712–1717 (2005)Google Scholar
  15. 15.
    Turk, M., Pentland, A.: Eigenfaces for recognition. J. Cogn. Neuro. 3, 71–86 (1991)CrossRefGoogle Scholar
  16. 16.
    Wallhoff, F.: Facial expressions and emotion database. Technische Universitt Mnchen (2006), http://www.mmk.ei.tum.de/waf/fgnet/feedtum.html
  17. 17.
    Zhang, T., Fang, B., Tang, Y.Y., Shang, Z., Xu, B.: Generalized discriminant analysis: a matrix exponential approach. IEEE Trans. Systems, Man, and Cybernetics, Part B: Cybernetics 40, 186–197 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringNational Institute of TechnologyUttarakhandIndia
  2. 2.School of Computer & System SciencesJawaharlal Nehru UniversityNew DelhiIndia
  3. 3.S. S. College of Business StudiesUniversity of DelhiDelhiIndia

Personalised recommendations