Fast Approximated Discriminative Common Vectors Using Rank-One SVD Updates

  • Francesc J. Ferri
  • Katerine Diaz-Chito
  • Wladimiro Diaz-Villanueva
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8228)


An efficient incremental approach to the discriminative common vector (DCV) method for dimensionality reduction and classification is presented. The proposal consists of a rank-one update along with an adaptive restriction on the rank of the null space which leads to an approximate but convenient solution. The algorithm can be implemented very efficiently in terms of matrix operations and space complexity, which enables its use in large-scale dynamic application domains. Deep comparative experimentation using publicly available high dimensional image datasets has been carried out in order to properly assess the proposed algorithm against several recent incremental formulations.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fukunaga, K.: Introduction to statistical pattern recognition, 2nd edn. Academic Press Professional, Inc., San Diego (1990)zbMATHGoogle Scholar
  2. 2.
    Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Trans. on Pattern Analysis and Machine Intelligence 19(7), 711–720 (1997)CrossRefGoogle Scholar
  3. 3.
    Wang, X., Tang, X.: A unified framework for subspace face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 26(9), 1222–1228 (2004)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Yu, H., Yang, J.: A direct lda algorithm for high-dimensional data – with application to face recognition. Pattern Recognition 34(10), 2067–2070 (2001)CrossRefzbMATHGoogle Scholar
  5. 5.
    Cevikalp, H., Neamtu, M., Wilkes, M., Barkana, A.: Discriminative common vectors for face recognition. IEEE Trans. Pattern Analysis and Machine Intelligence 27(1), 4–13 (2005)CrossRefGoogle Scholar
  6. 6.
    Ye, J.: Least squares linear discriminant analysis. In: ICML 2007: Proc. of the 24th Intl. Conf. on Machine Learning, pp. 1087–1093. ACM, New York (2007)Google Scholar
  7. 7.
    Chandrasekaran, S., Manjunath, B., Wang, Y., Winkler, J., Zhang, H.: An eigenspace update algorithm for image analysis. Graphical Models and Image Processing 59(5), 321–332 (1997)CrossRefGoogle Scholar
  8. 8.
    Ozawa, S., Toh, S.L., Abe, S., Pang, S., Kasabov, N.: Incremental learning of feature space and classifier for face recognition. Neur. Netw. 18(5), 575–584 (2005)CrossRefGoogle Scholar
  9. 9.
    Ye, J., Li, Q., Xiong, H., Park, H., Janardan, R., Kumar, V.: Idr/qr: An incremental dimension reduction algorithm via qr decomposition. IEEE Trans. on Knowl. and Data Eng. 17(9), 1208–1222 (2005)CrossRefGoogle Scholar
  10. 10.
    Kim, T.K., Wong, S.F., Stenger, B., Kittler, J., Cipolla, R.: Incremental linear discriminant analysis using sufficient spanning set approximations. In: Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–8 (2007)Google Scholar
  11. 11.
    Zhao, H., Yuen, P.C.: Incremental linear discriminant analysis for face recognition. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 38(1), 210–221 (2008)CrossRefzbMATHGoogle Scholar
  12. 12.
    Liu, L.P., Jiang, Y., Zhou, Z.H.: Least square incremental linear discriminant analysis. In: Intl Conf. on Data Mining, ICDM 2009, pp. 298–306 (2009)Google Scholar
  13. 13.
    Chu, D., Thye, G.S.: A new and fast implementation for null space based linear discriminant analysis. Pattern Recognition 43(4), 1373–1379 (2010)CrossRefzbMATHGoogle Scholar
  14. 14.
    Ferri, F.J., Diaz-Chito, K., Díaz-Villanueva, W.: Efficient dimensionality reduction on undersampled problems through incremental discriminative common vectors. In: Intl. Conf. on Data Mining Workshops, ICDMW 2010, pp. 1159–1166 (2010)Google Scholar
  15. 15.
    Lu, G.F., Zou, J., Wang, Y.: Incremental learning of discriminant common vectors for feature extraction. Appl. Math. and Computation 218(22), 11269–11278 (2012)CrossRefGoogle Scholar
  16. 16.
    Golub, G.H., Van Loan, C.F.: Matrix Computations (Johns Hopkins Studies in Mathematical Sciences), 3rd edn. The Johns Hopkins Univ. Press (1996)Google Scholar
  17. 17.
    Lu, G.F., Zheng, W.: Complexity-reduced implementations of complete and null-space-based linear discriminant analysis. Neural Networks (to appear, 2013)Google Scholar
  18. 18.
    Tamura, A., Zhao, Q.: Rough common vector: A new approach to face recognition. In: IEEE Intl. Conf. on Syst, Man and Cybernetics, pp. 2366–2371 (2007)Google Scholar
  19. 19.
    Brand, M.: Incremental singular value decomposition of uncertain data with missing values. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part I. LNCS, vol. 2350, pp. 707–720. Springer, Heidelberg (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Francesc J. Ferri
    • 1
  • Katerine Diaz-Chito
    • 1
    • 2
  • Wladimiro Diaz-Villanueva
    • 1
  1. 1.Departament d’InformàticaUniversitat de ValènciaSpain
  2. 2.Centre de Visió per ComputadorUniversitat Autònoma de BarcelonaSpain

Personalised recommendations