A New Dictionary Learning Method for Kernel Matching Pursuit

  • Shuiping Gou
  • Qing Li
  • Xiangrong Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4223)


This paper presents a method for dictionary training of Kernel matching pursuits (KMP) [1] applied in large size data classification. This algorithm uses the existing fuzzy clustering technique to design function dictionary from a set of training data. The motivation is to enhance the local and quickly searching ability of basic matching pursuit algorithm. As a result, this method reduces computation complexity of matching pursuit algorithm. Simulation results show the proposed algorithm is efficacious for training large size pattern space.


Dictionary Learn Remote Sense Image Fuzzy Cluster Algorithm Pursuit Algorithm Redundant Dictionary 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pascal, V., Yoshua, B.: Kernel Matching Pursuit. Machine Learning 48, 165–187 (2002)MATHCrossRefGoogle Scholar
  2. 2.
    Mallat, S., Zhang, Z.: Matching Pursuits with Time-frequency Dictionaries. IEEE Trans. Signal Process. 12(41), 3397–3415 (1993)CrossRefGoogle Scholar
  3. 3.
    Davis, G.M., Mallat, S., Avelanedo, M.: Greedy adaptive approximations. J. Constr. Approx. 13, 57–98 (1997)MATHGoogle Scholar
  4. 4.
    Olshausen, B.A., Millman, K.J.: Learning sparse codes with a mixture of Gaussian prior. Advances in Neural Information Processing Systems 12 (2000)Google Scholar
  5. 5.
    Liu, Q.S., Wang, Q., Wu, L.: Size of the Dictionary in Matching Pursuit Algorithm. IEEE Transactions on Signal Processing 52, 3403–3408 (2004)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Popovici, V., Thiran, J.P.: Adaptive Kernel Matching Pursuit for Pattern Classification. Artificial Intelligence and Applications, 235–239, 094–411 (2004)Google Scholar
  7. 7.
    Yaghllbi, M., Rabiee, H.R., Ghanbari, M., Shamsollahi, M.B.: A new Image Texture Extraction Algorithm Based on Matching Pursuit Gabor Wavelets. In: 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 741–744 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Shuiping Gou
    • 1
  • Qing Li
    • 1
  • Xiangrong Zhang
    • 1
  1. 1.Institute of Intelligent Information ProcessingXidian UniversityXi’anChina

Personalised recommendations