Cognitive Computation

, Volume 2, Issue 3, pp 160–164 | Cite as

Reducing Features Using Discriminative Common Vectors

  • Carlos M. Travieso
  • Marcos del Pozo
  • Miguel A. Ferrer
  • Jesús B. Alonso
Article

Abstract

A feature reduction system based on Discriminative Common Vector is presented and evaluated in this paper. The validation of this system was made with three databases, first one is DNA markers and the other two are The ORL Database of Face and The Yale Face Database. Moreover, a supervised classification system has been implemented with three different classifiers, achieving the best success rates with Support Vector Machines using Radial Basis Function kernel and a one-versus-all multiclass approach. The study shows clearly how our approach reduces the number of features and load times, keeping or improving the level of discrimination.

Keywords

Reduction features Discriminative Common Vector Machine learning Pattern Recognition 

Notes

Acknowledgments

This work was supported by the program “Programa José Castillejo 2008” from the Spanish Government under Grant JC2008-00398.

References

  1. 1.
    Zhi L, Shuixiu W, Xiaoqing W, Hao Y, Mingwen W, Jihua Y. Dimensional reduction based on independent component analysis for content based image retrieval. In: International joint conference on artificial intelligence; 2009. pp. 741–745.Google Scholar
  2. 2.
    Shiqing Z, Zhijin Z. Dimensionality reduction-based phoneme recognition. In: 9th international conference on signal processing; 2008. pp. 667–670.Google Scholar
  3. 3.
    Duda RO, Hart PE, Stork DG. Pattern classification. 2nd ed. New York: Wiley Interscience; 2000.Google Scholar
  4. 4.
    Cevikalp H, Neamtu M, Barkana A. The kernel common vector method: a novel nonlinear subspace classifier for pattern recognition. IEEE Trans Syst Man Cybern Part B. 2007;37(4):937–51.CrossRefGoogle Scholar
  5. 5.
    Cevikalp H, Neamtu M, Wilkes M. Discriminative Common Vector method with kernels. IEEE Trans Neural Netw. 2006;17(6):1832–8.CrossRefGoogle Scholar
  6. 6.
    Cristianini N, Shawe-Taylor J. An introduction to support vector machines. Cambridge: Cambridge University Press; 2000.Google Scholar
  7. 7.
    Joachims T. SVM_light support vector machine. Department of Computer Science, Cornell University, Version: 6.02. http://svmlight.joachims.org/ (2009). Last visit: 30 Mar 2009.
  8. 8.
    Mora-Urpí J, Arroyo C. Sobre origen y diversidad en pejibaye. Serie Técnica Pejibaye (Guilielma). Technical report, Ed. University of Costa Rica; 1996. Vol. 5, No 1, pp. 18–25.Google Scholar
  9. 9.
    Ferrer M, Eguiarte LE, Montana C. Genetic structure and outcrossing rates in Flourensia cernua (Asteraceae) growing at different densities in the South-western Chihuahuan Desert. Ann Bot. 2004;94:419–26.CrossRefPubMedGoogle Scholar
  10. 10.
    http://www.uk.research.att.com/facedatabase.html (2009). Last visit: 30 Mar 2009.
  11. 11.
    http://cvc.yale.edu (2009). Last visit: 30 Mar 2009.
  12. 12.
    Mitchell TM. Machine learning. New York: McGraw-Hill; 1997.Google Scholar
  13. 13.
    Bishop CM. Neural networks for pattern recognition. Oxford: Oxford University Press; 1996.Google Scholar
  14. 14.
    Travieso CM, Botella P, Alonso JB, Ferrer MA. Discriminative Common Vector for face identification. In: 43rd IEEE international carnahan conference on security technology; 2009. pp. 134–138.Google Scholar
  15. 15.
    Briceño JC, Travieso CM, Ferrer MA, Alonso JB, Vargas F. Off-line signature recognition based on contour parameterization. In: 12th international conference on computer aided system theory; 2009. pp. 118–120.Google Scholar
  16. 16.
    Gonzalez RC, Wood RE. Digital image processing. Reading: Addison-Wesley; 2002.Google Scholar
  17. 17.
    Hyvärinen A, Karhunen J, Oja E. Independent component analysis. New York: Wiley; 2001.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Carlos M. Travieso
    • 1
  • Marcos del Pozo
    • 1
  • Miguel A. Ferrer
    • 1
  • Jesús B. Alonso
    • 1
  1. 1.Signals and Communications Department, IDeTICUniversity of Las Palmas de Gran CanariaLas Palmas de Gran CanáriaSpain

Personalised recommendations