Skip to main content

Coevolutionary Feature Learning for Object Recognition

  • Conference paper
  • First Online:
Machine Learning and Data Mining in Pattern Recognition (MLDM 2003)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 2734))

  • 1438 Accesses

Abstract

In this paper, we consider the task of automatic synthesis/learning of pattern recognition systems. In particular, a method is proposed that, given exclusively training raster images, synthesizes complete feature-based recognition system. The proposed approach is general and does not require any assumptions concerning training data and application domain. Its novelty consists in procedural representation of features for recognition and utilization of coevolutionary computation for their synthesis. The paper describes the synthesis algorithm, outlines the architecture of the synthesized system, provides firm rationale for its design, and evaluates it experimentally on the real-world task of target recognition in synthetic aperture radar (SAR) imagery.

On a temporary leave from Poznań University of Technology, Poznań, Poland.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Banzhaf, W., Nordin, P., Keller, R., Francone F.: Genetic Programming. An Introduction. On the automatic Evolution of Computer Programs and its Application. Morgan Kaufmann, San Francisco, Calif. (1998)

    Google Scholar 

  2. Bhanu, B., Krawiec, K.: Coevolutionary Construction of Features for Transformation of Representation in Machine Learning. Proc. Workshop on Coevolution (GECCO 2002), AAAI Press, New York (2002) 249–254

    Google Scholar 

  3. Breiman, L.: Bagging predictors. Machine Learning 24 (1996) 123–140

    MATH  MathSciNet  Google Scholar 

  4. Draper, B., Hanson, A., Riseman, E.: Knowledge-Directed Vision: Control, Learning and Integration. Proc. IEEE 84 (1996) 1625–1637

    Article  Google Scholar 

  5. Luke, S.: ECJ Evolutionary Computation System. http://www.cs.umd.edu/projects/plus/ec/ecj/ (2001)

    Google Scholar 

  6. Luke, S., Wiegand, R.P.: When Coevolutionary Algorithms Exhibit Evolutionary Dynamic. Proc. Workshop on Coevolution (GECCO 2002), AAAI Press, New York, N.Y. (2002) 236–241

    Google Scholar 

  7. Matheus, C.J.: A Constructive Induction Framework. Proc. 6th Int’l Workshop on Machine Learning, Ithaca, New York (1989) 474–475

    Google Scholar 

  8. Peng, J., Bhanu, B.: Closed-Loop Object Recognition Using Reinforcement Learning. IEEE Trans. on PAMI 20 (1998) 139–154

    Google Scholar 

  9. Platt, J.: Fast Training of Support Vector Machines using Sequential Minimal Optimization. Advances in Kernel Methods — Support Vector Learning, B. Schölkopf, C. Burges, and A. Smola, eds., MIT Press, Cambridge, Mass. (1998)

    Google Scholar 

  10. Potter, M.A., De Jong, K.A.: Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents. Evolutionary Computation 8 (2000) 1–29

    Article  Google Scholar 

  11. Ross, T., Worell, S., Velten, V., Mossing, J., Bryant, M.: Standard SAR ATR Evaluation Experiments using the MSTAR Public Release Data Set. SPIE Proc.: Algorithms for Synthetic Aperture Radar Imagery V, Vol. 3370, Orlando, FL (1998) 566–573

    Google Scholar 

  12. Segen, J.: GEST: A Learning Computer Vision System that Recognizes Hand Gestures. Machine Learning. A Multistrategy Approach. Volume IV, Michalski, R.S., Tecuci, G., eds., Morgan Kaufmann, San Francisco, Calif. (1994) 621–634

    Google Scholar 

  13. Teller, A., Veloso, M.: A Controlled Experiment: Evolution for Learning Difficult Image Classification. Proc. 7th Portuguese Conference on Artificial Intelligence, Springer Verlag, Berlin, Germany (1995) 165–176

    Google Scholar 

  14. Wiegand, R.P., Liles, W.C., De Jong, K.A.: An Empirical Analysis of Collaboration Methods in Cooperative Coevolutionary Algorithms. Proc. Genetic and Evolutionary Computation Conference, Morgan Kaufmann, San Francisco, Calif. (2001) 1235–1242

    Google Scholar 

  15. Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations. Morgan Kaufmann, San Francisco, Calif. (1999)

    Google Scholar 

  16. Wolpert, D., Macready, W.G.: No Free Lunch Theorems for Search. Tech. Report SFI-TR-95-010, The Santa Fe Institute (1995)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Krawiec, K., Bhanu, B. (2003). Coevolutionary Feature Learning for Object Recognition. In: Perner, P., Rosenfeld, A. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2003. Lecture Notes in Computer Science, vol 2734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45065-3_20

Download citation

  • DOI: https://doi.org/10.1007/3-540-45065-3_20

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-40504-7

  • Online ISBN: 978-3-540-45065-8

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics