Genetic search for object identification (original) (raw)

Abstract

We attack the problem of recognizing real, planar objects from two-dimensional, intensity images taken from arbitrary viewpoints using genetic algorithms. More specifically, we use genetic algorithms to search for a geometric mapping that brings subsets of points comprising the model and subsets of points comprising the scene into alignment. The genetic algorithm searches the image space and we compare different encodings and operators on a set of three increasingly complex scenes. Our preliminary results are promising with exact and near exact matches being found reliably and quickly.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. G. Bebis, M. Georgiopoulos, N. da Vitoria Lobo, and M. Shah. Learning affine transformations of the plane for model-based object recognition. In Proceedings of the 13th International Conference on Pattern Recognition (ICPR-96), pages 60–64, 1996.
    Google Scholar
  2. R. Chin and C. Dyer. Model-based recognition in robot vision. Computing Surveys, 18(1):67–108, 1986.
    Google Scholar
  3. Larry J. Eshelman. The chc adaptive search algorithm: How to have safe search when engaging in nontraditional genetic recombination. In Gregory J. E. Rawlins, editor, Proceedings of the Foundations of Genetic Algorithms Workshop — 1, San Mateo, CA, 1990. Morgan Kauffman.
    Google Scholar
  4. D. E. Goldberg. Genetic Algorithm in Search, Optimization, and Machine Learning. Addison-Wesley, Reading, MA, 1989.
    Google Scholar
  5. J. Holland. Adaptation In Natural and Artificial Systems. The University of Michigan Press, Ann Arbor, 1975.
    Google Scholar
  6. Y. Lamdan, J. Schwartz, and H. Wolfson. Affine invariant model-based object recognition. IEEE Transactions on Robotics and Automation, 6(5):578–589, 1990.
    Google Scholar
  7. Sushil J. Louis and Gong Li. Augmenting genetic algorithms with memory to solve traveling salesman problems. In P. Wang, editor, Proceedings of the Joint Conference on Information Sciences, pages 108–111. Duke University Press, 1997.
    Google Scholar
  8. F. Mokhtarian and A. Mackworth. A theory of multiscale, curvature-based shape representation for planar curves. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(8):789–805, 1992.
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Nevada, 89557, Reno
    Sushil J. Louis, George Bebis, Satish Uthiram & Yaakov Varol

Authors

  1. Sushil J. Louis
  2. George Bebis
  3. Satish Uthiram
  4. Yaakov Varol

Editor information

V. W. Porto N. Saravanan D. Waagen A. E. Eiben

Rights and permissions

© 1998 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Louis, S.J., Bebis, G., Uthiram, S., Varol, Y. (1998). Genetic search for object identification. In: Porto, V.W., Saravanan, N., Waagen, D., Eiben, A.E. (eds) Evolutionary Programming VII. EP 1998. Lecture Notes in Computer Science, vol 1447. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0040773

Download citation

Keywords

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.

Publish with us