Skip to main content

Cooperative Coevolution of Image Feature Construction and Object Detection

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNCS,volume 3242)

Abstract

Most previous approaches using genetic programming tosolve object detection tasks have evolved classifiers which are basically arithmetic expressions using pre-extracted local pixel statistics as terminals. The pixel statistics chosen are often highly general, meaning that the classifier cannot exploit useful aspects of the domain, or are too domain specific and overfit. This work presents a system whereby a feature construction stage is simultaneously coevolved along side the GP object detectors. Effectively, the system learns both stages of the visual process simultaneously. This work shows initial results of using this technique on both artificial and natual images and shows how it can quickly adapt to form general solutions to difficult scale and rotation invariant problems.

Keywords

  • Object Detection
  • Feature Construction
  • Feature Subset Selection
  • Linear Genetic Programming
  • Cooperative Coevolution

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.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-540-30217-9_91
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   74.99
Price excludes VAT (USA)
  • ISBN: 978-3-540-30217-9
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge (1992)

    MATH  Google Scholar 

  2. Tackett, W.A.: Genetic programming for feature discovery and image discrimination. In: Proceedings of the 5th International Conference on Genetic Algorithms, ICGA 1993, pp. 303–309. Morgan Kaufmann, San Francisco (1994)

    Google Scholar 

  3. Daida, J.M., Bersano-Begey, T.F., Ross, S.J., Vesecky, J.F.: Computer-assisted design of image classification algorithms: Dynamic and static fitness evaluations in a scaffolded genetic programming environment. In: Koza, J.R., Goldberg, D.E., Fogel, D.B., Riolo, R.L. (eds.) Proceedings of the First Annual Conference on Genetic Programming 1996, Stanford University, CA, USA, pp. 279–284. MIT Press, Cambridge (1996)

    Google Scholar 

  4. Howard, D., Roberts, S.C.: Evolving object detectors for infrared imagery: a comparison of texture analysis against simple statistics. In: Miettinen, K., Mäkelä, M.M., Neittaanmäki, P., Periaux, J. (eds.) Evolutionary Algorithms in Engineering and Computer Science, pp. 79–86. John Wiley & Sons, Chichester (1999)

    Google Scholar 

  5. Howard, D., Roberts, S.C., Brankin, R.: Target detection in imagery by genetic programming. Advances in Engineering Software 30, 303–311 (1999)

    CrossRef  Google Scholar 

  6. Winkeler, J.F., Manjunath, B.S.: Genetic programming for object detection. In: Koza, J.R., et al. (eds.) Proceedings of the Second Annual Conference on Genetic Programming 1997, pp. 330–335. Morgan Kaufmann, San Francisco (1997)

    Google Scholar 

  7. Ross, B.J., Fueten, F., Yashkir, D.Y.: Edge detection of petrographic images using genetic programming. In: Proceedings of Genetic and Evolutionary Computation GECCO 2000, pp. 658–665. Morgan Kaufmann, San Francisco (2000)

    Google Scholar 

  8. Zhang, M.: A Domain Independent Approach to 2d Object Detection Based on Neural Networks and Genetic Paradigms. PhD thesis, Department of Computer Science, RMIT University, Melbourne, Victoria, Australia (2000)

    Google Scholar 

  9. Zhang, M., Bhowan, U.: Program size and pixel statistics in genetic programming for object detection. In: Raidl, G.R., Cagnoni, S., Branke, J., Corne, D.W., Drechsler, R., Jin, Y., Johnson, C.G., Machado, P., Marchiori, E., Rothlauf, F., Smith, G.D., Squillero, G. (eds.) EvoWorkshops 2004. LNCS, vol. 3005, pp. 377–386. Springer, Heidelberg (2004)

    Google Scholar 

  10. Potter, M.A., De Jong, K.A.: A cooperative coevolutionary approach to function optimization. In: Proceedings of the Third Conference on Parallel Problem Solving from Nature. LNCS, pp. 249–257. Springer, Heidelberg (1994)

    Google Scholar 

  11. Motoda, H., Liu, H.: Feature selection, extraction and construction. In: Towards the Foundation of DataMiningWorkshop, Sixth Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2002), Taipei, Taiwan, pp. 67–72 (2002)

    Google Scholar 

  12. Bala, J., Jong, K.D., Huang, J., Vafaie, H., Wechsler, H.: Using learning to facilitate the evolution of features for recognizing visual convepts. Evolutionary Computation 4 (1997)

    Google Scholar 

  13. Bala, J., Jong, K.D., Huang, J., Vafaie, H., Wechsler, H.: Visual routine for eye detection using hybrid genetic architectures. In: Bolle, R., Dickmanns, E. (eds.) Proceedings of the International Conference on Pattern Recognition, Vienna, Austria, vol. 3, pp. 606–610. IEEE, Los Alamitos (1996)

    CrossRef  Google Scholar 

  14. Krawiec, K., Bhanu, B.: Coevolution and linear genetic programming for visual learning. In: Cantú-Paz, E., Foster, J.A., Deb, K., Davis, L., Roy, R., O’Reilly, U.-M., Beyer, H.-G., Kendall, G., Wilson, S.W., Harman, M., Wegener, J., Dasgupta, D., Potter, M.A., Schultz, A., Dowsland, K.A., Jonoska, N., Miller, J., Standish, R.K. (eds.) GECCO 2003. LNCS, vol. 2723, pp. 332–343. Springer, Heidelberg (2003)

    CrossRef  Google Scholar 

  15. Lin, Y., Bhanu, B.: Learning features for object recognition. In: Cantú-Paz, E., Foster, J.A., Deb, K., Davis, L., Roy, R., O’Reilly, U.-M., Beyer, H.-G., Kendall, G., Wilson, S.W., Harman, M., Wegener, J., Dasgupta, D., Potter, M.A., Schultz, A., Dowsland, K.A., Jonoska, N., Miller, J., Standish, R.K. (eds.) GECCO 2003. LNCS, vol. 2724, pp. 2227–2239. Springer, Heidelberg (2003)

    CrossRef  Google Scholar 

  16. Guardo, A., Gal, C.L., Lux, A.: Evolving visual features and detectors. In: da Fontoura, et al. (eds.) International Symposium on Computer Graphics, Image Processing, and Vision (SIGGRAPI 1998), Rio De Janeiro, Brazil, pp. 246–253. IEEE, Los Alamitos (1998)

    Google Scholar 

  17. Ahluwalia, M., Bull, L.: Coevolving functions in genetic programming. Journal of Systems Architecture 47, 573–585 (2001)

    CrossRef  Google Scholar 

  18. Ahluwalia, M., Bell, L., Fogarty, T.C.: Co-evolving functions in genetic programming: A comparison in ADF selection strategies. In: Koza, J.R., Deb, K., Dorigo, M., Fogel, D.B., Garzon, M., Iba, H., Riolo, R.L. (eds.) Proceedings of the Second Annual Conference on Genetic Programming 1997, pp. 3–8. Morgan Kaufmann, San Francisco (1997)

    Google Scholar 

  19. Wiegand, R.P., Liles, W.C., Jong, K.A.D.: An empirical analysis of collaboration methods in cooperative coevolutionary algorithms. In: Raidl, G.R., Cagnoni, S., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), Berlin. LNCS, vol. 2611, pp. 1235–1245. Morgan Kaufmann, San Francisco (2001)

    Google Scholar 

  20. Viola, P., Jones, M.J.: Robust real-time face detection. International Journal of Computer Vision 57, 137–154 (2004)

    CrossRef  Google Scholar 

  21. Gathercole, C., Ross, P.: Dynamic training subset selection for supervised learning in genetic programming. In: Davidor, Y., Männer, R., Schwefel, H.-P. (eds.) PPSN 1994. LNCS, vol. 866, pp. 312–321. Springer, Heidelberg (1994)

    Google Scholar 

  22. Poli, R.: A simple but theoretically-motivated method to control bloat in genetic programming. In: Ryan, C., Soule, T., Keijzer, M., Tsang, E.P.K., Poli, R., Costa, E. (eds.) EuroGP 2003. LNCS, vol. 2610, pp. 200–210. Springer, Heidelberg (2003)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Roberts, M.E., Claridge, E. (2004). Cooperative Coevolution of Image Feature Construction and Object Detection. In: , et al. Parallel Problem Solving from Nature - PPSN VIII. PPSN 2004. Lecture Notes in Computer Science, vol 3242. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30217-9_91

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-30217-9_91

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-23092-2

  • Online ISBN: 978-3-540-30217-9

  • eBook Packages: Springer Book Archive