Skip to main content
SpringerLink
Log in
Book cover

International Conference on Parallel Problem Solving from Nature

PPSN 2004: Parallel Problem Solving from Nature - PPSN VIII pp 902–911Cite as

Cooperative Coevolution of Image Feature Construction and Object Detection

  • Conference paper

Part of the book series: Lecture Notes in Computer Science ((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.

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   74.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

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)

    Article  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)

    Chapter  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)

    Chapter  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)

    Chapter  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)

    Article  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)

    Article  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)

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Computer Science, University of Birmingham, B15 2TT, UK

    Mark E. Roberts & Ela Claridge

Authors
  1. Mark E. Roberts
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ela Claridge
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Xin Yao

  2. Automated Scheduling, Optimisation and Planning Group, School of Computer Science & IT, University of Nottingham, NG8 1BB, Nottingham, UK

    Edmund K. Burke

  3. Intelligent Systems Group Department of Computer Science and Artificial Intelligence, University of the Basque Country, Paseo Manuel de Lardizábal 1, 20018, San Sebastian, Donostia, Spain

    José A. Lozano

  4. University of the West of England, Bristol, United Kingdom

    Jim Smith

  5. GeNeura Team, Depto. Arquitectura y Tecnología de Computadores, Universidad de Granada, Spain

    Juan Julián Merelo-Guervós

  6. School of Computer Science, The University of Birmingham, B15 1TT, Edgbaston, Birmingham, UK

    John A. Bullinaria

  7. School of Computer Science, University of Birmingham, B15 2TT, Birmingham, Great Britain

    Jonathan E. Rowe

  8. School of Computer Science, University of Birmingham, United Kingdom

    Peter Tiňo

  9. School of Computer Science, The University of Birmingham, B15 2TT, Birmingham, UK

    Ata Kabán

  10. Faculty of Computer Science, Dortmund University of Technology, 44221, Dortmund, Germany

    Hans-Paul Schwefel

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: Yao, X., 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

Publish with us

Policies and ethics

Search

Navigation