A Biologically Motivated System for Unconstrained Online Learning of Visual Objects

  • Heiko Wersing
  • Stephan Kirstein
  • Michael Götting
  • Holger Brandl
  • Mark Dunn
  • Inna Mikhailova
  • Christian Goerick
  • Jochen Steil
  • Helge Ritter
  • Edgar Körner
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4132)

Abstract

We present a biologically motivated system for object recognition that is capable of online learning of several objects based on interaction with a human teacher. The training is unconstrained in the sense that arbitrary objects can be freely presented in front of a stereo camera system and labeled by speech input. The architecture unites biological principles such as appearance-based representation in topographical feature detection hierarchies and context-driven transfer between different levels of object memory. The learning is fully online and thus avoids an artificial separation of the interaction into training and test phases.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Steil, J.J., Wersing, H.: Recent trends in online learning for cognitive robotics. In: Proc. ESANN, pp. 77–87. Springer, Heidelberg (2006)Google Scholar
  2. 2.
    Wersing, H., Körner, E.: Learning optimized features for hierarchical models of invariant recognition. Neural Computation 15(7), 1559–1588 (2003)MATHCrossRefGoogle Scholar
  3. 3.
    Jebara, T., Pentland, A.: Action reaction learning: Automatic visual analysis and synthesis of interactive behaviour. In: Int. Conf. Computer Vision Systems (1999)Google Scholar
  4. 4.
    Garcia, L.M., Oliveira, A.A.F., Grupen, R.A., Wheeler, D.S., Fagg, A.H.: Tracing patterns and attention: Humanoid robot cognition. IEEE Intelligent Systems 15(4), 70–77 (2000)CrossRefGoogle Scholar
  5. 5.
    Steels, L., Kaplan, F.: AIBO’s first words. The social learning of language and meaning. Evolution of Communication 4(1), 3–32 (2001)CrossRefGoogle Scholar
  6. 6.
    Roy, D., Pentland, A.: Learning words from sights and sounds: a computational model. Cognitive Science 26(1), 113–146 (2002)CrossRefGoogle Scholar
  7. 7.
    Arsenio, A.: Developmental learning on a humanoid robot. In: Proc. Int. Joint Conf. Neur. Netw, Budapest, pp. 3167–3172 (2004)Google Scholar
  8. 8.
    Bekel, H., Bax, I., Heidemann, G., Ritter, H.: Adaptive computer vision: Online learning for object recognition. In: Proc. DAGM, Tuebingen, pp. 447–454 (2004)Google Scholar
  9. 9.
    Kirstein, S., Wersing, H., Körner, E.: Rapid online learning of objects in a biologically motivated recognition architecture. In: 27th Pattern Recognition Symposium DAGM, pp. 301–308. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Goerick, C., Wersing, H., Mikhailova, I., Dunn, M.: Peripersonal space and object recognition for humanoids. In: Proc. Humanoids Conf., Tsukuba (2005)Google Scholar
  11. 11.
    Götting, M., Steil, J., Wersing, H., Körner, E., Ritter, H.: Adaptive scenedependent filters in online learning environments. In: Proceedings Eur. Symp. Neur. Netw. ESANN, Bruges (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Heiko Wersing
    • 1
  • Stephan Kirstein
    • 1
  • Michael Götting
    • 2
  • Holger Brandl
    • 1
  • Mark Dunn
    • 1
  • Inna Mikhailova
    • 1
  • Christian Goerick
    • 1
  • Jochen Steil
    • 2
  • Helge Ritter
    • 2
  • Edgar Körner
    • 1
  1. 1.Honda Research Institute Europe GmbHOffenbach/MainGermany
  2. 2.Neuroinformatics Group, Faculty of TechnologyBielefeld UniversityBielefeldGermany

Personalised recommendations