Relational Reinforcement Learning Applied to Appearance-Based Object Recognition

  • Klaus Häming
  • Gabriele Peters
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 43)


In this paper we propose an adaptive, self-learning system, which utilizes relational reinforcement learning (RRL), and apply it to a computer vision problem. A common problem in computer vision consists in the discrimination between similar objects which differ in salient features visible from distinct views only. Usually existing object recognition systems have to scan an object from a large number of views for a reliable discrimination. Optimization is achieved at most with heuristics to reduce the amount of computing time or to save storage space. We apply RRL in an appearance-based approach to the problem of discriminating similar objects, which are presented from arbitray views. We are able to rapidly learn scan paths for the objects and to reliably distinguish them from only a few recorded views. The appearance-based approach and the possibility to define states and actions of the RRL system with logical descriptions allow for a large reduction of the dimensionality of the state space and thus save storage and computing time.


Relational reinforcement learning computer vision appearance-based object recognition object discrimination 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Dzeroski, S., De Raedt, L., Driessens, K.: Relational reinforcement learning. In: Machine Learning, vol. 43, pp. 7–52 (2001)Google Scholar
  2. 2.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
  3. 3.
    Gartner, T., Driessens, K., Ramon, J.: Graph kernels and gaussian processes for relational reinforcement learning. In: Inductive Logic Programming, 13th International Conference, ILP (2003)Google Scholar
  4. 4.
    Driessens, K., Ramon, J.: Relational instance based regression for relational reinforcement learning. In: Proceedings of the Twentieth International Conference on Machine Learning, pp. 123–130 (2003)Google Scholar
  5. 5.
    Peters, G.: A Vision System for Interactive Object Learning. In: IEEE International Conference on Computer Vision Systems (ICVS 2006), New York, USA, January 5-7 (2006)Google Scholar
  6. 6.
    Lindeberg, T., Bretzner, L.: Real-time scale selection in hybrid multi-scale representations. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, pp. 148–163. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  7. 7.
    Harris, C., Stephens, M.: A Combined Corner and Edge Detector. In: 4th ALVEY Vision Conference, pp. 147–151 (1988)Google Scholar
  8. 8.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. International Journal of Computer Vision 60(1), 63–86 (2004)CrossRefGoogle Scholar
  9. 9.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  10. 10.
    Baumberg, A.: Reliable feature matching across widely separated views. In: CVPR 2001, p. 1774 (2000)Google Scholar
  11. 11.
    Beis, J., Lowe, D.: Shape indexing using approximate nearest-neighbor search in highdimensional spaces (1997)Google Scholar
  12. 12.
    Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Klaus Häming
    • 1
  • Gabriele Peters
    • 1
  1. 1.Computer Science, Visual ComputingUniversity of Applied Sciences and ArtsDortmundGermany

Personalised recommendations