MEANING AND EFFICIENCY IN THE GESTALT-SYSTEM - An Approach to Automatic Image Description

E. Michaelsen, M. Arens, L. J. Doktorski, P. Ding, U. Stilla

Abstract

Knowledge-based image recognition and description systems have to balance soundness versus efficiency. For mining purposes in particular a theory of meaning – i.e. formal semantic or ontology – has to be given. However, efficiency is also most important for practicability. This contribution uses production systems. The semantics are analysed by means of confluence. Productions are used in an accumulating way instead of reductive. The interpretation scheme given allows breaking reasoning at any time with an approximate interpretation as result. Two example systems using this interpreter are discussed.

References

  1. Christensen, H. I., Nagel, H.-H. (eds), 2006.Cognitive Vision Systems, Springer, Berlin LNCS 3948, pp. 183- 198
  2. Draper, B., Collins, R., Brolio, J., Hanson, A., Riseman, E., 1989. The Schema System, IJCV, Vol. 2 pp. 209- 250.
  3. Janzen, M., 1988. confluent String Rewriting, Springer, Berlin.
  4. Lütjen, K., 1986. Ein Blackboard-basiertes Produktionssystem für die automatische Bildauswertung. In: Hartmann, G. (ed.) Mustererkennung 1986, DAGM 1986, Springer, Berlin, Informatik Fachberichte 125, pp. 164-168.
  5. Lütjen, K., 2001. Systeme und Verfahren für strukturelle Musteranalysen mit Produktionsnetzen, Diss., Univ. of Karlsruhe, institute for communications engineering, ISSN: 1433-3821.
  6. Matsuyama, T., Hwang, V. S.-S., 1990. Sigma a knowledge-based image understanding system, Plenum Press, New York.
  7. Michaelsen E., Stilla U., 2002. Probabilistic Decisions in Production Nets: An Example from Vehicle Recognition. In: Caelli T., Amin A., Duin R. P. W., Kamel M., Ridder D. de (eds). Structural, Syntactic and Statistical Pattern Recognition SSPR/SPR 2002, Springer, Berlin, LNCS 2396, pp. 225-233.
  8. Michaelsen E., Soergel U., Thoennessen U., 2006a. Perceptual Grouping in Automatic Detection of ManMade Structure in high resolution SAR data. Pattern Recognition Letters, Vol. 27, No. 4, pp. 218-225.
  9. Michaelsen, E., von Hansen, W., Kirchhof, M., Meidow, J., Stilla U., 2006b. Estimating the Essential Matrix: GOODSAC versus RANSAC. ISPRS Symposium on Photogrammetric Computer Vision (PCV 2006).
  10. Niemann, H., 1989. Pattern Analysis and Understanding, Springer, Berlin.
  11. Nister, D., 2004. An Efficient Solution to the Five Point Relative Pose Problem, IEEE PAMI, vol. 26, no. 6, pp. 756-769.
  12. Sagerer, G., 1982. Darstellung und Nutzung von Expertenwissen für ein Bildanalysesystem, Diss., Univ. of Erlangen-Nürnberg, Springer, Inormatik Fachberichte 104, Berlin.
  13. Stilla U., Michaelsen E., 1997. Semantic modelling of man-made objects by production nets. In: Gruen A., Baltsavias EP., Henricsson O. (eds). Automatic extraction of man-made objects fromaerial and space images (II). Birkhäuser, Basel, pp. 43-52.
Download


Paper Citation


in Harvard Style

Michaelsen E., Arens M., J. Doktorski L., Ding P. and Stilla U. (2007). MEANING AND EFFICIENCY IN THE GESTALT-SYSTEM - An Approach to Automatic Image Description . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Mathematical and Linguistic Techniques for Image Mining, (VISAPP 2007) ISBN 978-972-8865-75-7, pages 188-193. DOI: 10.5220/0002070601880193


in Bibtex Style

@conference{mathematical and linguistic techniques for image mining07,
author={E. Michaelsen and M. Arens and L. J. Doktorski and P. Ding and U. Stilla},
title={MEANING AND EFFICIENCY IN THE GESTALT-SYSTEM - An Approach to Automatic Image Description},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Mathematical and Linguistic Techniques for Image Mining, (VISAPP 2007)},
year={2007},
pages={188-193},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002070601880193},
isbn={978-972-8865-75-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 3: Mathematical and Linguistic Techniques for Image Mining, (VISAPP 2007)
TI - MEANING AND EFFICIENCY IN THE GESTALT-SYSTEM - An Approach to Automatic Image Description
SN - 978-972-8865-75-7
AU - Michaelsen E.
AU - Arens M.
AU - J. Doktorski L.
AU - Ding P.
AU - Stilla U.
PY - 2007
SP - 188
EP - 193
DO - 10.5220/0002070601880193