An Evolutionary Approach for Ontology Driven Image Interpretation

  • Germain Forestier
  • Sébastien Derivaux
  • Cédric Wemmert
  • Pierre Gançarski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4974)


Image mining and interpretation is a quite complex process. In this article, we propose to model expert knowledge on objects present in an image through an ontology. This ontology will be used to drive a segmentation process by an evolutionary approach. This method uses a genetic algorithm to find segmentation parameters which allow to identify in the image the objects described by the expert in the ontology. The fitness function of the genetic algorithm uses the ontology to evaluate the segmentation. This approach does not needs examples and enables to reduce the semantic gap between automatic interpretation of images and expert knowledge.


Genetic Algorithm Segmentation Algorithm Evolutionary Approach Watershed Segmentation Automatic Interpretation 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Vincent, L., Soille, P.: Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Pattern Analysis and Machine Intelligence 13(6), 583–598 (1991)CrossRefGoogle Scholar
  2. 2.
    Mueller, M., Segl, K., Kaufmann, H.: Edge- and region-based segmentation technique for the extraction of large, man-madeobjects in high-resolution satellite imagery. Pattern Recognition 37(8), 1619–1628 (2004)CrossRefGoogle Scholar
  3. 3.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Professional, Reading (1989)zbMATHGoogle Scholar
  4. 4.
    Pignalberi, G., Cucchiara, R., Cinque, L., Levialdi, S.: Tuning range image segmentation by genetic algorithm. EURASIP Journal on Applied Signal Processing 8, 780–790 (2003)CrossRefGoogle Scholar
  5. 5.
    Bhanu, B., Lee, S., Das, S.: Adaptive image segmentation using genetic and hybrid search methods. IEEE Transactions on Aerospace and Electronic Systems 31(4), 1268–1291 (1995)CrossRefGoogle Scholar
  6. 6.
    Song, A., Ciesielski, V.: Fast texture segmentation using genetic programming. IEEE Congress on Evolutionary Computation 3, 2126–2133 (2003)CrossRefGoogle Scholar
  7. 7.
    Feitosa, R.Q., Costa, G.A., Cazes, T.B., B., F.: A genetic approach for the automatic adaptation of segmentation parameters. In: International Conference on Object-based Image Analysis (2006)Google Scholar
  8. 8.
    Haris, K., Efstradiadis, S.N., Maglaveras, N., Katsaggelos, A.K.: Hybrid image segmentation using watersheds and fast region merging. IEEE Transaction On Image Processing 7(12), 1684–1699 (1998)CrossRefGoogle Scholar
  9. 9.
    Najman, L., Schmitt, M.: Geodesic saliency of watershed contours and hierarchical segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(12), 1163–1173 (1996)CrossRefGoogle Scholar
  10. 10.
    Durand, N., Derivaux, S., Forestier, G., Wemmert, C., Gancarski, P., Boussaid, D., O., Puissant, A.: Ontology-based object recognition for remote sensing image interpretation. In: IEEE International Conference on Tools with Artificial Intelligence, Patras, Greece, pp. 472–479 (2007)Google Scholar
  11. 11.
    Sheeren, D., Puissant, A., Weber, C., Gancarski, P., Wemmert, C.: Deriving classification rules from multiple sensed urban data with data mining. In: 1rst Workshop of the EARSel Special Interest Group Urban Remote Sensing, Berlin (2006)Google Scholar
  12. 12.
    Janssen, L., Molenaar, M.: Terrain objects, their dynamics and their monitoring by the integration of gis and remote sensing.  33, 749–758 (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Germain Forestier
    • 1
  • Sébastien Derivaux
    • 1
  • Cédric Wemmert
    • 1
  • Pierre Gançarski
    • 1
  1. 1.LSIIT - CNRSUniversity Louis Pasteur - UMR 7005IllkirchFrance

Personalised recommendations