Knowledge Integration for Machine Vision

  • A. Saroldi
Part of the International Centre for Mechanical Sciences book series (CISM, volume 307)


This paper emphasizes the importance of cooperation between knowledge sources for segmentation and interpretation of complex scenes.

A framework is then introduced to support qualitative and quantitative knowledge integration.

Experimental results, showing benefits of this approach, are presented.


Machine Vision Knowledge Source Knowledge Integration Complex Scene Region Segmentation 
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.
    Bolles & az Cain, “Recognizing and Locating Partially Visibile Objects: the Local-Feature-Focus Method”. Pugh, Robot Vision, 1983Google Scholar
  2. 2.
    Faugeras & Hebert, “The Representation, Recognition, and Locating of 3-D Objects”. International Journal of Robotics Research, Vol. 5, N. 3, 1986Google Scholar
  3. 3.
    Ohta, “Knowledge-based Interpretation of Outdoor Natural Color Scenes”. Pitman Advanced Publishing Program, 1985Google Scholar
  4. 4.
    Kanade, “Region Segmentation: Signal vs. Semantics”. International Conference on Pattern Recognition, 1978Google Scholar
  5. 5.
    Wallace et al. “First Results in Robot Road-Following” International Joint Conference on Artificial Intelligence, 1985Google Scholar
  6. 6.
    Davis et al. “Visual Navigation of Roadways”. Intelligent Autonomous Systems, 1986Google Scholar
  7. 7.
    Belknap Riseman & az Hanson, “The Information Fusion Problem and Rule-Based Hypotheses Applied to Complex Aggregation of Image Events”. IEEE Conference on Computer Vision and Pattern Recognition, 1986Google Scholar
  8. 8.
    Nazif & az Levine, “Low-Level Image Segmentation: an Expert System”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 6, N. 5, 1984Google Scholar
  9. 9.
    Monga & az Wrobel-Dautcourt, “Using Edges to Control Region Growing”. Reconaissance des Formes et Intelligence Artificielle, 1987Google Scholar
  10. 10.
    Lowe, “Visual Recognition from Spatial Correspondance and Perceptual Organization”. Proc. International Joint Conference on Artificial Intelligence, 1985.CrossRefGoogle Scholar
  11. 11.
    Tenenbaum & az Barrow, “Experiments in Interpretation- Guided Segmentation”. Artificial Intelligence, Vol. 8, 1977Google Scholar
  12. 12.
    Besl & az Jain, “Segmentation Through Variable-Order Surface Fitting”. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 10, N. 2, 1988Google Scholar
  13. 13.
    Saroldi, “Successive Groupings: Adding Knowledge to Improve Segmentation”. European Conference on Artificial Intelligence, 1988.Google Scholar

Copyright information

© Springer-Verlag Wien 1989

Authors and Affiliations

  • A. Saroldi
    • 1
  1. 1.Centro Ricerche FIATOrbassano (TO)Italy

Personalised recommendations