A Knowledge Based Approach to Industrial Scenes Analysis: Shadows and Reflexes Detection

  • M. Adimari
  • S. Masciangelo
  • L. Borghesi
  • G. Vernazza

Abstract

This paper describes a framework for detecting regions of special interest, like reflexes and shadows in industrial scenes. A new approach involving Artificial Intelligence techniques is tested; in fact procedural approaches exhibit several drawbacks such as lack of flexibility and of transparency in knowledge representation because knowledge is buried in code. A Knowledge-based system is proposed that is strictly interfaced with several low level image processing tools.

A brief description of the image processing modules is presented together with details concerning knowledge representation and the control strategy adopted. For a better understanding of the system performance and man-machine interface, a detailed analysis session is reported.

Keywords

Convolution Elon Undersampling 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Sueda, “An Expert System for Image Processing”, Image Technology and Information Display, vol. 17. no. 9. 19–22 (1985).Google Scholar
  2. [2]
    Sakane, Tamura, “Automatic Generation of Image Processing Program”, Proc. of CVPR, 189–192 (1985).Google Scholar
  3. [3]
    Wang, Srihari, “Object Recognition in Structured and Random Environments: Locating Address Block on Mail Pieces”, Vision and Signal Understanding (1986).Google Scholar
  4. [4]
    Wang, Srihari, “Object Recognition in Structured and Random Environments: Locating Address Block on Mail Pieces”, Vision and Signal Understanding (1986).Google Scholar
  5. [5]
    Kofka, “Principles of Gestalt Psychology”, Hartcourt, New York, Brace & World (1935).Google Scholar
  6. [6]
    Bhattacharyya, “A Simple Method of Resolution of a Distribution into Gaussian Components”, Biometrics 23. 115–135 (1967).CrossRefGoogle Scholar
  7. [7]
    Marr, Hildreth, “Theory of Edge Detection”, Proc. Royal Society London, B207, 187–217 (1980).CrossRefGoogle Scholar
  8. [8]
    J. F. Canny, “Finding Edges and Lines in Images”, MIT Report June 1983.Google Scholar
  9. [9]
    Del Canto, Fusconi, Piano, Roncarolo, “Uno strumento per la realizzazione di Sistemi Esperti e sua applicazione alla generazione dei cicli di lavorazione”, Relazione Interna ELSAG, Rei. SRC/125 (Marzo 1986 ).Google Scholar
  10. [10]
    Borghesi, Giuliano, Musso, Cablati, Ottonello,“Programmable Modified Systolic Array for Fast One-and-Two Dimensional Convolutions”, Journal Opt. Soc. Am. Vol. 3. N. 9. Sept.1986.Google Scholar

Copyright information

© Plenum Press, New York 1988

Authors and Affiliations

  • M. Adimari
    • 1
  • S. Masciangelo
    • 1
  • L. Borghesi
    • 1
  • G. Vernazza
    • 2
  1. 1.ELSAG S.p.A SRC Research DepartmentGenovaItaly
  2. 2.Biophysical and Electronic Engineering DepartmentUniversity of GenovaItaly

Personalised recommendations