Visual indexing with an attentive system

  • Ruggero Milanese
  • Jean-Marc Bost
  • Thierry Pun
Short Papers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 549)


In this paper we propose a new architecture for a general-purpose computer vision system whose design principles have been inspired by the study of human vision. Two important components are an object recognition module and a focus of attention module, respectively called “what” and “where” subsystems. The “what” subsystem is implemented through a set of agents that cooperate towards the interpretation of the image features. The “where” subsystem acts as a control module by detecting locations in the image which contain features that are likely to belong to interesting objects. A succession of attention windows is then generated for such locations and used to gate the parts of the image that are analyzed by the agents.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    I. Biederman, “Aspects and Extensions of a Theory of Human Image Understanding”, in: Z.W. Pylyshyn, ed., Computational Processes in Human Vision: An Interdisciplinary Perspective Ablex Publishing, 1988, pp. 370–428.Google Scholar
  2. [2]
    J.-M. Bost, “A Distributed Architecture for Visual Indexing”, University of Geneva, Computer Science Center, Technical Report in preparation.Google Scholar
  3. [3]
    R. Deriche, “Fast Algorithms for Low-Level Vision”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 12, No. 1, January 1990, pp. 78–87.Google Scholar
  4. [4]
    D.G. Lowe, “Organization of Smooth Image Curves at Multiple Scales”, Int. Journ. of Computer Vision, Vol. 3, 1989, pp. 119–130.Google Scholar
  5. [5]
    R. Milanese, “Focus of Attention in Human Vision: A Survey”, University of Geneva, Computer Science Center, A.I. and Vision Group, Technical Report 90-03, 1990.Google Scholar
  6. [6]
    R. Ohlander, K.E. Price and D.R. Reddy, “Picture Segmentation Using a Recursive Splitting Method”, Computer Graphics and Image Proc., Vol. 8, 1978, pp. 313–333.Google Scholar
  7. [7]
    T. Pun, “The Geneva Vision System: Modules, Integration, and Primal Access”, University of Geneva, Computer Science Center, A.I. and Vision Group, Technical Report 90-06, 1990.Google Scholar
  8. [8]
    J.K. Tsotsos, “Analyzing Vision at the Complexity Level”, Behavioral and Brain Sciences Vol 13 1990, pp. 423–469.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • Ruggero Milanese
    • 1
  • Jean-Marc Bost
    • 1
  • Thierry Pun
    • 1
  1. 1.Computer Science CentreUniversity of GenevaGenevaSwitzerland

Personalised recommendations