Pulsed neural networks and perceptive grouping

  • Dominique Derou
  • Laurent Herault
Recognition II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)


Tracking elementary features and coherently grouping them is an important problem in computer vision and a real challenging feature extraction problem. Perceptual grouping techniques can be applied to some feature tracking problems. Such an approach is presented in this paper. Moreover we show how a perceptual grouping problem can be expressed as a global optimization problem. In order to solve it, we devise an original neural network, called pulsed neural network. The specific application concerned here is particle tracking velocimetry in fluid mechanics.


Particle Tracking Perceptual Grouping Global Optimization Problem Particle Tracking Velocimetry Potential Feature 
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.


  1. 1.
    R.J. Adrian. Particle-imaging techniques for experimental fluid mechanics. Annual Review of Fluid Mechanics, 23:261–304, 1991.Google Scholar
  2. 2.
    J.C. Agui and J. Jimenez. On the performance of particle tracking. Journal of Fluid Mechanics, 185:447–468, 1987.Google Scholar
  3. 3.
    D. Derou and L. Herault. Perceptive grouping and pulsed neural network. Application to particle tracking velocimetry. Technical report, Commissariat a l'Energie Atomique-LETI-Departement Systemes, February 1994. LETI/DSYS/SCSI/MV-25.Google Scholar
  4. 4.
    L. Herault and R. Horaud. Figure-ground discrimination: a combinatorial optimization approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(9):899–914, 1993.Google Scholar
  5. 5.
    L. Hesselink. Digital image processing in flow visualization. Annual Review of Fluid Mechanics, 20:421–485, 1988.Google Scholar
  6. 6.
    D.G. Lowe. Perceptual organization and visual recognition. Kluwer Academic Publishers, Boston, 1985.Google Scholar
  7. 7.
    P. Parent and S.W. Zucker. Trace inference, curvature consistency and curve detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(8):823–839, 1989.Google Scholar
  8. 8.
    C. Peterson and T.Rognvaldsson. An introduction to artificial neural networks. Lectures given at the 1991 CERN School of Computing, Ystad, Sweden, July 1991.Google Scholar
  9. 9.
    A. Sha'ashua. Structural saliency: the detection of globally salient structures using a locally connected network. Master's thesis, dept. of Applied Math., Weizmann Institute of Science, Rehovot, Israel, 1988.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Dominique Derou
    • 1
  • Laurent Herault
    • 1
  1. 1.LETI-(CEA-Technologies Avancées)Grenoble Cedex 9France

Personalised recommendations