Cellular Neural Networks with UBN and MVN

  • Igor N. Aizenberg
  • Naum N. Aizenberg
  • Joos Vandewalle
Chapter

Abstract

Cellular Neural Networks (CNN) with UBN and MVN as the basic neurons (respectively, CNN-UBN and CNN-MVN) are considered in this chapter. A brief introduction to the CNN, and an observation of the related applied problems are presented. It is shown that the use of MVN and UBN as the basic CNN neurons may extend their functionality by implementing mappings described with non-threshold Boolean and multiple-valued threshold functions. Some problems of image processing, which may be effectively solved using CNN-UBN and CNN-MVN are considered: precise edge detection, edge detection by narrow direction, impulsive noise filtering, multi-valued nonlinear filtering for noise reduction and frequency correction (extraction of image details).

Keywords

Boolean Function Edge Detection Cellular Neural Network Impulsive Noise Linear Filter 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Science+Business Media Dordrecht 2000

Authors and Affiliations

  • Igor N. Aizenberg
    • 1
  • Naum N. Aizenberg
    • 1
  • Joos Vandewalle
    • 2
  1. 1.Neural Networks Technologies Ltd.Israel
  2. 2.Departement Elektrotechniek, ESAT/SISTAKatholieke Universiteit LeuvenBelgium

Personalised recommendations