Image processing applications via time-multiplexing cellular neural network simulator with numerical integration algorithms

A novel approach to simulate cellular neural networks (CNN) is presented in this paper. The approach, time-multiplexing simulation, is prompted by the need to simulate hardware models and test hardware implementations of CNN. For practical applications, due to hardware limitations, it is impossible...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of computer mathematics Jg. 87; H. 4; S. 840 - 848
1. Verfasser: Murugesh, V.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Abingdon Taylor & Francis 01.03.2010
Taylor & Francis Ltd
Schlagworte:
Algorithms
Blocking
cellular neural networks
Computer simulation
Differential equations
Dynamical systems
Euler algorithm
G.1.7
Hardware
Image processing systems
Mathematical models
Neural networks
Optimization algorithms
ordinary differential equations
Processors
RK-Butcher algorithm
RK-Gill algorithm
Simulation
ISSN:0020-7160, 1029-0265
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A novel approach to simulate cellular neural networks (CNN) is presented in this paper. The approach, time-multiplexing simulation, is prompted by the need to simulate hardware models and test hardware implementations of CNN. For practical applications, due to hardware limitations, it is impossible to have a one-to-one mapping between the CNN hardware processors and all the pixels of the image. This simulator provides a solution by processing the input image block by block, with the number of pixels in a block being the same as the number of CNN processors in the hardware. The algorithm for implementing this simulator is presented along with popular numerical integration algorithms. Some simulation results and comparisons are also presented.
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0020-7160
1029-0265
DOI:10.1080/00207160802217219