Karim Achour ; Nadia Zenati ; Oualid Djekoune - Contribution to image restoration using a neural network model

arima:1829 - Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, September 22, 2002, Volume 1, 2002 - https://doi.org/10.46298/arima.1829
Contribution to image restoration using a neural network modelArticle

Authors: Karim Achour 1; Nadia Zenati 1; Oualid Djekoune 1

  • 1 Laboratoire de Recherche en Intelligence Artificielle [Alger]

The reduction of the blur and the noise is an important task in image processing. Indeed, these two types of degradation are some undesirable components during some high level treatments. In this paper, we propose an optimization method based on neural network model for the regularized image restoration. We used in this application a modified Hopfield neural network. We propose two algorithms using the modified Hopfield neural network with two updating modes : the algorithm with a sequential updates and the algorithm with the n-simultaneous updates. The quality of the obtained result attests the efficiency of the proposed method when applied on several images degraded with blur and noise.


Volume: Volume 1, 2002
Published on: September 22, 2002
Submitted on: March 24, 2002
Keywords: Neural network, Hopfield neural network, modified Hopfield neural network, image restoration, sequential algorithm, n-simultaneous algorithm.,réseaux de neurones,réseau de Hopfield,réseau de Hopfield modifié,restauration d'images,algorithme séquentiel,algorithme n-simultané.,[INFO]Computer Science [cs],[MATH]Mathematics [math]

Consultation statistics

This page has been seen 287 times.
This article's PDF has been downloaded 571 times.