DocumentCode
3374011
Title
Adaptive image restoration using Hopfield neural network
Author
Ghennam, Souheila ; Benmahammed, Khier
Author_Institution
Dept. of Electron., Ferhat Abbas Univ., Setif, Algeria
fYear
2001
fDate
2001
Firstpage
569
Lastpage
578
Abstract
In this paper, a solution to the restoration problem of degraded and noisy image is proposed, using the modified Hopfield network. To improve the network performances, the eliminating highest error EHE is used. In order to keep the image structures unaltered, an adaptive regularization scheme is employed that allows better compromise between inversion degradation process and smoothing. To do this, the statistics analysis is used to assign each pixel one regularization parameter according to its spatial activity
Keywords
Hopfield neural nets; image restoration; Hopfield neural network; adaptive image restoration; adaptive regularization scheme; degraded image; image structures; noisy image; spatial activity; Additive noise; Artificial neural networks; Biological neural networks; Degradation; Gaussian noise; Hopfield neural networks; Image restoration; Neurons; Smoothing methods; Statistical analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks for Signal Processing XI, 2001. Proceedings of the 2001 IEEE Signal Processing Society Workshop
Conference_Location
North Falmouth, MA
ISSN
1089-3555
Print_ISBN
0-7803-7196-8
Type
conf
DOI
10.1109/NNSP.2001.943161
Filename
943161
Link To Document