Alternative continuous- and discrete-time neural networks for image restoration.
Network
; 30(1-4): 107-124, 2019.
Article
em En
| MEDLINE
| ID: mdl-31662021
ABSTRACT
This paper presents alternative continuous- and discrete-time neural networks for image restoration in real time by introducing new vectors and transforming its optimization conditions into a system of double projection equations. The proposed neural networks are shown to be stable in the sense of Lyapunov and convergent for any starting point. Compared with the existing neural networks for image restoration, the proposed models have the least neurons, a one-layer structure and the faster convergence, and is suitable to parallel implementation. The validity and transient behaviour of the proposed neural network is demonstrated by numerical examples.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Simulação por Computador
/
Processamento de Imagem Assistida por Computador
/
Redes Neurais de Computação
Idioma:
En
Revista:
Network
Assunto da revista:
NEUROLOGIA
Ano de publicação:
2019
Tipo de documento:
Article