Variational PDE based image restoration using neural network

Author

Wu, Y.-D. ; Sun, Y. ; Zhang, H.-Y. ; Sun, S.-X.

Author_Institution

Coll. of Comput. Sci. & Technol., Southwest Univ. of Sci. & Technol., Mianyang

Volume

1

Issue

1

fYear

2007

fDate

3/1/2007 12:00:00 AM

Firstpage

85

Lastpage

93

Abstract

Two variational partial differential equations as regularisation terms are proposed for the image restoration model based on the modified Hopfield neural network. One is based on a harmonic model and the other is based on a total variation model. The performance of these regularisation terms is analysed from the viewpoint of nonlinear diffusion. It can be shown that the two proposed restoration models have edge-preserving performance superior to that of the traditional restoration model. Two algorithms have been proposed on the basis of the harmonic restoration model and the total variation model. Experimental results show that the proposed algorithms are more effective than the traditional algorithm

Keywords

Hopfield neural nets; image restoration; partial differential equations; variational techniques; edge-preserving performance; harmonic restoration model; image restoration; modified Hopfield neural network; nonlinear diffusion; regularisation terms; total variation model; variational PDE; variational partial differential equations;

fLanguage

English

Journal_Title

Image Processing, IET

Publisher

iet

ISSN

1751-9659

Type

jour

DOI

10.1049/iet-ipr:20050383

Filename

4149699