Two image restoration algorithms using variational PDE based neural network

Ya-Dong Wu,Shi-Xin Sun,Hong-Ying Zhang,Yu Sun

doi:10.1145/1280940.1281085

Two image restoration algorithms using variational PDE based neural network

Ya-Dong Wu, Shi-Xin Sun + Show 2 more

https://doi.org/10.1145/1280940.1281085

Copy DOI

Publication Date: Aug 12, 2007

Citations: 14

Affiliation: Southwest University of Science and Technology, University of Electronic Science and Technology of China, University of Central Arkansas

#Modified Hopfield Neural Network #Variational Partial Differential Equations + Show 8 more

Abstract
Full-Text PDF
Similar Papers

Abstract

In this paper, based on the modified Hopfield neural network, we present two variational PDEs (Partial Differential Equations) as the regularization terms to the image restoration model. One is based on a harmonic model and the other is based on a total variation model. Then, we propose two novel variational image restoration algorithms based on the Modified Hopfield Neural Network (MHNN). Both algorithms are aiming to restore the degraded images and preserve the edges with improved visual quality. The experimental results demonstrate that our proposed algorithms perform better than other known neural network based restoration algorithms.

Full Text