An improved algorithm for image restoration based on modified Hopfield neural network

Author

Wu, Ya-Dong ; Chen, Yong-Hui ; Zhang, Hong-Ying

Author_Institution

Sch. of Comput. Sci. & Eng., Univ. of Sci. & Technol. of China, Chengdu, China

Volume

8

fYear

2005

fDate

18-21 Aug. 2005

Firstpage

4720

Abstract

The neural network method is widely used in image restoration, since its advantages such as the abilities of parallel computing, nonlinear mapping and self-adaptiveness. In this paper, an improved sequential algorithm is proposed, which uses the modified Hopfield neural network based on continuous state change, and maximal energy descent in the update rule. Experiment results show that the improved sequential algorithm could converge to a stable point with high speed, and give more precise restoration results.

Keywords

Hopfield neural nets; image restoration; continuous state change; convergence; image restoration; maximal energy descent; modified Hopfield neural network; sequential algorithm; update rule; Atmospheric modeling; Computer science; Degradation; Electronic mail; Hopfield neural networks; Image processing; Image restoration; Neural networks; Neurons; Parallel processing; Image restoration; neural network; sequential algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on

Conference_Location

Guangzhou, China

Print_ISBN

0-7803-9091-1

Type

conf

DOI

10.1109/ICMLC.2005.1527772

Filename

1527772