Image restoration using the Hopfield network with nonzero autoconnection

Joon K. Paik*, Aggelos K Katsaggelos

*Corresponding author for this work

Research output: Contribution to journalArticle

6 Scopus citations

Abstract

A modified Hopfield network model for image restoration is presented. The proposed network does not require zero autoconnections, which is one of the major drawbacks of the Hopfield network. A new number-representation scheme for implementing the proposed network is given. The proposed network with sequential update is shown to converge. The sufficient conditions for convergence of n-simultaneous updates are also given. When the image-restoration problem does not satisfy the convergence conditions, a greedy algorithm which guarantees convergence (at the expense of the image quality) is used.

Original languageEnglish (US)
Pages (from-to)1909-1912
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume4
StatePublished - Dec 1 1990

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Fingerprint Dive into the research topics of 'Image restoration using the Hopfield network with nonzero autoconnection'. Together they form a unique fingerprint.

Cite this