Robust image association by recurrent neural subnetworks

Wladyslaw Skarbek, Andrzej Cichocki

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)

Abstract

A neural network consisting of a gallery of independent subnetworks is developed for associative memory which stores and recalls gray scale images. Each original image is encoded by a unique stable state of one of neural recurrent subnetworks. Comparing to Amari-Hopfield associative memory, our solution has no spurious states, is less sensitive to noise, and its network complexity is significantly lower. Computer simulations confirm that associative recall in this system for images of natural scenes is very robust. Colored additive and multiplicative noise with standard deviation up to σ = 2 can be removed perfectly from normalized image. The same observations are valid for spiky noise distributed on up to 70% of image area. Even if we remove up to 95% pixels from the original image in deterministic or random way, still the network performs the correct association.

Original languageEnglish
Pages (from-to)131-138
Number of pages8
JournalNeural Processing Letters
Volume3
Issue number3
DOIs
Publication statusPublished - 1996
Externally publishedYes

Keywords

  • Associative memory
  • Image compression
  • Recurrent neural network

Fingerprint

Dive into the research topics of 'Robust image association by recurrent neural subnetworks'. Together they form a unique fingerprint.

Cite this