A design procedure is presented for neural associative memories storing gray-scale images. It is an evolution of a previous work based on the decomposition of the image with 2(L) gray levels into L binary patterns, stored in L uncoupled neural networks. In this letter, an L-layer neural network is proposed with both intralayer and interlayer connections. The connections between different layers introduce interactions among all the neurons, increasing the recall performance with respect to the uncoupled case. In particular, the proposed network can store images with the commonly used number of 256 gray levels instead of 16, as in the previous approach.
Costantini, G., Casali, D., & Perfetti, R. (2006). Associative memory design for 256 gray-level images using a multilayer neural network. IEEE TRANSACTIONS ON NEURAL NETWORKS, 14(3), 703-707.
Tipologia: | Articolo su rivista |
Citazione: | Costantini, G., Casali, D., & Perfetti, R. (2006). Associative memory design for 256 gray-level images using a multilayer neural network. IEEE TRANSACTIONS ON NEURAL NETWORKS, 14(3), 703-707. |
Lingua: | English |
Settore Scientifico Disciplinare: | Settore ING-IND/31 - Elettrotecnica |
Revisione (peer review): | Sì, ma tipo non specificato |
Tipo: | Articolo |
Rilevanza: | Rilevanza internazionale |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1109/TNN.2005.863465 |
Stato di pubblicazione: | Pubblicato |
Data di pubblicazione: | 2006 |
Titolo: | Associative memory design for 256 gray-level images using a multilayer neural network |
Autori: | |
Autori: | Costantini, G; Casali, D; Perfetti, R |
Appare nelle tipologie: | 01 - Articolo su rivista |
File in questo prodotto:
File | Descrizione | Tipologia | Licenza | |
---|---|---|---|---|
2006-Associative memory design for 256 Gray-Level Images.pdf | N/A | Non specificato | Open Access Visualizza/Apri |