PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Bedini L., Tonazzini A. Neural network use in maximum entropy image restoration. In: Image and Vision Computing, vol. 8 (2) pp. 108 - 114. Elsevier, 1990.
 
 
Abstract
(English)
The computational properties of analogue electrical circuits, recently proposed as models for highly-interconnected networks of non-linear analogue neurons, have been found attractive in solving optimization problems. The computation power of these circuits is based on the high connectivity typical of neural systems, and on the convergence speed of analogue electrical circuits in reaching stable states. The problem of image restoration using the maximum entropy (ME) method is considered. This problem is rigorously formuated as a constrained optimization problem in a primaldual Lagrange multipliers framework. In this way, an alterative scheme which can be used to solve the ME image restoration problem can be defined. The iterative scheme takes advantage of the computation power of neural networks in solving optimization problems. A possible electrical circuit for the neural networks is proposed. Some features which can be useful for a practical implementation of the proposed circuit are also reported.
Subject Image restoration
Maximum entropy
Neural networks


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional