Title :
Artificial neural network for image compression
Author :
Sicuranza, Giovanni L. ; Romponi, G. ; Marsi, Stefano
Author_Institution :
Treiste Univ., Italy
fDate :
3/29/1990 12:00:00 AM
Abstract :
An artificial neural network is proposed which is able to compress an image by computing a nonlinear nonorthogonal transform and its inverse. The network is trained with small blocks extracted from an image; after the learning phase, it proves to give satisfactory performances both for the learned and for different unlearned images.
Keywords :
data compression; learning systems; neural nets; picture processing; transforms; artificial neural network; image compression; inverse transform; learning phase; network training; nonlinear nonorthogonal transform;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19900310
