THE RGF PANDEMONIUM - A LOW-LEVEL REPRESENTATIONAL MODEL FOR IMAGES

Authors
RODRIGUEZSANCHEZ R GARCIA JA FDEZVALDIVIA J
Citation
R. Rodriguezsanchez et al., THE RGF PANDEMONIUM - A LOW-LEVEL REPRESENTATIONAL MODEL FOR IMAGES, Pattern recognition, 31(11), 1998, pp. 1797-1810
Citations number
8
Categorie Soggetti
Computer Science Artificial Intelligence","Engineering, Eletrical & Electronic","Computer Science Artificial Intelligence
Journal title
Pattern recognition → ACNP
ISSN journal
00313203
Volume
31
Issue
11
Year of publication
1998
Pages
1797 - 1810
Database
ISI
SICI code
0031-3203(1998)31:11<1797:TRP-AL>2.0.ZU;2-F
Abstract
In this work, we have reformulated the selection of a few responding u nits tuned to patterns of activity from the Fourier spectrum as a mult ilayer system composed of four stages of different kinds of feature de tectors. The system output is a sparse representation for images that produces an organization according to object power discrimination. The resultant multilayer system provides a more efficient representation for later stages of processing because it possesses a higher degree of perceptual independence among its outputs. (C) 1998 Pattern Recogniti on Society. Published by Elsevier Science Ltd. All rights reserved.