Share Email Print
cover

Proceedings Paper

Visual image processing by way of neural nets with nonlocal ties
Author(s): Nicolai S. Belliustin; Alexander G. Khobotov
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This investigation is one of the preliminary steps to create an artificial system of visual image recognition and reconstruction implementing main principles of visual image processing in living biological systems. A previous study of neural net models with decreasing inner neurons' dynamics proved that net with lateral inhibition ties is able to convert image into compressed form and to pick out key elements of the picture. The present papers propose to use a reverse neural net with increasing inner neurons' dynamics with the same other parameters (the conjugate net) for image back reconstruction and image histograms' entropy measures as integral values for dynamic image processing monitoring and control.

Paper Details

Date Published: 7 December 1994
PDF: 9 pages
Proc. SPIE 2430, Optical Memory & Neural Networks '94: Optical Neural Networks, (7 December 1994); doi: 10.1117/12.195619
Show Author Affiliations
Nicolai S. Belliustin, Radiophysical Research Institute (Russia)
Alexander G. Khobotov, Research & Development Institute of Technology and Industrial Engineering (Russia)


Published in SPIE Proceedings Vol. 2430:
Optical Memory & Neural Networks '94: Optical Neural Networks
Andrei L. Mikaelian, Editor(s)

© SPIE. Terms of Use
Back to Top