Share Email Print

Proceedings Paper

Global stability in nonlinear lateral inhibition
Author(s): Gerard F. McLean; M. Ed Jernigan
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Pinter’s model of lateral inhibition using nonlinear local interactions adapts to local signal characteristics to perform range compression and edge enhancement. The model does this with no forced-choice or thresholding, making it suitable for implementation as a generalised image preprocessor. However, the global behaviour of the model is problematic, as its nonlinear and recurrent structure demands that iterative solution procedures be used. Using such techniques, the model proposed by Pinter has been shown to be extremely sensitive to parameter specifications, often providng unstable signal response. In this paper, we investigate the structure of alternatives to the Pinter model which include locally adaptive gain functions. We show that the alternative models display similar adaptive behaviour and decreased sensitivity to gain selection compared to the original Pinter model.

Paper Details

Date Published: 1 September 1990
PDF: 12 pages
Proc. SPIE 1360, Visual Communications and Image Processing '90: Fifth in a Series, (1 September 1990); doi: 10.1117/12.24116
Show Author Affiliations
Gerard F. McLean, Univ. of Victoria (Canada)
M. Ed Jernigan, Univ. of Waterloo (Canada)

Published in SPIE Proceedings Vol. 1360:
Visual Communications and Image Processing '90: Fifth in a Series
Murat Kunt, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?