Share Email Print

Proceedings Paper

Recognition in the presence of nonuniform illumination
Author(s): Daniel Lefebvre; Henri H. Arsenault; Sebastien Roy
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Linear filtering methods often fail to detect dark objects because the correlation peak height is proportional to the object intensity. And the high response from very bright clutter can result in false detections. In real world situations, intensity variations of targets occur. We address the problem of image recognition in the presence of unknown uniform and nonuniform intensity transformations. The uniform intensity transformations considered are multiplicative and additive. This part of the problem has already been solved using a method that we recently proposed called the LACIF (Locally Adaptive Contrast-Invariant Filter). In this paper we generalize this method for situations where a linear intensity gradient across an object can be present. For this we use a set of four orthonormal images, compute the correlations between each of those images and the scene. Then we do one more correlation and combine the fives correlation planes in a nonlinear manner. Results show that discrimination is good.

Paper Details

Date Published: 23 October 2003
PDF: 6 pages
Proc. SPIE 5202, Optical Information Systems, (23 October 2003); doi: 10.1117/12.501636
Show Author Affiliations
Daniel Lefebvre, COPL, Univ. Laval (Canada)
Henri H. Arsenault, COPL, Univ. Laval (Canada)
Sebastien Roy, COPL, Univ. Laval (Canada)

Published in SPIE Proceedings Vol. 5202:
Optical Information Systems
Bahram Javidi; Demetri Psaltis, 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?