Paper
23 October 2003 Recognition in the presence of nonuniform illumination
Daniel Lefebvre, Henri H. Arsenault, Sebastien Roy
Author Affiliations +
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.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Daniel Lefebvre, Henri H. Arsenault, and Sebastien Roy "Recognition in the presence of nonuniform illumination", Proc. SPIE 5202, Optical Information Systems, (23 October 2003); https://doi.org/10.1117/12.501636
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Digital filtering

Image segmentation

Nonlinear filtering

Linear filtering

Pattern recognition

Target detection

Target recognition

RELATED CONTENT


Back to Top