Share Email Print

Optical Engineering

Nonlinear composite filter performance
Format Member Price Non-Member Price
PDF $20.00 $25.00
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

We use nonlinear composite filters in object recognition, even when they have rotation, scale, noise, and illumination distortions. We generated 936 images of the letters E, F, H, P, and B. The images consisted of these letters scaled from 70% to 130% and rotated 360 deg. The maximum number of images supported by these filters was determined by a numerical experiment. Considering a system confidence level of at least 80%, the maximum number of images is around 216. We found a "rotation problem" when the filter contained the letter rotated 360 deg, since circles were artificially introduced, and this creates complications when working with images that also have circles in their spectrum. Due to this, we propose a segmented filter that breaks the circular symmetry. Experiments where carried out in order to find the noise tolerance of each filter, and the use of Spearman's rank correlation (in conjunction with the nonlinear method, SNM) is proposed in order to increase that tolerance. We also made an assessment of the impact that illumination changes had in the correlation output, in the problem image, and we propose the use of SNM to obtain illumination invariance. We tested these filters with two real-life problems; nonlinear composite filters can recognize the target in the presence of distortions.

Paper Details

Date Published: 1 June 2009
PDF: 11 pages
Opt. Eng. 48(6) 067201 doi: 10.1117/1.3152777
Published in: Optical Engineering Volume 48, Issue 6
Show Author Affiliations
Ricardo Enrique Guerrero-Moreno, Ctr. de Investigación Científica y de Educación Superior de Ensenada (Mexico)
Josué Álvarez-Borrego, Ctr. de Investigación Científica y de Educación Superior de Ensenada (Mexico)

© SPIE. Terms of Use
Back to Top