Abstract

Optical pattern recognition under variations of illumination is an important issue. The sliced orthogonal nonlinear generalized (SONG) correlation has been proposed as an optical pattern recognition tool to discriminate with high efficiency between objects. But, at the same time, the SONG correlation is very sensitive to gray-scale image variations. In a previous work, we expanded the definition of the SONG correlation to the Weighted SONG (WSONG) correlation to modify the discrimination capability in a controlled way. Here, we propose to use the WSONG when pattern recognition is obtained by means of optical correlation under nonuniform illumination. The calculation of the WSONG correlation requires the summation of many linear correlations between binary images. To implement it optically, we use a time sequential joint transform correlator.

© 2002 Optical Society of America

Maximum likelihood for target location in the presence of substitutive noise

Pascuala Garcia-Martinez, Philippe Réfrégier, Henri H. Arsenault, and Carlos Ferreira
Appl. Opt. 40(23) 3855-3860 (2001)

Illumination-invariant pattern recognition with joint-transform-correlator-based morphological correlation

Shuqun Zhang and Mohammad A. Karim
Appl. Opt. 38(35) 7228-7237 (1999)

Nonlinear pattern recognition correlators based on color-encoding single-channel systems

Pascuala García-Martínez, Joaquín Otón, José J. Vallés, and Henri H. Arsenault
Appl. Opt. 43(2) 425-432 (2004)

Target recognition under nonuniform illumination conditions

Victor H. Diaz-Ramirez and Vitaly Kober
Appl. Opt. 48(7) 1408-1418 (2009)

Preprocessed multiobject joint transform correlator

M. S. Alam, O. Perez, and M. A. Karim
Appl. Opt. 32(17) 3102-3107 (1993)