Abstract

The use of fuzzy-logic techniques on the correlation output plane is analyzed as a method to improve the discrimination capabilities of pattern-recognition procedures. The study is divided into two parts: one recounts a computer-simulated example corresponding to pattern recognition by the use of input images that may be defocused, tilted, or corrupted by additive Gaussian noise, and the second part describes an experimental setup in which the deformation of foam material is studied.

© 1996 Optical Society of America

Correlation postprocessing-based method for the detection of defocused images

Arturo Carnicer, Santiago Vallmitjana, and Ignacio Juvells
Appl. Opt. 36(20) 4807-4811 (1997)

Optical generation of fuzzy-based rules

Eran Gur, David Mendlovic, and Zeev Zalevsky
Appl. Opt. 41(23) 4753-4761 (2002)

Fuzzy syntactical pattern recognition

H. John Caulfield
Appl. Opt. 29(17) 2600-2602 (1990)

Fourier-domain-based angular correlation for quasiperiodic pattern recognition. Applications to web inspection

María S. Millán and Jaume Escofet
Appl. Opt. 35(31) 6253-6260 (1996)

Multichannel single-output color pattern recognition by use of a joint-transform correlator

Meir Deutsch, Javier García, and David Mendlovic
Appl. Opt. 35(35) 6976-6982 (1996)