Abstract

The cascaded correlator architecture comprises a series of traditional linear correlators separated by nonlinear threshold functions, trained with neural-network techniques. We investigate the shift-invariant classification performance of cascaded correlators in comparison with optimum Bayes classifiers. Inputs are formulated as randomly generated sample members of known statistical class distributions. It is shown that when the separability of true and false classes is varied in both the first and the second orders, the two-stage cascaded correlator shows performance similar to that of the optimum quadratic Bayes classifier throughout the studied range. It is shown that this is due to the similar decision boundaries implemented by the two nonlinear classifiers.

© 2000 Optical Society of America

Cascaded linear shift-invariant processors in optical pattern recognition

Stuart Reed and Jeremy Coupland
Appl. Opt. 40(23) 3843-3849 (2001)

Rotationally invariant pattern recognition by use of linear and nonlinear cascaded filters

Ning Wu, Robin D. Alcock, Neil A. Halliwell, and Jeremy M. Coupland
Appl. Opt. 44(20) 4315-4322 (2005)

Two class minimax distance transform correlation filter

Marios Savvides, B. V. K. Vijaya Kumar, and Pradeep K. Khosla
Appl. Opt. 41(32) 6829-6840 (2002)

Optimum classification of correlation-plane data by Bayesian decision theory

Bret F. Draayer, Gary W. Carhart, and Michael K. Giles
Appl. Opt. 33(14) 3034-3049 (1994)

Nonlinear cascaded correlation processes to improve the performances of automatic spatial-frequency-selective filters in pattern recognition

Frank Dubois
Appl. Opt. 35(23) 4589-4597 (1996)