Abstract

We discuss the merits of using single-layer (linear and nonlinear) and multiple-layer (nonlinear) filters for rotationally invariant and noise-tolerant pattern recognition. The capability of each approach is considered with reference to a two-class, rotation-invariant, character recognition problem. The minimum average correlation energy (MACE) filter is a linear filter that is generally accepted to be optimal for detecting signals that are free from noise. Here it is found that an optimized MACE filter cannot differentiate between the characters E and F in a rotation-invariant manner. We have found, however, that this task is possible when a single optimized linear filter is used to achieve the required response when a nonlinear threshold function is included after the filter. We show that this structure can be cascaded to form a multiple-layer, cascaded filter and that the capability of such a system is enhanced by its increased noise tolerance in the character recognition problem. Finally, we show the capability of a two-layer cascade as a means to detect different species of bacteria in images obtained from a phase-contrast microscope.

© 2005 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)

Distortion-invariant pattern recognition with Fourier-plane nonlinear filters

Bahram Javidi and Dean Painchaud
Appl. Opt. 35(2) 318-331 (1996)

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)

Nonlinear filter for pattern recognition invariant to illumination and to out-of-plane rotations

Daniel Lefebvre, Henri H. Arsenault, and Sébastien Roy
Appl. Opt. 42(23) 4658-4662 (2003)

Automatic spatial frequency selection algorithm for pattern recognition by correlation

Frank Dubois
Appl. Opt. 32(23) 4365-4371 (1993)