Abstract

Independent analyses using Fisher information, optimal filtering, and information theory show that matched filtering images with hypothetical patterns in the logarithmic domain provides an optimal method for pattern recognition in the presence of signal-dependent noise arising from complex Gaussian fluctuations in the received fields. This provides a mathematical justification for the use of logarithmic units (i.e., decibels) in a variety of engineering applications.

© 1995 Optical Society of America

Pattern recognition based on the correlated intensity fluctuations of thermal light

Yi-Kuo Liu, Ying Wang, De-Zhong Cao, and Su-Heng Zhang
J. Opt. Soc. Am. A 31(7) 1547-1551 (2014)

Shift and projection invariant pattern recognition using logarithmic harmonics

David Mendlovic, Naim Konforti, and Emanuel Marom
Appl. Opt. 29(32) 4784-4789 (1990)

Optical pattern recognition based on color vision models

M. S. Millán, M. Corbalán, J. Romero, and M. J. Yzuel
Opt. Lett. 20(16) 1722-1724 (1995)

Projection-invariant pattern recognition with a phase-only logarithmic-harmonic-derived filter

A. Moya, D. Mendlovic, J. García, and C. Ferreira
Appl. Opt. 35(20) 3862-3867 (1996)

One-dimensional logarithmic harmonic synthetic discriminant function filters for shift-, scale-, and projection-invariant pattern recognition

Jianping Yao and Guy Lebreton
Opt. Lett. 23(7) 537-539 (1998)