Abstract

In this paper, we extend the method of expansion into circular harmonic functions (CHF) by using vector rather than scalar target signatures. The reference vector consists of correlation products between the reference image and individual harmonics of the CHF expansion of the reference image. The use of vectors furnishes certain advantages including the ability to detect targets in poor signal-to-noise or low-contrast environments.

© 1984 Optical Society of America

Rotation-invariant pattern recognition using optimum feature extraction

Ronald Wu and Henry Stark
Appl. Opt. 24(2) 179-184 (1985)

Rotation-invariant digital pattern recognition using circular harmonic expansion

Yuan-Neng Hsu, H. H. Arsenault, and G. April
Appl. Opt. 21(22) 4012-4015 (1982)

Rotation invariant color pattern recognition by use of a three-dimensional Fourier transform

Oscar Gualdrón, Josep Nicolás, Juan Campos, and Maria J. Yzuel
Appl. Opt. 42(8) 1434-1440 (2003)

Nonlinear rotation-invariant pattern recognition by use of the optical morphological correlation

Pascuala Garcia-Martinez, Carlos Ferreira, Javier Garcia, and Henri H. Arsenault
Appl. Opt. 39(5) 776-781 (2000)

Image preprocessing for rotation-invariant pattern recognition in the presence of signal-dependent noise

Jean-Christophe Terrillon
Appl. Opt. 35(11) 1879-1893 (1996)