Abstract

We propose a new optical pattern-recognition method that is invariant to shift, rotation, and scale changes. By means of a zero-order circular-harmonic filter the input object can be transformed into a correlation peak whose outline retains a shape similar to the outline of the input object. After multilevel thresholding and binarization, a bank composed of many contours with different sizes is formed. The invariant recognition can be obtained by a small contour line being taking as a reference and its second-order circular-harmonic component being taken as a filter. In addition to the scale invariance the correlation peak is superior to the classical circular-harmonic filter and the phase-only circular-harmonic filter in terms of peak intensity, half-maximum width, and peak-to-sidelobe ratio.

© 1994 Optical Society of America

Real filter based on Mellin radial harmonics for scale-invariant pattern recognition

E. Tajahuerce, A. Moya, J. García, and C. Ferreira
Appl. Opt. 33(14) 3086-3093 (1994)

Invariant pattern recognition based on centroids

Shoude Chang, Henri H. Arsenault, Pascuala Garcia-Martinez, and Chander P. Grover
Appl. Opt. 39(35) 6641-6648 (2000)

Shift- and scale-invariant recognition of contour objects with logarithmic radial harmonic filters

Antonio Moya, José J. Esteve-Taboada, Javier García, and Carlos Ferreira
Appl. Opt. 39(29) 5347-5352 (2000)

Wavelet-transform-based composite filters for invariant pattern recognition

Zeev Zalevsky, Ido Ouzieli, and David Mendlovic
Appl. Opt. 35(17) 3141-3147 (1996)

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

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