Abstract

The well-known scale and rotation invariant polar-logarithmic coordinate transformation is used to achieve in-plane distortion invariant pattern recognition. The coordinate transform is produced by a computer-generated hologram on a laser printer. Attention is given to weighting terms in the output and their effect on resolution and the number of input plane pixels removed near the origin. The optically produced coordinate transformed input pattern is interfaced to a correlator by a pocket liquid crystal TV to provide real-time processing. Experimental results are included.

© 1987 Optical Society of America

Scale and projection invariant pattern recognition

David Mendlovic, Naim Konforti, and Emanuel Marom
Appl. Opt. 28(23) 4982-4986 (1989)

Shift-and-scale-invariant pattern recognition using an elliptic coordinate-transformed phase-only filter

Javier García, Tomasz Szoplik, and Carlos Ferreira
Appl. Opt. 31(23) 4823-4828 (1992)

Deformation invariant optical processors using coordinate transformations

Demetri Psaltis and David Casasent
Appl. Opt. 16(8) 2288-2292 (1977)

Coordinate-transformed filter for shift-invariant and scale-invariant pattern recognition

Dan Cojoc, M. Teresa Molina, Javier García, and Carlos Ferreira
Appl. Opt. 36(20) 4812-4815 (1997)

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)