Abstract

An optical angular feature mapping of an object for pattern recognition is presented that uses self-pumped phase conjugation followed by a vertical projection. In this method the vertical contour features of an object are most enhanced and vertically projected at each angle as the object is rotated. The vertical enhancement of the contour and the projection are performed optically with self-pumped phase conjugation and a cylindrical lens, respectively. The peaks in the resulting projection at the angle are located and integrated to produce an angular signature function. The signature function is then energy normalized for scale invariance, and pattern recognition is performed by calculation of a cross correlation between two signature functions. The method exhibits invariance to shift, rotation, and variations in scale. Effects of a spatial filter and incident-beam conditions used for phase conjugation are also discussed along with experimental results.

© 1994 Optical Society of America

Invariant pattern recognition using angular signature functions

Yim-Kul Lee and William T. Rhodes
Appl. Opt. 32(23) 4372-4377 (1993)

Invariant optical-pattern recognition based on a contour bank

Shoude Chang, Henri H. Arsenault, and Dahe Liu
Appl. Opt. 33(14) 3076-3085 (1994)

Photorefractive-crystal shape-parameter influence on formation of self-pumped phase conjugation

Xuefeng Yue, Zongshu Shao, Jun Chen, Yongyuan Song, and Huanchu Chen
Appl. Opt. 33(14) 3135-3138 (1994)

Generation of self-pumped phase conjugation from the -c face of BaTiO₃ with femtosecond pulses

Changxi Yang, Kaoru Minoshima, Katuo Seta, Hirokazu Matsumoto, and Yong Zhu
Appl. Opt. 38(9) 1704-1708 (1999)

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)