Share Email Print

Proceedings Paper

Optical pattern recognition based on normalized correlation
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We propose a method for optical correlation-based intensity invariant pattern recognition. Our approach relays on a normalization of the correlation signal applicable in conjunction with simple linear or nonlinear filtering of any type. The normalization is based on the Holder's inequality if the input signal is segmented and on the Cauchy-Schwarz's inequality if more than one target object may be present in the input signal. We discuss the difference between our formula and the previously proposed simpler normalization, which is an approximation to the results obtained in the present paper. The performance of the normalized correlation with segmented and multiobject input is illustrated with numerical simulations.

Paper Details

Date Published: 18 November 1999
PDF: 12 pages
Proc. SPIE 3904, Fourth International Conference on Correlation Optics, (18 November 1999); doi: 10.1117/12.370406
Show Author Affiliations
Rafal Kotynski, Warsaw Univ. (Poland)
Katarzyna Chalasinska-Macukow, Warsaw Univ. (Poland)

Published in SPIE Proceedings Vol. 3904:
Fourth International Conference on Correlation Optics
Oleg V. Angelsky, Editor(s)

© SPIE. Terms of Use
Back to Top