Share Email Print
cover

Proceedings Paper

Nonlinear binary correlations for rotation-invariant pattern recognition using circular harmonic decomposition
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We apply the sliced orthogonal nonlinear generalized (SONG) correlation to rotation invariant pattern recognition using circular harmonic decompositions. The images are decomposed into disjoint binary slices to correlate each of them with one object binary slice circular harmonic component. To obtain the final Rotation Invariant SONG correlation output, we add the correlations from each slice. In addition, in order to improve discrimination capability, the method avoids the time-consuming process of finding proper center for the circular harmonic decompositions.

Paper Details

Date Published: 14 August 2001
PDF: 4 pages
Proc. SPIE 4419, 4th Iberoamerican Meeting on Optics and 7th Latin American Meeting on Optics, Lasers, and Their Applications, (14 August 2001); doi: 10.1117/12.437126
Show Author Affiliations
Pascuala Garcia-Martinez, Univ. de Valencia (Spain)
Henri H. Arsenault, Univ. Laval (Canada)
Carlos Ferreira, Univ. de Valencia (Spain)


Published in SPIE Proceedings Vol. 4419:
4th Iberoamerican Meeting on Optics and 7th Latin American Meeting on Optics, Lasers, and Their Applications

© SPIE. Terms of Use
Back to Top