Share Email Print

Proceedings Paper

Shift- and rotation-invariant interpattern heteroassociation model
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A shift and rotation invariant neural network using interpattern hetero association (IHA) model is illustrated. To preserve the shift and rotation invariant properties, a set of binarized-encoded circular harmonic expansion (CHE) function at the Fourier domain is used as the training set. The interconnection weight matrix is constructed using an IHA model. By using the shift and symmetric properties of the modulus Fourier spectral, the problem of centering the CHE functions can be avoided. Computer simulations and experimental demonstrations are provided in which we have shown that the shift and rotation invariant properties of the proposed IHA neural net are indeed preserved.

Paper Details

Date Published: 25 October 1993
PDF: 10 pages
Proc. SPIE 1959, Optical Pattern Recognition IV, (25 October 1993); doi: 10.1117/12.160318
Show Author Affiliations
Francis T. S. Yu, The Pennsylvania State Univ. (United States)
Chii-Maw Uang, The Pennsylvania State Univ. (Taiwan)
Shizhuo Yin, The Pennsylvania State Univ. (United States)

Published in SPIE Proceedings Vol. 1959:
Optical Pattern Recognition IV
David P. Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top