Share Email Print

Proceedings Paper

Multilayer perceptron for rotationally invariant feature extraction and classification
Author(s): Michael H. W. Smart; Alan F. Murray
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper we introduce a technique for incorporating adaptive, rotationally invariant (RI), feature extraction into the initial layer parameters of a multilayer perceptron for classifying real IR imagery. Feature extraction parameters are not usually estimated directly due to their high dimensionality but it is possible to reduce the dimensionality by constraining these parameters to a feature subspace where the parameters are restricted to a continuous RI generating functional form (e.g. a circularly symmetric radial polynomial transform.) The lower dimensional function parameters and the classification parameters can then be estimated simultaneously to minimize an overall classification error criterion. This can be considered as an extension of previous work by other authors where non-RI filter parameters, such as Gabor filter directional selectivity, were successfully tuned for feature extraction.

Paper Details

Date Published: 22 March 1996
PDF: 8 pages
Proc. SPIE 2760, Applications and Science of Artificial Neural Networks II, (22 March 1996); doi: 10.1117/12.235935
Show Author Affiliations
Michael H. W. Smart, Edinburgh Univ. (United Kingdom)
Alan F. Murray, Edinburgh Univ. (United Kingdom)

Published in SPIE Proceedings Vol. 2760:
Applications and Science of Artificial Neural Networks II
Steven K. Rogers; Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top