Share Email Print

Proceedings Paper

Shape Recognition Using A CMAC Based Learning System
Author(s): F. H. Glanz; W. T. Miller
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper discusses pattern recognition using a learning system which can learn an arbitrary function of the input and which has built-in generalization with the characteristic that similar inputs lead to similar outputs even for untrained inputs. The amount of similarity is controlled by a parameter of the program at compile time. Inputs and/or outputs may be vectors. The system is trained in a way similar to other pattern recognition systems using an LMS rule. Patterns in the input space are not separated by hyperplanes in the way they normally are using adaptive linear elements. As a result, linear separability is not the problem it is when using Perceptron or Adaline type elements. In fact, almost any shape category region is possible, and a region need not be simply connected nor convex. An example is given of geometric shape recognition using as features autoregressive model parameters representing the shape boundaries. These features are approximately independent of translation, rotation, and size of the shape. Results in the form of percent correct on test sets are given for eight different combinations of training and test sets derived from two groups of shapes.

Paper Details

Date Published: 19 February 1988
PDF: 5 pages
Proc. SPIE 0848, Intelligent Robots and Computer Vision VI, (19 February 1988);
Show Author Affiliations
F. H. Glanz, University of New Hampshire (United States)
W. T. Miller, University of New Hampshire (United States)

Published in SPIE Proceedings Vol. 0848:
Intelligent Robots and Computer Vision VI
David P. Casasent; Ernest L. Hall, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?