Share Email Print
cover

Proceedings Paper

Towards A Neural Net Architecture For Rapid Learning In Machine Vision
Author(s): Paul T. Hadingham
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Though they boast many attractive features, major problems exist in using an artificial neural network to represent knowledge. In particular, network training is usually a considerable task. Moreover, the network connections in the trained network bear no obviously derivable relationship to the component structures or concepts existing in the knowledge which has been learned. Research described here attempts to tackle both these issues in the context of edge interpretation in machine vision. The basis for a novel artificial neural network architecture is proposed which supports the direct representation of domain knowledge, in this case, the relationship between simple edge patterns and objects represented by the edge patterns. This means that the time-consuming training cycle can be avoided because network weights are directly calculated as functions of the edge structures which make up each object so that connection weights have a natural interpretation in terms of concepts comprising an object. The notions of arc and arc relation space have been developed as the cornerstones of this architecture. Their analysis in this limited domain indicates that such spaces may have a significant part to play in the general context of object recognition based on edge structures in machine vision.

Paper Details

Date Published: 1 February 1990
PDF: 10 pages
Proc. SPIE 1197, Automated Inspection and High-Speed Vision Architectures III, (1 February 1990); doi: 10.1117/12.969957
Show Author Affiliations
Paul T. Hadingham, The University of Western Australia (Australia)


Published in SPIE Proceedings Vol. 1197:
Automated Inspection and High-Speed Vision Architectures III
Michael J. W. Chen, Editor(s)

© SPIE. Terms of Use
Back to Top