Share Email Print

Proceedings Paper

Optimization and application of a RAM-based neural network for fast image processing tasks
Author(s): Thomas Martini Joergensen; Steen Sloth Christensen; Allan Weimar Andersen; Christian Liisberg
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A RAM-based neural network applicable for object detection in machine vision is considered. It is shown that it is easy to perform a crossvalidation test for the training set using this network type. This is relevant for measuring the network generalization capability (robustness). An information measure combining the concept of crossvalidation and Shannon information is proposed. We describe how this measure can be used to select the input connections of the network. The task of recognizing handwritten digits is used to demonstrate the capability of the selection strategy.

Paper Details

Date Published: 10 October 1994
PDF: 11 pages
Proc. SPIE 2353, Intelligent Robots and Computer Vision XIII: Algorithms and Computer Vision, (10 October 1994);
Show Author Affiliations
Thomas Martini Joergensen, Riso National Labs. (Denmark)
Steen Sloth Christensen, Riso National Labs. (Denmark)
Allan Weimar Andersen, Riso National Labs. (Denmark)
Christian Liisberg, Riso National Labs. (Denmark)

Published in SPIE Proceedings Vol. 2353:
Intelligent Robots and Computer Vision XIII: Algorithms and Computer Vision
David P. Casasent, 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?