Neural network analysis of images for non-destructive evaluation

John Sadowsky, Isaac Bankman, Vincent Sigillito

Research output: Contribution to journalConference article

Abstract

An effort to develop a neural network-based system that is capable of analyzing images for the presence of particular features is reported. In particular, the system would automatically analyze X-ray images as part of a non-destructive evaluation (NDE) function. Of particular interest is the development of neural network-based systems that can easily and inexpensively be retained when design changes are made in parts to be inspected. Backpropagation networks with one hidden layer, based on classification and image compression concepts, were designed and tested with X-rays of Army M764 fuzes.

Original languageEnglish (US)
Pages (from-to)562-569
Number of pages8
JournalConference Record - Asilomar Conference on Circuits, Systems & Computers
Volume2
StatePublished - Dec 1 1991
Event24th Asilomar Conference on Signals, Systems and Computers Part 2 (of 2) - Pacific Grove, CA, USA
Duration: Nov 5 1990Nov 7 1990

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Neural network analysis of images for non-destructive evaluation'. Together they form a unique fingerprint.

  • Cite this