Neural network analysis of images for non-destructive evaluation

John Sadowsky, Isaac Bankman, Vincent Sigillito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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)
Title of host publicationConference Record - Asilomar Conference on Circuits, Systems & Computers
PublisherPubl by Maple Press, Inc
Pages562-569
Number of pages8
Volume2
StatePublished - 1991
Event24th Asilomar Conference on Signals, Systems and Computers Part 2 (of 2) - Pacific Grove, CA, USA
Duration: Nov 5 1990Nov 7 1990

Other

Other24th Asilomar Conference on Signals, Systems and Computers Part 2 (of 2)
CityPacific Grove, CA, USA
Period11/5/9011/7/90

Fingerprint

Electric network analysis
Neural networks
X rays
Function evaluation
Image compression
Backpropagation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sadowsky, J., Bankman, I., & Sigillito, V. (1991). Neural network analysis of images for non-destructive evaluation. In Conference Record - Asilomar Conference on Circuits, Systems & Computers (Vol. 2, pp. 562-569). Publ by Maple Press, Inc.

Neural network analysis of images for non-destructive evaluation. / Sadowsky, John; Bankman, Isaac; Sigillito, Vincent.

Conference Record - Asilomar Conference on Circuits, Systems & Computers. Vol. 2 Publ by Maple Press, Inc, 1991. p. 562-569.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sadowsky, J, Bankman, I & Sigillito, V 1991, Neural network analysis of images for non-destructive evaluation. in Conference Record - Asilomar Conference on Circuits, Systems & Computers. vol. 2, Publ by Maple Press, Inc, pp. 562-569, 24th Asilomar Conference on Signals, Systems and Computers Part 2 (of 2), Pacific Grove, CA, USA, 11/5/90.
Sadowsky J, Bankman I, Sigillito V. Neural network analysis of images for non-destructive evaluation. In Conference Record - Asilomar Conference on Circuits, Systems & Computers. Vol. 2. Publ by Maple Press, Inc. 1991. p. 562-569
Sadowsky, John ; Bankman, Isaac ; Sigillito, Vincent. / Neural network analysis of images for non-destructive evaluation. Conference Record - Asilomar Conference on Circuits, Systems & Computers. Vol. 2 Publ by Maple Press, Inc, 1991. pp. 562-569
@inproceedings{06a5f751894045d5afca087ecba50e81,
title = "Neural network analysis of images for non-destructive evaluation",
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.",
author = "John Sadowsky and Isaac Bankman and Vincent Sigillito",
year = "1991",
language = "English (US)",
volume = "2",
pages = "562--569",
booktitle = "Conference Record - Asilomar Conference on Circuits, Systems & Computers",
publisher = "Publ by Maple Press, Inc",

}

TY - GEN

T1 - Neural network analysis of images for non-destructive evaluation

AU - Sadowsky, John

AU - Bankman, Isaac

AU - Sigillito, Vincent

PY - 1991

Y1 - 1991

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0026397981&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026397981&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026397981

VL - 2

SP - 562

EP - 569

BT - Conference Record - Asilomar Conference on Circuits, Systems & Computers

PB - Publ by Maple Press, Inc

ER -