Automated visual inspection and classification using neural networks

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

Abstract

This research presents schemes for automated visual inspection for boundary defects and classification using neural networks. An efficient method for representing circular boundaries is proposed utilizing a curvature and circular fitting algorithm. For the classification schemes, two types of neural network models are established. First, a multi-layer perception is discussed for defect classification problems. Second, a Hopfield network is modeled to be used for continuous-type variables by minimizing the energy function. Extensive tests are conducted on castings, then the results of neural networks are compared with those of traditional pattern classifiers.

Original languageEnglish (US)
Title of host publicationIndustrial Engineering Research - Conference Proceedings
PublisherIIE
Pages286-294
Number of pages9
StatePublished - 1995
EventProceedings of the 1995 4th Industrial Engineering Research Conference - Nashville, TN, USA
Duration: May 24 1995May 25 1995

Other

OtherProceedings of the 1995 4th Industrial Engineering Research Conference
CityNashville, TN, USA
Period5/24/955/25/95

Fingerprint

Inspection
Neural networks
Defects
Classifiers
Castings

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Cite this

Kim, T., & Tirupatikumara, S. R. (1995). Automated visual inspection and classification using neural networks. In Industrial Engineering Research - Conference Proceedings (pp. 286-294). IIE.
Kim, Taioun ; Tirupatikumara, Soundar Rajan. / Automated visual inspection and classification using neural networks. Industrial Engineering Research - Conference Proceedings. IIE, 1995. pp. 286-294
@inproceedings{2fe2a5ebc403472dab74b6490f536537,
title = "Automated visual inspection and classification using neural networks",
abstract = "This research presents schemes for automated visual inspection for boundary defects and classification using neural networks. An efficient method for representing circular boundaries is proposed utilizing a curvature and circular fitting algorithm. For the classification schemes, two types of neural network models are established. First, a multi-layer perception is discussed for defect classification problems. Second, a Hopfield network is modeled to be used for continuous-type variables by minimizing the energy function. Extensive tests are conducted on castings, then the results of neural networks are compared with those of traditional pattern classifiers.",
author = "Taioun Kim and Tirupatikumara, {Soundar Rajan}",
year = "1995",
language = "English (US)",
pages = "286--294",
booktitle = "Industrial Engineering Research - Conference Proceedings",
publisher = "IIE",

}

Kim, T & Tirupatikumara, SR 1995, Automated visual inspection and classification using neural networks. in Industrial Engineering Research - Conference Proceedings. IIE, pp. 286-294, Proceedings of the 1995 4th Industrial Engineering Research Conference, Nashville, TN, USA, 5/24/95.

Automated visual inspection and classification using neural networks. / Kim, Taioun; Tirupatikumara, Soundar Rajan.

Industrial Engineering Research - Conference Proceedings. IIE, 1995. p. 286-294.

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

TY - GEN

T1 - Automated visual inspection and classification using neural networks

AU - Kim, Taioun

AU - Tirupatikumara, Soundar Rajan

PY - 1995

Y1 - 1995

N2 - This research presents schemes for automated visual inspection for boundary defects and classification using neural networks. An efficient method for representing circular boundaries is proposed utilizing a curvature and circular fitting algorithm. For the classification schemes, two types of neural network models are established. First, a multi-layer perception is discussed for defect classification problems. Second, a Hopfield network is modeled to be used for continuous-type variables by minimizing the energy function. Extensive tests are conducted on castings, then the results of neural networks are compared with those of traditional pattern classifiers.

AB - This research presents schemes for automated visual inspection for boundary defects and classification using neural networks. An efficient method for representing circular boundaries is proposed utilizing a curvature and circular fitting algorithm. For the classification schemes, two types of neural network models are established. First, a multi-layer perception is discussed for defect classification problems. Second, a Hopfield network is modeled to be used for continuous-type variables by minimizing the energy function. Extensive tests are conducted on castings, then the results of neural networks are compared with those of traditional pattern classifiers.

UR - http://www.scopus.com/inward/record.url?scp=0029425560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029425560&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029425560

SP - 286

EP - 294

BT - Industrial Engineering Research - Conference Proceedings

PB - IIE

ER -

Kim T, Tirupatikumara SR. Automated visual inspection and classification using neural networks. In Industrial Engineering Research - Conference Proceedings. IIE. 1995. p. 286-294