9 Citations (Scopus)

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 classification, two types of neural network modelling schemes are established. First, a multi-layer perceptron is discussed for defect classification problems. Second, a Hopfield network is modelled to be used for continuous-type variables by a minimizing energy function. Extensive tests are conducted on the casting parts, then the results of neural networks are compared with those of traditional pattern classifiers.

Original languageEnglish (US)
Pages (from-to)2397-2412
Number of pages16
JournalInternational Journal of Production Research
Volume35
Issue number9
DOIs
StatePublished - Jan 1 1997

Fingerprint

Neural networks
Defects
Multilayer neural networks
Casting
Classifiers
Inspection
Curvature
Classifier
Energy
Modeling

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

@article{a5292591931e4e30b3222178dd7f8b68,
title = "Boundary defect recognition 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 classification, two types of neural network modelling schemes are established. First, a multi-layer perceptron is discussed for defect classification problems. Second, a Hopfield network is modelled to be used for continuous-type variables by a minimizing energy function. Extensive tests are conducted on the casting parts, then the results of neural networks are compared with those of traditional pattern classifiers.",
author = "T. Kim and Tirupatikumara, {Soundar Rajan}",
year = "1997",
month = "1",
day = "1",
doi = "10.1080/002075497194561",
language = "English (US)",
volume = "35",
pages = "2397--2412",
journal = "International Journal of Production Research",
issn = "0020-7543",
publisher = "Taylor and Francis Ltd.",
number = "9",

}

Boundary defect recognition using neural networks. / Kim, T.; Tirupatikumara, Soundar Rajan.

In: International Journal of Production Research, Vol. 35, No. 9, 01.01.1997, p. 2397-2412.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Boundary defect recognition using neural networks

AU - Kim, T.

AU - Tirupatikumara, Soundar Rajan

PY - 1997/1/1

Y1 - 1997/1/1

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 classification, two types of neural network modelling schemes are established. First, a multi-layer perceptron is discussed for defect classification problems. Second, a Hopfield network is modelled to be used for continuous-type variables by a minimizing energy function. Extensive tests are conducted on the casting parts, 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 classification, two types of neural network modelling schemes are established. First, a multi-layer perceptron is discussed for defect classification problems. Second, a Hopfield network is modelled to be used for continuous-type variables by a minimizing energy function. Extensive tests are conducted on the casting parts, then the results of neural networks are compared with those of traditional pattern classifiers.

UR - http://www.scopus.com/inward/record.url?scp=0031234729&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031234729&partnerID=8YFLogxK

U2 - 10.1080/002075497194561

DO - 10.1080/002075497194561

M3 - Article

AN - SCOPUS:0031234729

VL - 35

SP - 2397

EP - 2412

JO - International Journal of Production Research

JF - International Journal of Production Research

SN - 0020-7543

IS - 9

ER -