Automated visual inspection and classification using neural networks

Research output: Contribution to conferencePaper

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)
Pages286-294
Number of pages9
StatePublished - Dec 1 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

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Automated visual inspection and classification using neural networks'. Together they form a unique fingerprint.

  • Cite this

    Kim, T., & Kumara, S. R. T. (1995). Automated visual inspection and classification using neural networks. 286-294. Paper presented at Proceedings of the 1995 4th Industrial Engineering Research Conference, Nashville, TN, USA, .