Advanced

A parametrisable system for physically plausible surface inspection

Grunditz, CH and Spaanenburg, Lambert LU (2004) In Journal of Intelligent & Fuzzy Systems 15(1). p.29-39
Abstract
Visual quality assurance techniques focus on the detection and qualification of abnormal structures in the image of an object. The features of abnormality are extracted through image mining, whereupon classification is performed on characteristic combinations. Many techniques for feature extraction have been proposed, but the feed-forward neural network is seldom utilized despite its popularity in other application areas. Based on the wide experience base, this paper shows how a multi-tier feed-forward network can be constructed to model detectable peaks using only the physical properties of the image domain. This generic architecture can easily be adapted for different applications, as in metal plate inspection and protein detection, with... (More)
Visual quality assurance techniques focus on the detection and qualification of abnormal structures in the image of an object. The features of abnormality are extracted through image mining, whereupon classification is performed on characteristic combinations. Many techniques for feature extraction have been proposed, but the feed-forward neural network is seldom utilized despite its popularity in other application areas. Based on the wide experience base, this paper shows how a multi-tier feed-forward network can be constructed to model detectable peaks using only the physical properties of the image domain. This generic architecture can easily be adapted for different applications, as in metal plate inspection and protein detection, with mean error rate below 5%. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Journal of Intelligent & Fuzzy Systems
volume
15
issue
1
pages
29 - 39
publisher
IOS Press
external identifiers
  • wos:000226874700005
  • scopus:10044265439
ISSN
1064-1246
language
English
LU publication?
yes
id
65232bfc-a18c-478c-b8e1-6f7a514ea6ef (old id 254344)
date added to LUP
2007-08-02 13:52:56
date last changed
2017-01-01 07:22:40
@article{65232bfc-a18c-478c-b8e1-6f7a514ea6ef,
  abstract     = {Visual quality assurance techniques focus on the detection and qualification of abnormal structures in the image of an object. The features of abnormality are extracted through image mining, whereupon classification is performed on characteristic combinations. Many techniques for feature extraction have been proposed, but the feed-forward neural network is seldom utilized despite its popularity in other application areas. Based on the wide experience base, this paper shows how a multi-tier feed-forward network can be constructed to model detectable peaks using only the physical properties of the image domain. This generic architecture can easily be adapted for different applications, as in metal plate inspection and protein detection, with mean error rate below 5%.},
  author       = {Grunditz, CH and Spaanenburg, Lambert},
  issn         = {1064-1246},
  language     = {eng},
  number       = {1},
  pages        = {29--39},
  publisher    = {IOS Press},
  series       = {Journal of Intelligent & Fuzzy Systems},
  title        = {A parametrisable system for physically plausible surface inspection},
  volume       = {15},
  year         = {2004},
}