Advanced

Constructing a neural system for surface inspection

Grunditz, C.; Walder, M and Spaanenburg, Lambert LU (2004) 2004 IEEE International Joint Conference on Neural Networks (IJCNN) In 2004 IEEE International Joint Conference on Neural Networks p.1881-1886
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 this 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,... (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 this 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
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
feature extraction, image mining, image classification, object image detection, visual quality assurance techniques, surface inspection, neural system, protein detection, multiple tier feedforward neural network, metal plate inspection
in
2004 IEEE International Joint Conference on Neural Networks
pages
1881 - 1886
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
2004 IEEE International Joint Conference on Neural Networks (IJCNN)
external identifiers
  • WOS:000224941900326
  • Scopus:10844252252
ISBN
0-7803-8359-1
language
English
LU publication?
yes
id
1e6e35db-fa32-42a0-822f-f735ecae2455 (old id 614849)
alternative location
http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1380897
date added to LUP
2007-11-26 18:55:26
date last changed
2016-10-13 04:43:51
@misc{1e6e35db-fa32-42a0-822f-f735ecae2455,
  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 this 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, C. and Walder, M and Spaanenburg, Lambert},
  isbn         = {0-7803-8359-1},
  keyword      = {feature extraction,image mining,image classification,object image detection,visual quality assurance techniques,surface inspection,neural system,protein detection,multiple tier feedforward neural network,metal plate inspection},
  language     = {eng},
  pages        = {1881--1886},
  publisher    = {ARRAY(0x9b211f0)},
  series       = {2004 IEEE International Joint Conference on Neural Networks},
  title        = {Constructing a neural system for surface inspection},
  year         = {2004},
}