Constructing a neural system for surface inspection
Author
Editor
- Jacek Malec
Summary, in English
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%.
Publishing year
2004
Language
English
Pages
68-73
Publication/Series
SAIS Workshop
Document type
Conference paper
Publisher
SAIS
Topic
- Electrical Engineering, Electronic Engineering, Information Engineering
Conference name
Joint SAIS/SSLS Workshop, 2004
Conference date
2004-04-15 - 2004-04-16
Conference place
Lund, Sweden
Status
Published
Research group
- DISKA/DO:PING