Skip to main content

Research Repository

Advanced Search

Impact of object extraction methods on classification performance in surface inspection systems

Raiser, Stefan; Lughofer, Edwin; Eitzinger, Christian; Smith, Jim

Impact of object extraction methods on classification performance in surface inspection systems Thumbnail


Authors

Stefan Raiser

Edwin Lughofer

Christian Eitzinger

Profile Image

Jim Smith James.Smith@uwe.ac.uk
Professor in Interactive Artificial Intelligence



Abstract

In surface inspection applications, the main goal is to detect all areas which might contain defects or unacceptable imperfections, and to classify either every single 'suspicious' region or the investigated part as a whole. After an image is acquired by the machine vision hardware, all pixels that deviate from a pre-defined 'ideal' master image are set to a non-zero value, depending on the magnitude of deviation. This procedure leads to so-called "contrast images", in which accumulations of bright pixels may appear, representing potentially defective areas. In this paper, various methods are presented for grouping these bright pixels together into meaningful objects, ranging from classical image processing techniques to machine-learning-based clustering approaches. One important issue here is to find reasonable groupings even for non-connected and widespread objects. In general, these objects correspond either to real faults or to pseudo-errors that do not affect the surface quality at all. The impact of different extraction methods on the accuracy of image classifiers will be studied. The classifiers are trained with feature vectors calculated for the extracted objects found in images labeled by the user and showing surfaces of production items. In our investigation artificially created contrast images will be considered as well as real ones recorded on-line at a CD imprint production and at an egg inspection system. © Springer-Verlag 2009.

Citation

Raiser, S., Lughofer, E., Eitzinger, C., & Smith, J. (2010). Impact of object extraction methods on classification performance in surface inspection systems. Machine Vision and Applications, 21(5), 627-641. https://doi.org/10.1007/s00138-009-0205-z

Journal Article Type Article
Publication Date Aug 1, 2010
Deposit Date Aug 25, 2010
Publicly Available Date Nov 15, 2016
Journal Machine Vision and Applications
Print ISSN 0932-8092
Electronic ISSN 1432-1769
Publisher Springer Verlag
Peer Reviewed Peer Reviewed
Volume 21
Issue 5
Pages 627-641
DOI https://doi.org/10.1007/s00138-009-0205-z
Keywords object extraction methods, classification performance, surface inspection systems
Public URL https://uwe-repository.worktribe.com/output/976600
Publisher URL http://dx.doi.org/10.1007/s00138-009-0205-z
Related Public URLs http://www.springerlink.com/content/g1613x4147420l23/

Files







You might also like



Downloadable Citations