Change search
ReferencesLink to record
Permanent link

Direct link
An automatic assessment scheme for steel quality inspection
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.ORCID iD: 0000-0002-9081-2170
2000 (English)In: Machine Vision and Applications, ISSN 0932-8092, E-ISSN 1432-1769, Vol. 12, no 3, 113-128 p.Article in journal (Refereed) Published
Abstract [en]

This paper presents an automatic system for steel quality assessment, by measuring textural properties of carbide distributions. In current steel inspection, specially etched and polished steel specimen surfaces are classified manually under a light microscope, by comparisons with a standard chart. This procedure is basically two-dimensional, reflecting the size of the carbide agglomerations and their directional distribution. To capture these textural properties in terms of image features, we first apply a rich set of image-processing operations, including mathematical morphology, multi-channel Gabor filtering, and the computation of texture measures with automatic scale selection in linear scale-space. Then, a feature selector is applied to a 40-dimensional feature space, and a classification scheme is defined, which on a sample set of more than 400 images has classification performance values comparable to those of human metallographers. Finally, a fully automatic inspection system is designed, which actively selects the most salient carbide structure on the specimen surface for subsequent classification. The feasibility of the overall approach for future use in the production process is demonstrated by a prototype system. It is also shown how the presented classification scheme allows for the definition of a new reference chart in terms of quantitative measures.

Place, publisher, year, edition, pages
2000. Vol. 12, no 3, 113-128 p.
Keyword [en]
multi-scale analysis, automatic scale selection, multi-channel texture analysis, active inspection system, carbide classification, texture segmentation, filters, images, scale
National Category
Computer Science
URN: urn:nbn:se:kth:diva-20110DOI: 10.1007/s001380050130ISI: 000089927000002OAI: diva2:338803

QC 20100525

Available from: 2013-04-05 Created: 2010-08-10 Last updated: 2013-04-05Bibliographically approved

Open Access in DiVA

fulltext(1051 kB)103 downloads
File information
File name FULLTEXT01.pdfFile size 1051 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Lindeberg, Tony
By organisation
Numerical Analysis and Computer Science, NADA
In the same journal
Machine Vision and Applications
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 103 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 89 hits
ReferencesLink to record
Permanent link

Direct link