Unsupervised segmentation of surface defects

Author

Iivarinen, Jukka ; Rauhamaa, Juhani ; Visa, Ari

Author_Institution

Lab. of Comput. & Inf. Sci., Helsinki Univ. of Technol., Espoo, Finland

Volume

4

fYear

1996

fDate

25-29 Aug 1996

Firstpage

356

Abstract

A segmentation scheme to detect surface defects is proposed. An unsupervised neural network, the self-organizing map, is used to estimate the distribution of fault-free samples. An unknown sample is classified as a defect if it differs enough from this estimated distribution. A new scheme for determining this difference is suggested. The scheme makes use of the Voronoi set of each map unit and defines a new rule for finding the best-matching map unit. The proposed scheme is general in the sense that it can be applied to fault detection of different types of surfaces

Keywords

automatic optical inspection; computational geometry; flaw detection; image segmentation; self-organising feature maps; Voronoi set; fault-free sample distribution estimation; self-organizing map; surface defect detection; unsupervised neural network; unsupervised segmentation; Fault detection; Feature extraction; Image segmentation; Inspection; Laboratories; Monitoring; Neural networks; Organizing; Paper technology; Pixel;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1996., Proceedings of the 13th International Conference on

Conference_Location

Vienna

ISSN

1051-4651

Print_ISBN

0-8186-7282-X

Type

conf

DOI

10.1109/ICPR.1996.547445

Filename

547445