Unsupervised segmentation of surface defects

  title={Unsupervised segmentation of surface defects},
  author={Jukka Iivarinen and Juhani Rauhamaa and Ari Visa},
A segmentation scheme to detect surface defects is proposed. An unsupervised neural network, the SelfOrganizing Map, is used to estimate the distribution of faulty-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… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 23 extracted citations


Publications referenced by this paper.
Showing 1-10 of 17 references

Unsupervised Image Segmentation Based on a Sel forganizing Feature Map and a Texture Measure

  • A. Visa
  • Proceedings of 11th IAPR International Conference…
  • 1992
Highly Influential
4 Excerpts

Map and Reduced Kernel Density Estimation

  • A. Hämäläinen.Self-Organizing
  • PhD thesis,
  • 1995
1 Excerpt

Representation and Identification of Fault Conditions of an Anaesthesia System by Means of the Self-Organizing Map

  • M. Vapola, O. Simula, T. Kohonen, P. Meriläinen
  • In Proceedings of the International Conference on…
  • 1994
1 Excerpt

A Two-Stage Classifier for Wood Boards

  • I. Yläkoski, A. Visa
  • InProceedings of The 8th Scandinavian Conference…
  • 1993
1 Excerpt

Boyle.Image Processing, Analysis and Machine Vision

  • M. Sonka, V. Hlavac
  • Chapman & Hall Computing,
  • 1993
1 Excerpt

Process State Monitoring Using Self-Organizing Maps

  • M. Kasslin, J. Kangas, O. Simula
  • editors,Artificial Neural Networks,
  • 1992
1 Excerpt

Shapiro.Computer and Robot Vision, volume 1

  • L.G.R.M. Haralick
  • 1992
1 Excerpt

Texture Measur es for Surface Inspection

  • T. Ojala, M. Pietikäinen, O. Silven
  • In11th International Conference in Pattern…
  • 1992
1 Excerpt

Process Error Detection Using Self-Organizing Feature Maps

  • J. T. Alander, M. Frisk, L. Holmström
  • A tificial Neural Networks ,
  • 1991
2 Excerpts

Self-Organizing Feature Maps for Process Control in Chemistry

  • V. Tryba, K. Goser
  • Artificial Neural Networks,
  • 1991
2 Excerpts

Similar Papers

Loading similar papers…