Share Email Print

Proceedings Paper

Surface defect detection using adaptive image modeling
Author(s): Philippe Salembier
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper deals with surface defect detection. The approach investigated here attempts to detect grey level as well as texture defects. The defects are regarded as being characterized by abrupt, local and unpredictable changes in an image. On the other hand, a defect-free surface is assumed to be regular and homogeneous, possibly with smooth and slow variation in its features. The detection is based on adaptive image modeling. It is shown that a classical autoregressive model is not really suitable for this detection problem. Then, two modified models are proposed. Their advantage lies in their taking into account the grey level value as well as the texture information.The model adaptation can be stated as a joint optimization problem with constraint. Two different algorithms are defined and tested. The first algorithm performs the adaptation in a recursive way while enforcing the constraint at each step, whereas the second one imposes the constraint only at optimum. The performance of each algorithms is assessed with a statistical test using synthetic images. Finally, it is shown how this adaptive modeling technique can be applied to practical defect detection problems. Several cases are presented and discussed.

Paper Details

Date Published: 1 September 1990
PDF: 12 pages
Proc. SPIE 1360, Visual Communications and Image Processing '90: Fifth in a Series, (1 September 1990); doi: 10.1117/12.24140
Show Author Affiliations
Philippe Salembier, Swiss Federal Institute of Technology (Switzerland)

Published in SPIE Proceedings Vol. 1360:
Visual Communications and Image Processing '90: Fifth in a Series
Murat Kunt, Editor(s)

© SPIE. Terms of Use
Back to Top