Share Email Print

Proceedings Paper

Automatic defect detection
Author(s): Guylaine Daillant; Dominique Micollet; Michel Paindavoine
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We propose in this article a complete acquisition and processing line of weld radiographies, from which must be highlighted cavity shaped defects. The main features of the films are a high optical density, a strong inhomogeneous background in both directions and a weak contrast. We present the study of three trend removal methods (least square fitting, Fourier smoothing and adjustment splines) allowing to improve the signal/noise ratio of the edges pictures. The segmentation is derived from the edges picture by the mean of a constrained watershed algorithm. The constraints are deduced in an automatic way from the shape of the histogram.

Paper Details

Date Published: 26 August 1996
PDF: 11 pages
Proc. SPIE 2785, Vision Systems: New Image Processing Techniques, (26 August 1996); doi: 10.1117/12.248533
Show Author Affiliations
Guylaine Daillant, Univ. de Bourgogne (France)
Dominique Micollet, Univ. de Bourgogne (France)
Michel Paindavoine, Univ. de Bourgogne (France)

Published in SPIE Proceedings Vol. 2785:
Vision Systems: New Image Processing Techniques
Philippe Refregier, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?