Title :
Defects in a weld: a complete radiographies processing line
Author :
Daillant, Guylaine ; Micollet, Dominique ; Paindavoine, Michel
Author_Institution :
Lab. LIESIB, Bourgogne Univ., Dijon, France
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 allowing improvement of 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
Keywords :
automatic optical inspection; computer vision; edge detection; image segmentation; radiography; welding; acquisition line; cavity shaped defects; constrained watershed algorithm; edges pictures; high optical density; radiographies processing line; segmentation; signal/noise ratio; strong inhomogeneous background; trend removal methods; weak contrast; weld defects; Detectors; Filters; Image edge detection; Least squares methods; Noise shaping; Optical films; Polynomials; Radiography; Signal to noise ratio; Welding;
Conference_Titel :
Industrial Electronics, Control, and Instrumentation, 1996., Proceedings of the 1996 IEEE IECON 22nd International Conference on
Conference_Location :
Taipei
Print_ISBN :
0-7803-2775-6
DOI :
10.1109/IECON.1996.565966
