By Topic

Automatic defect detection in X-ray images using image data fusion

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
5 Author(s)
Tian, Yuan ; Key Laboratory for Advanced Materials Processing Technology of Ministry of Education, Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China ; Du, Dong ; Cai, Guorui ; Wang, Li
more authors

Automatic defect detection in X-ray images is currently a focus of much research at home and abroad. The technology requires computerized image processing, image analysis, and pattern recognition. This paper describes an image processing method for automatic defect detection using image data fusion which synthesizes several methods including edge extraction, wave profile analyses, segmentation with dynamic threshold, and weld district extraction. Test results show that defects that induce an abrupt change over a predefined extent of the image intensity can be segmented regardless of the number, location, shape, or size. Thus, the method is more robust and practical than the current methods using only one method.

Published in:

Tsinghua Science and Technology  (Volume:11 ,  Issue: 6 )