Skip to main content
padlock icon - secure page this page is secure

A novel method for detecting weld defects accurately and reliably in radiographic images

Buy Article:

$22.00 + tax (Refund Policy)

To improve the accuracy and reliability of detecting weld defects in radiographic images, we propose a novel defect detection method (ANDM) using the peak-valley index (PVI) and defect index (DI) that are first defined in this paper. In the proposed method, first a region of interest (ROI) is extracted from the entire weld radiographic image. Second, a profile curve of grey level intensity is yielded by a line across the weld ROI and its Bézier approximated curve is acquired. Then the Bézier approximated error between the above two curves is calculated by curve subtraction. Finally, the PVI and DI are obtained according to the characteristic analysis of the Bézier approximated curve and error. Using the PVI and DI, the existence of weld defects is successfully detected from the weld radiographic image. In order to evaluate the performance of the proposed method, we have performed some comparative experiments of detecting the various types of defect in manufacture. Moreover, the experimental results reveal that the proposed method achieves a successful detection rate of 98.5% and a false alarm rate of 2%, which shows a significant improvement on the accuracy and reliability of detecting weld defects in radiographic images.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics


Document Type: Research Article

Publication date: January 1, 2016

More about this publication?
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more