Automatic weld bead extraction from digitised radiographs using grey level intensity profiles and least-squares fitting
Weld bead segmentation is an important precursor to automatic detection of weld defects in digitised radiographs. This paper presents a simple and effective approach for the segmentation of the weld bead from a digitised weld radiograph using grey level intensity profles. The intensity profles were extracted across the weld and divided into two parts based on the maximum intensity. Least-squares lines were ftted to the data points in each half of the profle using a predefned range threshold. Using an error threshold, the weld bead boundary points were detected. For radiographs having undercut defects, an alternative approach based on a straight line connecting the minimum trough intensity pixel and the maximum distance from the original profle is proposed. The weld bead segmentation algorithm has been successfully tested on 30 digitised weld radiographs having various defects.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Affiliations: 1 School of Mechanical Engineering, Engineering Campus, Universiti Sains Malaysia, 14300 Nibong Tebal, Penang, Malaysia.
Publication date: January 1, 2008
More about this publication?
- Official Journal of The British Institute of Non-Destructive Testing - includes original research and devlopment papers, technical and scientific reviews and case studies in the fields of NDT and CM.
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Information for Advertisers
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites