Machine Vision Application For Automatic Defect Segmentation In Weld Radiographs
Loading...
Date
2006-04
Authors
SAY LEONG, SOO
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The objective of the research is to develop an automatic weld defect
segmentation methodology to segment different types of defects in radiographic
images of welds. The segmentation methodology consists of three main algorithms.
namely label removal algorithm. weld extraction algorithm and defect segmentation
algorithm. The label removal algorithm was developed to detect and remove labels that
are printed on weld radiographs automatically before weld extraction algorithm and
defect detection algorithm are applied. The weld extraction algorithm was developed to
locate and extract welds automatically from the intensity profiles taken across the
image by using graphical analysis. This algorithm was able to extract weld from a
radiograph regardless of whether the intensity profile is Gaussian or otherwise. This
method is an improvement compared to the previous weld extraction methods which
are limited to weld image with Gaussian intensity profiles. Finally. a defect
segmentation algorithm was developed to segment the defects automatically from the
image using background subtraction and rank leveling method. A comparative study on
weld radiograph image background estimation by rank leveling technique and
polynomial surface fitting algorithm was also carried out. The rank leveling technique
was found to yield better result compared to polynomial surface fitting algorithm in the
tested images. The developed automated defect segmentation methodology was
successfully tested on 30 weld radiographs. One main contribution of this research is
the development of an automatic label removal algorithm which. to the best of the
author's knowledge, no previous work has been published on this topic. The label
removal algorithm developed enables the application of the defect segmentation
methodology on weld radiographs which contains labels. Besides that, a weld
extraction methodology which improved the previous method was developed to extract
weld area across good as well as defective welds. Finally, an automatic defect
segmentation algorithm by rank leveling technique was developed to segment
defective area from non-uniformly \llIuminated weld radiographic images. The weld
extraction and defect segmentation algorithm proposed in this research are able to
process noisy and non-uniformly illuminated weld radiographic images.
Description
Keywords
Mechanical , Engineering