Discontinuities detection in welded joints based on inverse surface thresholding

Haniza Yazid, H. Arof, Hafizal Yazid, Sahrim Ahmad, A. A. Mohamed, F. Ahmad

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Automated detection of welding defects in radiographic images becomes nontrivial when uneven illumination, contrast and noise are present. In this paper, a new approach using surface thresholding method is proposed to detect defects in radiographic images of welding joints. In the first stage, several image processing techniques namely fuzzy c means clustering, region filling, mean filtering, edge detection, Otsu thresholding, and morphological operations method are utilized to locate the area where defects might exist. This is followed by the construction of the inverse thresholding surface and its implementation to locate defects in the identified area. The proposed method was tested on 60 radiographic images and it obtained 94.6% sensitivity. Its performance is compared to that of the watershed segmentation, which obtained 69.6%.

Original languageEnglish
Pages (from-to)563-570
Number of pages8
JournalNDT and E International
Volume44
Issue number7
DOIs
Publication statusPublished - Nov 2011
Externally publishedYes

Fingerprint

welded joints
discontinuity
Welds
Defects
defects
welding
Welding
edge detection
Edge detection
Watersheds
image processing
Image processing
Lighting
illumination
sensitivity

Keywords

  • Fuzzy c means clustering
  • Inverse surface thresholding
  • Non-destructive testing
  • Welded joints

ASJC Scopus subject areas

  • Materials Science(all)
  • Mechanical Engineering
  • Condensed Matter Physics

Cite this

Discontinuities detection in welded joints based on inverse surface thresholding. / Yazid, Haniza; Arof, H.; Yazid, Hafizal; Ahmad, Sahrim; Mohamed, A. A.; Ahmad, F.

In: NDT and E International, Vol. 44, No. 7, 11.2011, p. 563-570.

Research output: Contribution to journalArticle

Yazid, Haniza ; Arof, H. ; Yazid, Hafizal ; Ahmad, Sahrim ; Mohamed, A. A. ; Ahmad, F. / Discontinuities detection in welded joints based on inverse surface thresholding. In: NDT and E International. 2011 ; Vol. 44, No. 7. pp. 563-570.
@article{242c2f32be1b4a89b0bb15f5020c609a,
title = "Discontinuities detection in welded joints based on inverse surface thresholding",
abstract = "Automated detection of welding defects in radiographic images becomes nontrivial when uneven illumination, contrast and noise are present. In this paper, a new approach using surface thresholding method is proposed to detect defects in radiographic images of welding joints. In the first stage, several image processing techniques namely fuzzy c means clustering, region filling, mean filtering, edge detection, Otsu thresholding, and morphological operations method are utilized to locate the area where defects might exist. This is followed by the construction of the inverse thresholding surface and its implementation to locate defects in the identified area. The proposed method was tested on 60 radiographic images and it obtained 94.6{\%} sensitivity. Its performance is compared to that of the watershed segmentation, which obtained 69.6{\%}.",
keywords = "Fuzzy c means clustering, Inverse surface thresholding, Non-destructive testing, Welded joints",
author = "Haniza Yazid and H. Arof and Hafizal Yazid and Sahrim Ahmad and Mohamed, {A. A.} and F. Ahmad",
year = "2011",
month = "11",
doi = "10.1016/j.ndteint.2011.06.002",
language = "English",
volume = "44",
pages = "563--570",
journal = "NDT and E International",
issn = "0963-8695",
publisher = "Elsevier Limited",
number = "7",

}

TY - JOUR

T1 - Discontinuities detection in welded joints based on inverse surface thresholding

AU - Yazid, Haniza

AU - Arof, H.

AU - Yazid, Hafizal

AU - Ahmad, Sahrim

AU - Mohamed, A. A.

AU - Ahmad, F.

PY - 2011/11

Y1 - 2011/11

N2 - Automated detection of welding defects in radiographic images becomes nontrivial when uneven illumination, contrast and noise are present. In this paper, a new approach using surface thresholding method is proposed to detect defects in radiographic images of welding joints. In the first stage, several image processing techniques namely fuzzy c means clustering, region filling, mean filtering, edge detection, Otsu thresholding, and morphological operations method are utilized to locate the area where defects might exist. This is followed by the construction of the inverse thresholding surface and its implementation to locate defects in the identified area. The proposed method was tested on 60 radiographic images and it obtained 94.6% sensitivity. Its performance is compared to that of the watershed segmentation, which obtained 69.6%.

AB - Automated detection of welding defects in radiographic images becomes nontrivial when uneven illumination, contrast and noise are present. In this paper, a new approach using surface thresholding method is proposed to detect defects in radiographic images of welding joints. In the first stage, several image processing techniques namely fuzzy c means clustering, region filling, mean filtering, edge detection, Otsu thresholding, and morphological operations method are utilized to locate the area where defects might exist. This is followed by the construction of the inverse thresholding surface and its implementation to locate defects in the identified area. The proposed method was tested on 60 radiographic images and it obtained 94.6% sensitivity. Its performance is compared to that of the watershed segmentation, which obtained 69.6%.

KW - Fuzzy c means clustering

KW - Inverse surface thresholding

KW - Non-destructive testing

KW - Welded joints

UR - http://www.scopus.com/inward/record.url?scp=79959704000&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959704000&partnerID=8YFLogxK

U2 - 10.1016/j.ndteint.2011.06.002

DO - 10.1016/j.ndteint.2011.06.002

M3 - Article

AN - SCOPUS:79959704000

VL - 44

SP - 563

EP - 570

JO - NDT and E International

JF - NDT and E International

SN - 0963-8695

IS - 7

ER -