Automatic label removal from digitized weld radiographs

This paper presents a methodology to remove labels automatically from digitized weld radiographs as part of the automatic weld defect detection process. An algorithm was developed to detect and remove labels printed onto weld radiographs before weld extraction algorithm or defect detection algorithm...

Full description

Bibliographic Details
Main Authors: Soo, Say Leong, Ratnam, Mani Maran, Samad, Zahurin, Khalid, Mohd. Ashhar
Format: Article
Language:English
Published: Penerbit UTM Press 2007
Subjects:
Online Access:http://eprints.utm.my/6200/1/JTDIS47D01.pdf
_version_ 1825909857850490880
author Soo, Say Leong
Ratnam, Mani Maran
Samad, Zahurin
Khalid, Mohd. Ashhar
author_facet Soo, Say Leong
Ratnam, Mani Maran
Samad, Zahurin
Khalid, Mohd. Ashhar
author_sort Soo, Say Leong
collection ePrints
description This paper presents a methodology to remove labels automatically from digitized weld radiographs as part of the automatic weld defect detection process. An algorithm was developed to detect and remove labels printed onto weld radiographs before weld extraction algorithm or defect detection algorithm is applied. Normality test was used to determine if the intensity profile parallel to the weld contains label pixels. Thresholding followed by region filling operations were carried out to remove the labels. The algorithm was tested on 50 weld radiographs with labels and the labels on 90% of these images were successfully removed.
first_indexed 2024-03-05T18:08:24Z
format Article
id utm.eprints-6200
institution Universiti Teknologi Malaysia - ePrints
language English
last_indexed 2024-03-05T18:08:24Z
publishDate 2007
publisher Penerbit UTM Press
record_format dspace
spelling utm.eprints-62002017-11-01T04:17:25Z http://eprints.utm.my/6200/ Automatic label removal from digitized weld radiographs Soo, Say Leong Ratnam, Mani Maran Samad, Zahurin Khalid, Mohd. Ashhar TJ Mechanical engineering and machinery This paper presents a methodology to remove labels automatically from digitized weld radiographs as part of the automatic weld defect detection process. An algorithm was developed to detect and remove labels printed onto weld radiographs before weld extraction algorithm or defect detection algorithm is applied. Normality test was used to determine if the intensity profile parallel to the weld contains label pixels. Thresholding followed by region filling operations were carried out to remove the labels. The algorithm was tested on 50 weld radiographs with labels and the labels on 90% of these images were successfully removed. Penerbit UTM Press 2007-12 Article PeerReviewed application/pdf en http://eprints.utm.my/6200/1/JTDIS47D01.pdf Soo, Say Leong and Ratnam, Mani Maran and Samad, Zahurin and Khalid, Mohd. Ashhar (2007) Automatic label removal from digitized weld radiographs. Jurnal Teknologi D . pp. 1-14. ISSN 0127-9696 http://www.penerbit.utm.my/onlinejournal/47/D/JTDIS47D01.pdf
spellingShingle TJ Mechanical engineering and machinery
Soo, Say Leong
Ratnam, Mani Maran
Samad, Zahurin
Khalid, Mohd. Ashhar
Automatic label removal from digitized weld radiographs
title Automatic label removal from digitized weld radiographs
title_full Automatic label removal from digitized weld radiographs
title_fullStr Automatic label removal from digitized weld radiographs
title_full_unstemmed Automatic label removal from digitized weld radiographs
title_short Automatic label removal from digitized weld radiographs
title_sort automatic label removal from digitized weld radiographs
topic TJ Mechanical engineering and machinery
url http://eprints.utm.my/6200/1/JTDIS47D01.pdf
work_keys_str_mv AT soosayleong automaticlabelremovalfromdigitizedweldradiographs
AT ratnammanimaran automaticlabelremovalfromdigitizedweldradiographs
AT samadzahurin automaticlabelremovalfromdigitizedweldradiographs
AT khalidmohdashhar automaticlabelremovalfromdigitizedweldradiographs