Defect detection in thermal image using thresholding technique

This paper proposes a technique to detect defects as depicted in a thermal image. The technique is based on a local neighborhood pixel operation using kernel window 3x3. All pixels within this window will be mapped to only a single pixel value. Next, the thresholding technique is used. The main focu...

Full description

Bibliographic Details
Main Authors: Heriansyah, Rudi, Syed Abu Bakar, Syed Abdul Rahman
Format: Conference or Workshop Item
Published: 2007
Subjects:
Online Access:http://eprints.utm.my/8630/
_version_ 1848891729371987968
author Heriansyah, Rudi
Syed Abu Bakar, Syed Abdul Rahman
author_facet Heriansyah, Rudi
Syed Abu Bakar, Syed Abdul Rahman
author_sort Heriansyah, Rudi
building UTeM Institutional Repository
collection Online Access
description This paper proposes a technique to detect defects as depicted in a thermal image. The technique is based on a local neighborhood pixel operation using kernel window 3x3. All pixels within this window will be mapped to only a single pixel value. Next, the thresholding technique is used. The main focus of the employed thresholding technique is the popular Otsu method and testing with other global thresholding technique is also given in the text. From the results obtained, it is shown that the proposed method is able to detect defects occur in a thermal image using any standard thresholding technique which is not designed for thermal images. The technique is easy to implement yet the result is promising.
first_indexed 2025-11-15T21:02:36Z
format Conference or Workshop Item
id utm-8630
institution Universiti Teknologi Malaysia
institution_category Local University
last_indexed 2025-11-15T21:02:36Z
publishDate 2007
recordtype eprints
repository_type Digital Repository
spelling utm-86302009-07-27T05:01:21Z http://eprints.utm.my/8630/ Defect detection in thermal image using thresholding technique Heriansyah, Rudi Syed Abu Bakar, Syed Abdul Rahman TK Electrical engineering. Electronics Nuclear engineering This paper proposes a technique to detect defects as depicted in a thermal image. The technique is based on a local neighborhood pixel operation using kernel window 3x3. All pixels within this window will be mapped to only a single pixel value. Next, the thresholding technique is used. The main focus of the employed thresholding technique is the popular Otsu method and testing with other global thresholding technique is also given in the text. From the results obtained, it is shown that the proposed method is able to detect defects occur in a thermal image using any standard thresholding technique which is not designed for thermal images. The technique is easy to implement yet the result is promising. 2007 Conference or Workshop Item PeerReviewed Heriansyah, Rudi and Syed Abu Bakar, Syed Abdul Rahman (2007) Defect detection in thermal image using thresholding technique. In: 6th WSEAS International Conference on Circuits, Systems, Electrnics, Control & Signal Processing (CSECS'07).
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Heriansyah, Rudi
Syed Abu Bakar, Syed Abdul Rahman
Defect detection in thermal image using thresholding technique
title Defect detection in thermal image using thresholding technique
title_full Defect detection in thermal image using thresholding technique
title_fullStr Defect detection in thermal image using thresholding technique
title_full_unstemmed Defect detection in thermal image using thresholding technique
title_short Defect detection in thermal image using thresholding technique
title_sort defect detection in thermal image using thresholding technique
topic TK Electrical engineering. Electronics Nuclear engineering
url http://eprints.utm.my/8630/