A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging
X-ray computed tomography (CT) is a powerful imaging tool for defect detection, segmentation and feature extraction in industrial applications as it enables non-destructive evaluation. The presence of artifacts and noise, however, imposes difficulties on the defect detection due to low contrast bet...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | deu |
| Published: |
NDT.net
2025-02-01
|
| Series: | e-Journal of Nondestructive Testing |
| Online Access: | https://www.ndt.net/search/docs.php3?id=30735 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832086592581271552 |
|---|---|
| author | Virginia Florian Jiayang Shi Willem Jan Palestijn Daniël M. Pelt K. Joost Batenburg Thomas Lang Christoph Heinzl Christian Kretzer Stefan Kasperl Dominik Wolfschläger Robert H. Schmitt |
| author_facet | Virginia Florian Jiayang Shi Willem Jan Palestijn Daniël M. Pelt K. Joost Batenburg Thomas Lang Christoph Heinzl Christian Kretzer Stefan Kasperl Dominik Wolfschläger Robert H. Schmitt |
| author_sort | Virginia Florian |
| collection | DOAJ |
| description |
X-ray computed tomography (CT) is a powerful imaging tool for defect detection, segmentation and feature extraction in industrial applications as it enables non-destructive evaluation. The presence of artifacts and noise, however, imposes difficulties on the defect detection due to low contrast between defects and material. Different methods, the most recent ones based on deep learning, have been proposed to address both CT artifacts and noise. In this work, three state-of-the-art denoising techniques, namely BM3D, a supervised UNet and Noise2Inverse are compared with a novel approach based on a set of CNNs applied at different stages of the CT data acquisition pipeline. The comparison is done regarding the capabilities of the methods in terms of image quality enhancement as a preprocessing step in CT-based data analysis before performing defect segmentation.
|
| format | Article |
| id | doaj-art-b340c2403bd64bfb928bf40ab748c580 |
| institution | Kabale University |
| issn | 1435-4934 |
| language | deu |
| publishDate | 2025-02-01 |
| publisher | NDT.net |
| record_format | Article |
| series | e-Journal of Nondestructive Testing |
| spelling | doaj-art-b340c2403bd64bfb928bf40ab748c5802025-02-06T10:48:19ZdeuNDT.nete-Journal of Nondestructive Testing1435-49342025-02-0130210.58286/30735A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT ImagingVirginia FlorianJiayang ShiWillem Jan PalestijnDaniël M. PeltK. Joost BatenburgThomas Langhttps://orcid.org/0000-0001-5939-3919Christoph Heinzlhttps://orcid.org/0000-0002-3173-8871Christian KretzerStefan Kasperlhttps://orcid.org/0000-0002-8118-7609Dominik Wolfschlägerhttps://orcid.org/0000-0003-2399-4856Robert H. Schmitthttps://orcid.org/0000-0002-0011-5962 X-ray computed tomography (CT) is a powerful imaging tool for defect detection, segmentation and feature extraction in industrial applications as it enables non-destructive evaluation. The presence of artifacts and noise, however, imposes difficulties on the defect detection due to low contrast between defects and material. Different methods, the most recent ones based on deep learning, have been proposed to address both CT artifacts and noise. In this work, three state-of-the-art denoising techniques, namely BM3D, a supervised UNet and Noise2Inverse are compared with a novel approach based on a set of CNNs applied at different stages of the CT data acquisition pipeline. The comparison is done regarding the capabilities of the methods in terms of image quality enhancement as a preprocessing step in CT-based data analysis before performing defect segmentation. https://www.ndt.net/search/docs.php3?id=30735 |
| spellingShingle | Virginia Florian Jiayang Shi Willem Jan Palestijn Daniël M. Pelt K. Joost Batenburg Thomas Lang Christoph Heinzl Christian Kretzer Stefan Kasperl Dominik Wolfschläger Robert H. Schmitt A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging e-Journal of Nondestructive Testing |
| title | A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging |
| title_full | A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging |
| title_fullStr | A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging |
| title_full_unstemmed | A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging |
| title_short | A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging |
| title_sort | comparative study of supervised and self supervised denoising techniques for defect segmentation in industrial ct imaging |
| url | https://www.ndt.net/search/docs.php3?id=30735 |
| work_keys_str_mv | AT virginiaflorian acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT jiayangshi acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT willemjanpalestijn acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT danielmpelt acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT kjoostbatenburg acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT thomaslang acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT christophheinzl acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT christiankretzer acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT stefankasperl acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT dominikwolfschlager acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT roberthschmitt acomparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT virginiaflorian comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT jiayangshi comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT willemjanpalestijn comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT danielmpelt comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT kjoostbatenburg comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT thomaslang comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT christophheinzl comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT christiankretzer comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT stefankasperl comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT dominikwolfschlager comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging AT roberthschmitt comparativestudyofsupervisedandselfsuperviseddenoisingtechniquesfordefectsegmentationinindustrialctimaging |