Attention U-Net-based semantic segmentation for welding line detection

Abstract In industrial processes, quality assurance through methods such as visual inspection is essential for ensuring process stability. Traditional manual visual inspection is a time-consuming and costly endeavor. If the opportunity arises, replacing manual visual inspection with AI could lead to...

Full description

Saved in:
Bibliographic Details
Main Authors: Hunor István Lukács, Bence Zsolt Beregi, Balázs Porteleki, Tamás Fischl, János Botzheim
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-00257-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850206107035762688
author Hunor István Lukács
Bence Zsolt Beregi
Balázs Porteleki
Tamás Fischl
János Botzheim
author_facet Hunor István Lukács
Bence Zsolt Beregi
Balázs Porteleki
Tamás Fischl
János Botzheim
author_sort Hunor István Lukács
collection DOAJ
description Abstract In industrial processes, quality assurance through methods such as visual inspection is essential for ensuring process stability. Traditional manual visual inspection is a time-consuming and costly endeavor. If the opportunity arises, replacing manual visual inspection with AI could lead to significant efficiency gains. However, simply judging the correctness or incorrectness of a process is often insufficient; quantitative attributes must also be associated with visual inspection. This paper proposes a solution for replacing manual visual inspection with AI specifically for welded joints. The aim is not only to detect the presence of weld joints but also to assess their geometric dimensions. Leveraging a proposed Attention U-Net architecture in combination with rule-based metrics, the proposed method offers a novel solution for identifying welding lines in images. By integrating semantic segmentation techniques, the method effectively distinguishes weld joint elements, while rule-based metrics facilitate the identification of critical cases requiring human intervention. Experimental results demonstrate the method’s capability to automate a significant portion of inspection tasks, thereby reducing the reliance on manual labor and enhancing overall process efficiency and reliability.
format Article
id doaj-art-79a69dbfc9b34f20b2b05de8969744e4
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-79a69dbfc9b34f20b2b05de8969744e42025-08-20T02:10:56ZengNature PortfolioScientific Reports2045-23222025-05-0115111110.1038/s41598-025-00257-2Attention U-Net-based semantic segmentation for welding line detectionHunor István Lukács0Bence Zsolt Beregi1Balázs Porteleki2Tamás Fischl3János Botzheim4Department of Artificial Intelligence, Faculty of Informatics, ELTE Eötvös Loránd UniversityDepartment of Artificial Intelligence, Faculty of Informatics, ELTE Eötvös Loránd UniversityRobert Bosch KftRobert Bosch KftDepartment of Artificial Intelligence, Faculty of Informatics, ELTE Eötvös Loránd UniversityAbstract In industrial processes, quality assurance through methods such as visual inspection is essential for ensuring process stability. Traditional manual visual inspection is a time-consuming and costly endeavor. If the opportunity arises, replacing manual visual inspection with AI could lead to significant efficiency gains. However, simply judging the correctness or incorrectness of a process is often insufficient; quantitative attributes must also be associated with visual inspection. This paper proposes a solution for replacing manual visual inspection with AI specifically for welded joints. The aim is not only to detect the presence of weld joints but also to assess their geometric dimensions. Leveraging a proposed Attention U-Net architecture in combination with rule-based metrics, the proposed method offers a novel solution for identifying welding lines in images. By integrating semantic segmentation techniques, the method effectively distinguishes weld joint elements, while rule-based metrics facilitate the identification of critical cases requiring human intervention. Experimental results demonstrate the method’s capability to automate a significant portion of inspection tasks, thereby reducing the reliance on manual labor and enhancing overall process efficiency and reliability.https://doi.org/10.1038/s41598-025-00257-2Weld detectionAttention U-NetSemantic segmentationIndustrial AIAI-based automatizationMachine vision
spellingShingle Hunor István Lukács
Bence Zsolt Beregi
Balázs Porteleki
Tamás Fischl
János Botzheim
Attention U-Net-based semantic segmentation for welding line detection
Scientific Reports
Weld detection
Attention U-Net
Semantic segmentation
Industrial AI
AI-based automatization
Machine vision
title Attention U-Net-based semantic segmentation for welding line detection
title_full Attention U-Net-based semantic segmentation for welding line detection
title_fullStr Attention U-Net-based semantic segmentation for welding line detection
title_full_unstemmed Attention U-Net-based semantic segmentation for welding line detection
title_short Attention U-Net-based semantic segmentation for welding line detection
title_sort attention u net based semantic segmentation for welding line detection
topic Weld detection
Attention U-Net
Semantic segmentation
Industrial AI
AI-based automatization
Machine vision
url https://doi.org/10.1038/s41598-025-00257-2
work_keys_str_mv AT hunoristvanlukacs attentionunetbasedsemanticsegmentationforweldinglinedetection
AT bencezsoltberegi attentionunetbasedsemanticsegmentationforweldinglinedetection
AT balazsporteleki attentionunetbasedsemanticsegmentationforweldinglinedetection
AT tamasfischl attentionunetbasedsemanticsegmentationforweldinglinedetection
AT janosbotzheim attentionunetbasedsemanticsegmentationforweldinglinedetection