Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Enhancing recall in asphalt pavement crack segmentation using a HoughNet-extended U-Net architecture with reconstruction head.

Scientific reports·2025
Same author

Colonial bacterial memetic algorithm and its application on a darts playing robot.

Scientific reports·2025
Same author

Designing an Embedded Feature Selection Algorithm for a Drowsiness Detector Model Based on Electroencephalogram Data.

Sensors (Basel, Switzerland)·2023
Same author

Development of an Adaptive Computer-Aided Soft Sensor Diagnosis System for Assessment of Executive Functions.

Sensors (Basel, Switzerland)·2022
Same author

Placement of Optical Sensors in 3D Terrain Using a Bacterial Evolutionary Algorithm.

Sensors (Basel, Switzerland)·2022
Same author

Combining Reflexes and External Sensory Information in a Neuromusculoskeletal Model to Control a Quadruped Robot.

IEEE transactions on cybernetics·2021

Related Experiment Video

Updated: May 9, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K

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

Hunor István Lukács1,2, Bence Zsolt Beregi3,4, Balázs Porteleki4

  • 1Department of Artificial Intelligence, Faculty of Informatics, ELTE Eötvös Loránd University, Pázmány P. Sétány 1/A, Budapest, 1117, Hungary. lukacs.hunor@inf.elte.hu.

Scientific Reports
|May 1, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces an AI-powered system for automated visual inspection of welded joints, assessing both presence and geometric dimensions. This innovation significantly enhances industrial process efficiency and reliability by reducing manual labor.

Keywords:
AI-based automatizationAttention U-NetIndustrial AIMachine visionSemantic segmentationWeld detection

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

319

Related Experiment Videos

Last Updated: May 9, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.3K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

319

Area of Science:

  • Industrial Engineering
  • Computer Vision
  • Materials Science

Background:

  • Quality assurance in industrial processes is critical for stability.
  • Manual visual inspection of components like welded joints is labor-intensive and costly.
  • Current methods often lack quantitative assessment of defects.

Purpose of the Study:

  • To develop an AI-driven solution for automated visual inspection of welded joints.
  • To enable quantitative assessment of weld joint geometric dimensions.
  • To improve efficiency and reliability in industrial quality control.

Main Methods:

  • Utilized an Attention U-Net architecture for image analysis.
  • Integrated semantic segmentation to identify weld joint features.
  • Applied rule-based metrics for quantitative defect assessment and critical case identification.

Main Results:

  • Successfully automated the detection of weld joints and assessment of their dimensions.
  • Demonstrated the capability to distinguish weld joint elements effectively.
  • Identified critical cases requiring human intervention through rule-based metrics.

Conclusions:

  • The proposed AI method can replace manual visual inspection for welded joints.
  • Automating inspection tasks reduces reliance on manual labor.
  • The system enhances overall industrial process efficiency and reliability.