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 Experiment Video

Updated: May 28, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.1K

Optimal surface defect detector design based on deep learning for 3D geometry.

Sangmin Suh1,2

  • 1Department of Information and Telecommunication Engineering, Gangneung-Wonju National University, Wonju-si, Gangwon-do, 26403, Republic of Korea. sangminsuh@gwnu.ac.kr.

Scientific Reports
|February 14, 2025
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same journal

Impact of room configuration on energy use intensity in high-density pilgrim accommodations: a case study in Makkah, Saudi Arabia.

Scientific reportsยท2026
Same journal

Retraction Note: Improving the power production efficiency of microbial fuel cell by using biosynthesized polyanaline coated Fe<sub>3</sub>O<sub>4</sub> as pencil graphite anode modifier.

Scientific reportsยท2026
Same journal

Stylopine as multi-target anti-Alzheimer agent.

Scientific reportsยท2026
Same journal

Principal component analysis of morphological features of the aortic arch for predicting the risk for acute type B aortic dissection.

Scientific reportsยท2026
Same journal

An explainable AfroXLMR approach for multi-label emotion classification of Amharic social media text with dataset release.

Scientific reportsยท2026
Same journal

Bridging in vitro bioactivities and in silico insights of Rubia cordifolia L. (Rubiaceae) leaf extracts for therapeutic applications.

Scientific reportsยท2026

This study introduces a novel method for detecting steel surface defects using geometric transformations and model optimization, achieving near-ideal performance in harsh manufacturing environments. The new approach overcomes limitations of existing deep learning techniques for 3D steel products.

Area of Science:

  • Materials Science
  • Computer Vision
  • Artificial Intelligence

Background:

  • Steel manufacturing environments pose significant risks to human inspectors due to poor visibility and extreme conditions.
  • Current automated inspection methods, including deep learning, face limitations with 2D data and performance degradation due to data curvature.

Purpose of the Study:

  • To develop an advanced automated system for detecting surface defects on 3D steel products in challenging industrial settings.
  • To address the performance limitations of existing deep learning models in steel surface inspection.

Main Methods:

  • Dataset generation via geometric transformations that parameterize steel surface defect detector hardware.
  • Development of a performance-based model optimization algorithm tailored for steel defect detection.
Keywords:
3D geometryArtificial intelligenceDeep learningGeometric transformationSurface defect detection

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

454
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.7K

Related Experiment Videos

Last Updated: May 28, 2025

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
11:34

Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography

Published on: May 15, 2017

11.1K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

454
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.7K
  • Application of deep learning techniques to analyze 3D steel product geometries.

    • Main Results:

    • Achieved an average F1 score of 0.932 in validation experiments.
    • Obtained an average area under the curve (AUC) of 0.99, indicating near-ideal detection performance.
    • Demonstrated the effectiveness of the proposed method for 3D steel products, a novel area of research.

    Conclusions:

    • The proposed dataset generation and model optimization approach significantly enhances steel surface defect detection accuracy.
    • This research provides a robust solution for automated inspection of 3D steel products, improving safety and efficiency in manufacturing.
    • The developed algorithm offers a promising advancement over current transfer learning-based methods for industrial defect detection.