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

Visualizing the 3D Evolution and Morphology of Hydrogen-Assisted Ductile Crack Growth in Hydrogen-Precharged P355NH Steel Using X-Ray Micro-Computed Tomography.

Materials (Basel, Switzerland)·2026
Same author

Automated Coffee Roast Level Classification Using Machine Learning and Deep Learning Models.

Journal of food science·2025
Same author

Monitoring of Layered Thermoplastic Composites Using Shape Memory Alloys as Integrated Sensors for Multifunctional Lightweight Structures.

Materials (Basel, Switzerland)·2025
Same author

Brief Review of Vibrothermography and Optical Thermography for Defect Quantification in CFRP Material.

Sensors (Basel, Switzerland)·2025
Same author

Target Design in SEM-Based Nano-CT and Its Influence on X-ray Imaging.

Journal of imaging·2023
Same author

High-Frequency Ultrasonic Spectroscopy of Structure Gradients in Injection-Molded PEEK Using a Focusing Transducer.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: May 10, 2025

Author Spotlight: Enhancing Fiber Composite Laminate Quality with the Wet Hand Lay-Up/Vacuum Bag Process
09:54

Author Spotlight: Enhancing Fiber Composite Laminate Quality with the Wet Hand Lay-Up/Vacuum Bag Process

Published on: June 30, 2023

1.9K

Advanced Thermal Imaging Processing and Deep Learning Integration for Enhanced Defect Detection in Carbon

Renan Garcia Rosa1, Bruno Pereira Barella1, Iago Garcia Vargas1

  • 1Faculty of Computing, Federal University of Uberlandia, Uberlandia 38408-100, Brazil.

Materials (Basel, Switzerland)
|April 24, 2025
PubMed
Summary

Thermal image preprocessing significantly enhances defect detection in carbon fiber composites. This method improves segmentation accuracy for non-destructive testing, crucial for industries like aerospace and automotive.

Keywords:
carbon fiber-reinforced polymerdeep learningnon-destructive testing (NDT)polynomial approximationpulsed thermographythermal image preprocessing

More Related Videos

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

11.0K
Cutting Procedures, Tensile Testing, and Ageing of Flexible Unidirectional Composite Laminates
07:53

Cutting Procedures, Tensile Testing, and Ageing of Flexible Unidirectional Composite Laminates

Published on: April 27, 2019

8.2K

Related Experiment Videos

Last Updated: May 10, 2025

Author Spotlight: Enhancing Fiber Composite Laminate Quality with the Wet Hand Lay-Up/Vacuum Bag Process
09:54

Author Spotlight: Enhancing Fiber Composite Laminate Quality with the Wet Hand Lay-Up/Vacuum Bag Process

Published on: June 30, 2023

1.9K
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

11.0K
Cutting Procedures, Tensile Testing, and Ageing of Flexible Unidirectional Composite Laminates
07:53

Cutting Procedures, Tensile Testing, and Ageing of Flexible Unidirectional Composite Laminates

Published on: April 27, 2019

8.2K

Area of Science:

  • Materials Science
  • Non-Destructive Testing
  • Image Processing

Background:

  • Carbon fiber-reinforced polymer (CFRP) laminates are vital in high-performance industries due to their superior strength-to-weight ratio.
  • Defect detection in CFRP is critical but challenging, especially under low signal-to-noise ratio (SNR) conditions common in pulsed thermography.
  • Existing segmentation methods often fail to achieve high accuracy due to noise and signal variations.

Purpose of the Study:

  • To evaluate the effectiveness of thermal image preprocessing techniques in improving defect segmentation for CFRP laminates.
  • To enhance the signal-to-noise ratio (SNR) and defect visibility in thermographic data.
  • To assess the performance of the U-Net architecture for defect segmentation with and without preprocessing.

Main Methods:

  • Applied polynomial approximations and first- and second-order derivatives for thermographic signal refinement.
  • Utilized the U-Net convolutional neural network architecture for image segmentation.
  • Compared segmentation performance on datasets before and after applying preprocessing techniques.

Main Results:

  • Preprocessing significantly improved defect segmentation accuracy in CFRP laminates.
  • Achieved an Intersection over Union (IoU) of 95% and an F1-Score of 99% with preprocessing.
  • Outperformed segmentation methods that did not incorporate preprocessing steps.

Conclusions:

  • Thermal image preprocessing is crucial for enhancing defect segmentation reliability in CFRP non-destructive testing.
  • The developed preprocessing approach substantially boosts the performance of U-Net segmentation models.
  • This study highlights the potential of optimized image processing to advance defect detection capabilities in critical industries.