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

Beyond the Page: Solar Loading Thermographic Imaging and Predictive Modeling for Ancient Book Diagnostics-Preliminary Results.

Sensors (Basel, Switzerland)·2026
Same author

Tackling inter-subject variability in smartwatch data using factorization models.

Scientific reports·2025
Same author

Heart disease detection using an acceleration-deceleration curve-based neural network with consumer-grade smartwatch data.

Heliyon·2024
Same author

Supervised machine learning on electrocardiography features to classify sleep in noncritically ill children.

Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine·2024
Same author

An electroencephalography-based sleep index and supervised machine learning as a suitable tool for automated sleep classification in children.

Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine·2023
Same author

A Comprehensive Study on Measurement Accuracy of Distributed Fiber Optic Sensors Embedded within Capillaries of Solid Structures.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Aug 17, 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

11.2K

A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared

Morteza Moradi1,2, Ramin Ghorbani3, Stefano Sfarra4

  • 1Structural Integrity & Composites Group, Aerospace Engineering Faculty, Delft University of Technology, Kluyverweg 1, 2629 HS Delft, The Netherlands.

Sensors (Basel, Switzerland)
|December 11, 2022
PubMed
Summary

This study introduces a novel spatiotemporal deep neural network for non-destructive defect detection in cultural heritage artworks using Infrared Thermography. The advanced AI model significantly improves the accuracy of identifying hidden flaws in mural paintings.

Keywords:
cultural heritage assetsdeep learninginfrared thermographynon-destructive testingspatiotemporal deep neural network

More Related Videos

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.9K
The Use of Thermal Infra-Red Imaging to Detect Delayed Onset Muscle Soreness
08:51

The Use of Thermal Infra-Red Imaging to Detect Delayed Onset Muscle Soreness

Published on: January 22, 2012

19.4K

Related Experiment Videos

Last Updated: Aug 17, 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

11.2K
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.9K
The Use of Thermal Infra-Red Imaging to Detect Delayed Onset Muscle Soreness
08:51

The Use of Thermal Infra-Red Imaging to Detect Delayed Onset Muscle Soreness

Published on: January 22, 2012

19.4K

Area of Science:

  • * Art conservation science
  • * Non-destructive testing (NDT) methods
  • * Artificial intelligence in heritage preservation

Background:

  • * Assessing cultural heritage assets requires non-destructive inspection methods.
  • * Infrared Thermography (IRT) can detect surface and subsurface defects by analyzing heat diffusion.
  • * Defect detection is crucial for the restoration of artworks, particularly mural paintings.

Purpose of the Study:

  • * To develop and evaluate an advanced deep learning model for defect identification in artworks.
  • * To apply machine learning and deep learning techniques to Infrared Thermography data for heritage conservation.
  • * To compare the performance of a novel spatiotemporal deep neural network against conventional algorithms.

Main Methods:

  • * Development of a spatiotemporal deep neural network model.
  • * Application of the model to Infrared Thermography data from a mock-up artwork.
  • * Consideration of both temporal and spatial data from step-heating thermography.
  • * Comparative analysis with traditional defect detection algorithms.

Main Results:

  • * The proposed spatiotemporal deep neural network demonstrated superior performance in defect identification.
  • * The AI model effectively detected defects in the mock-up artwork.
  • * The results indicate a significant improvement over conventional methods in accuracy and efficiency.

Conclusions:

  • * Spatiotemporal deep neural networks offer a powerful tool for non-destructive defect detection in cultural heritage.
  • * The developed AI approach enhances the precision and reliability of artwork assessment and restoration.
  • * This method holds significant promise for the future of art conservation and NDT.