A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared Thermography
Assessment of cultural heritage assets is now extremely important all around the world. Non-destructive inspection is essential for preserving the integrity of artworks while avoiding the loss of any precious materials that make them up. The use of Infrared Thermography is an interesting concept sin...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/23/9361 |
_version_ | 1797462116027858944 |
---|---|
author | Morteza Moradi Ramin Ghorbani Stefano Sfarra David M.J. Tax Dimitrios Zarouchas |
author_facet | Morteza Moradi Ramin Ghorbani Stefano Sfarra David M.J. Tax Dimitrios Zarouchas |
author_sort | Morteza Moradi |
collection | DOAJ |
description | Assessment of cultural heritage assets is now extremely important all around the world. Non-destructive inspection is essential for preserving the integrity of artworks while avoiding the loss of any precious materials that make them up. The use of Infrared Thermography is an interesting concept since surface and subsurface faults can be discovered by utilizing the 3D diffusion inside the object caused by external heat. The primary goal of this research is to detect defects in artworks, which is one of the most important tasks in the restoration of mural paintings. To this end, machine learning and deep learning techniques are effective tools that should be employed properly in accordance with the experiment’s nature and the collected data. Considering both the temporal and spatial perspectives of step-heating thermography, a spatiotemporal deep neural network is developed for defect identification in a mock-up reproducing an artwork. The results are then compared with those of other conventional algorithms, demonstrating that the proposed approach outperforms the others. |
first_indexed | 2024-03-09T17:31:56Z |
format | Article |
id | doaj.art-6dda61f8883440de8d9b6fbfd3de5030 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T17:31:56Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-6dda61f8883440de8d9b6fbfd3de50302023-11-24T12:12:56ZengMDPI AGSensors1424-82202022-12-012223936110.3390/s22239361A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared ThermographyMorteza Moradi0Ramin Ghorbani1Stefano Sfarra2David M.J. Tax3Dimitrios Zarouchas4Structural Integrity & Composites Group, Aerospace Engineering Faculty, Delft University of Technology, Kluyverweg 1, 2629 HS Delft, The NetherlandsPattern Recognition Laboratory, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Van Mourik Broekmanweg 6, 2628 XE Delft, The NetherlandsDepartment of Industrial and Information Engineering and Economics (DIIIE), University of L’Aquila, Piazzale E. Pontieri 1, Monteluco di Roio, 67100 L’Aquila, ItalyPattern Recognition Laboratory, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Van Mourik Broekmanweg 6, 2628 XE Delft, The NetherlandsStructural Integrity & Composites Group, Aerospace Engineering Faculty, Delft University of Technology, Kluyverweg 1, 2629 HS Delft, The NetherlandsAssessment of cultural heritage assets is now extremely important all around the world. Non-destructive inspection is essential for preserving the integrity of artworks while avoiding the loss of any precious materials that make them up. The use of Infrared Thermography is an interesting concept since surface and subsurface faults can be discovered by utilizing the 3D diffusion inside the object caused by external heat. The primary goal of this research is to detect defects in artworks, which is one of the most important tasks in the restoration of mural paintings. To this end, machine learning and deep learning techniques are effective tools that should be employed properly in accordance with the experiment’s nature and the collected data. Considering both the temporal and spatial perspectives of step-heating thermography, a spatiotemporal deep neural network is developed for defect identification in a mock-up reproducing an artwork. The results are then compared with those of other conventional algorithms, demonstrating that the proposed approach outperforms the others.https://www.mdpi.com/1424-8220/22/23/9361infrared thermographynon-destructive testingcultural heritage assetsdeep learningspatiotemporal deep neural network |
spellingShingle | Morteza Moradi Ramin Ghorbani Stefano Sfarra David M.J. Tax Dimitrios Zarouchas A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared Thermography Sensors infrared thermography non-destructive testing cultural heritage assets deep learning spatiotemporal deep neural network |
title | A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared Thermography |
title_full | A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared Thermography |
title_fullStr | A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared Thermography |
title_full_unstemmed | A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared Thermography |
title_short | A Spatiotemporal Deep Neural Network Useful for Defect Identification and Reconstruction of Artworks Using Infrared Thermography |
title_sort | spatiotemporal deep neural network useful for defect identification and reconstruction of artworks using infrared thermography |
topic | infrared thermography non-destructive testing cultural heritage assets deep learning spatiotemporal deep neural network |
url | https://www.mdpi.com/1424-8220/22/23/9361 |
work_keys_str_mv | AT mortezamoradi aspatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT raminghorbani aspatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT stefanosfarra aspatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT davidmjtax aspatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT dimitrioszarouchas aspatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT mortezamoradi spatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT raminghorbani spatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT stefanosfarra spatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT davidmjtax spatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography AT dimitrioszarouchas spatiotemporaldeepneuralnetworkusefulfordefectidentificationandreconstructionofartworksusinginfraredthermography |