Infrared thermal defect identification and reconstruction of artworks using a spatiotemporal deep neural network

M. Moradi; R. Ghorbani; Stefano Sfarra; D.M.J. Tax; D. Zarouchas

Infrared thermal defect identification and reconstruction of artworks using a spatiotemporal deep neural network

M. Moradi^*, R. Ghorbani, Stefano Sfarra, D.M.J. Tax, D. Zarouchas

^*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

Assessment of cultural heritage assets is now extremely important all around the world. Non-destructive inspection is essential for preserving the integrity of the artworks while avoiding the loss of any precious materials that make it up. The use of Infrared Thermography (IRT) 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, a spatiotemporal deep neural network (STDNN) is utilized for defect identification in a mock-up reproducing an artwork, taking into account both the temporal and spatial perspectives of step-heating (SH) thermography. Finally, the outcomes are compared to those of other conventional algorithms.

Original language	English
Title of host publication	Proceedings of the International Conference on Inverse Problems in Engineering 2022
Place of Publication	Francavilla al Mare (Chieti), ITALY
Chapter	3
Pages	503-510
Number of pages	8
Volume	10
Publication status	Published - 2022
Event	10th International Conference on Inverse Problems in Engineering 2022 - Francavilla al Mare, Chieti, Italy Duration: 15 May 2022 → 19 May 2022 Conference number: 10

Conference

Conference	10th International Conference on Inverse Problems in Engineering 2022
Abbreviated title	ICIPE 2022
Country/Territory	Italy
City	Chieti
Period	15/05/22 → 19/05/22

Keywords

Deep Learning
spatiotemporal deep neural network
Infrared thermography
Damage Detection
Non-destructive method (NDT)
Convolutional Neural Network (CNN)
U-Net
Artworks
Cultural heritage
MLP neural network

Cite this

@inproceedings{6c2f08cec58046a78d0617a941146613,

title = "Infrared thermal defect identification and reconstruction of artworks using a spatiotemporal deep neural network",

abstract = "Assessment of cultural heritage assets is now extremely important all around the world. Non-destructive inspection is essential for preserving the integrity of the artworks while avoiding the loss of any precious materials that make it up. The use of Infrared Thermography (IRT) 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, a spatiotemporal deep neural network (STDNN) is utilized for defect identification in a mock-up reproducing an artwork, taking into account both the temporal and spatial perspectives of step-heating (SH) thermography. Finally, the outcomes are compared to those of other conventional algorithms.",

keywords = "Deep Learning, spatiotemporal deep neural network, Infrared thermography, Damage Detection, Non-destructive method (NDT), Convolutional Neural Network (CNN), U-Net, Artworks, Cultural heritage, MLP neural network",

author = "M. Moradi and R. Ghorbani and Stefano Sfarra and D.M.J. Tax and D. Zarouchas",

year = "2022",

language = "English",

volume = "10",

pages = "503--510",

booktitle = "Proceedings of the International Conference on Inverse Problems in Engineering 2022",

note = "10th International Conference on Inverse Problems in Engineering 2022, ICIPE 2022 ; Conference date: 15-05-2022 Through 19-05-2022",

}

Moradi, M , Ghorbani, R, Sfarra, S, Tax, DMJ & Zarouchas, D 2022, Infrared thermal defect identification and reconstruction of artworks using a spatiotemporal deep neural network. in Proceedings of the International Conference on Inverse Problems in Engineering 2022. vol. 10, Francavilla al Mare (Chieti), ITALY, pp. 503-510, 10th International Conference on Inverse Problems in Engineering 2022, Chieti, Italy, 15/05/22.

Infrared thermal defect identification and reconstruction of artworks using a spatiotemporal deep neural network. / Moradi, M.; Ghorbani, R.; Sfarra, Stefano et al.
Proceedings of the International Conference on Inverse Problems in Engineering 2022. Vol. 10 Francavilla al Mare (Chieti), ITALY, 2022. p. 503-510.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Infrared thermal defect identification and reconstruction of artworks using a spatiotemporal deep neural network

AU - Moradi, M.

AU - Ghorbani, R.

AU - Sfarra, Stefano

AU - Tax, D.M.J.

AU - Zarouchas, D.

N1 - Conference code: 10

PY - 2022

Y1 - 2022

N2 - Assessment of cultural heritage assets is now extremely important all around the world. Non-destructive inspection is essential for preserving the integrity of the artworks while avoiding the loss of any precious materials that make it up. The use of Infrared Thermography (IRT) 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, a spatiotemporal deep neural network (STDNN) is utilized for defect identification in a mock-up reproducing an artwork, taking into account both the temporal and spatial perspectives of step-heating (SH) thermography. Finally, the outcomes are compared to those of other conventional algorithms.

AB - Assessment of cultural heritage assets is now extremely important all around the world. Non-destructive inspection is essential for preserving the integrity of the artworks while avoiding the loss of any precious materials that make it up. The use of Infrared Thermography (IRT) 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, a spatiotemporal deep neural network (STDNN) is utilized for defect identification in a mock-up reproducing an artwork, taking into account both the temporal and spatial perspectives of step-heating (SH) thermography. Finally, the outcomes are compared to those of other conventional algorithms.

KW - Deep Learning

KW - spatiotemporal deep neural network

KW - Infrared thermography

KW - Damage Detection

KW - Non-destructive method (NDT)

KW - Convolutional Neural Network (CNN)

KW - U-Net

KW - Artworks

KW - Cultural heritage

KW - MLP neural network

M3 - Conference contribution

VL - 10

SP - 503

EP - 510

BT - Proceedings of the International Conference on Inverse Problems in Engineering 2022

CY - Francavilla al Mare (Chieti), ITALY

T2 - 10th International Conference on Inverse Problems in Engineering 2022

Y2 - 15 May 2022 through 19 May 2022

ER -

Infrared thermal defect identification and reconstruction of artworks using a spatiotemporal deep neural network

Abstract

Conference

Keywords

Fingerprint

Cite this