Due to fungal growth and mishandling in the book, there are various types of defects as they age such as foxing, tears, and creases. It is important to develop novel non-invasive inspection techniques and defect recognition algorithms. In this work, three non-invasive inspection techniques, including infrared thermography (IRT), terahertz time-domain spectroscopy (THz-TDS), and air-coupled ultrasound (ACU), were employed for the detection of defects in an ancient book cover. To improve the image quality and defect contrast, principal component analysis, fast Fourier transform, and partial least squares regression algorithms are used as the postprocessing methods. Furthermore, the YOLOv7 network is deployed for defect automatic detection. Finite element analysis and finite-difference time-domain methods were employed for generating training dataset of YOLOv7 network. Experimental results demonstrate that IRT and THz-TDS has excellent detection capability for surface and subsurface defects, respectively. By employing YOLOv7 network with simulation datasets, defects can be effectively identified.

Non-invasive inspection for a hand-bound book of the 19th century: Numerical simulations and experimental analysis of infrared, terahertz, and ultrasonic methods

Sfarra, Stefano;
2024-01-01

Abstract

Due to fungal growth and mishandling in the book, there are various types of defects as they age such as foxing, tears, and creases. It is important to develop novel non-invasive inspection techniques and defect recognition algorithms. In this work, three non-invasive inspection techniques, including infrared thermography (IRT), terahertz time-domain spectroscopy (THz-TDS), and air-coupled ultrasound (ACU), were employed for the detection of defects in an ancient book cover. To improve the image quality and defect contrast, principal component analysis, fast Fourier transform, and partial least squares regression algorithms are used as the postprocessing methods. Furthermore, the YOLOv7 network is deployed for defect automatic detection. Finite element analysis and finite-difference time-domain methods were employed for generating training dataset of YOLOv7 network. Experimental results demonstrate that IRT and THz-TDS has excellent detection capability for surface and subsurface defects, respectively. By employing YOLOv7 network with simulation datasets, defects can be effectively identified.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11697/242100
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact