EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review

Lingxi Liu iD, Tsveta Miteva iD, Giovanni Delnevo iD, Silvia Mirri iD, Philippe Walter iD, Laurence de Viguerie, Emeline Pouyet

Sensors · 22.02.2023 · 23 (5) · 2419

DOI: 10.3390/s23052419 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 22.02.2023. Verfasst von Lingxi Liu und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering-Interdepartmental Centre for Industrial ICT Research (CIRI ICT), University of Bologna, 40126 Bologna,…. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 113 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral imaging (HSI) has become widely used in cultural heritage (CH). This very efficient method for artwork analysis is connected with the generation of large amounts of spectral data. The effective processing of such heavy spectral datasets remains an active research area. Along with the firmly established statistical and multivariate analysis methods, neural networks (NNs) represent a promising alternative in the field of CH. Over the last five years, the application of NNs for pigment identification and classification based on HSI datasets has drastically expanded due to the flexibility of the types of data they can process, and their superior ability to extract structures contained in the raw spectral data. This review provides an exhaustive analysis of the literature related to NNs applied for HSI data in the CH field. We outline the existing data processing workflows and propose a comprehensive comparison of the applications and limitations of the various input dataset preparation methods and NN architectures. By leveraging NN strategies in CH, the paper contributes to a wider and more systematic application of this novel data analysis method.

Schlagwörter

Stichwörter der Autor:innen

cultural heritagedeep learninghyperspectral imagingneural network

Autor:innen und Institutionen

  • Department of Computer Science and Engineering-Interdepartmental Centre for Industrial ICT Research (CIRI ICT), University of Bologna, 40126 Bologna, Italy.
  • Laboratoire de Chimie Physique-Matière et Rayonnement (LCPMR), UMR 7614, CNRS, Sorbonne Université, 75005 Paris, France.
  • Laboratoire d'Archéologie Moléculaire et Structurale (LAMS), CNRS, Sorbonne Université, 75005 Paris, France.

ORCID-Profile: Lingxi Liu, Tsveta Miteva, Giovanni Delnevo, Silvia Mirri, Philippe Walter

Zitieren

APA

Liu, L., Miteva, T., Delnevo, G., Mirri, S., Walter, P., de Viguerie, L., & Pouyet, E. (2023). Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review. Sensors, 23(5), 2419. https://doi.org/10.3390/s23052419

Vancouver

Liu L, Miteva T, Delnevo G, Mirri S, Walter P, de Viguerie L, et al. Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review. Sensors. 2023;23(5):2419. doi:10.3390/s23052419

BibTeX
@article{Liu2023,
  author = {Liu, Lingxi and Miteva, Tsveta and Delnevo, Giovanni and Mirri, Silvia and Walter, Philippe and de Viguerie, Laurence and Pouyet, Emeline},
  title = {Neural Networks for Hyperspectral Imaging of Historical Paintings: A Practical Review},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {5},
  pages = {2419},
  doi = {10.3390/s23052419}
}
Kostenlos starten →