EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Exploring the Potential of Multispectral Imaging for Automatic Clustering of Archeological Wall Painting Fragments

Piercarlo Dondi iD, Lucia Cascone iD, Chiara Delledonne iD, Michela Albano iD, Elena Mariani iD, Marina Volonté, Marco Malagodi iD, Giacomo Fiocco iD

Sensors · 28.03.2026 · 26 (7) · 2111

DOI: 10.3390/s26072111 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 28.03.2026. Verfasst von Piercarlo Dondi und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, 27100 Pavia, Italy. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The digital reconstruction of damaged archeological wall paintings is a challenging task due to severe material degradation, high fragmentation, and the lack of reference images. A crucial preliminary step is the separation and grouping of fragments originating from different wall paintings, which are often found mixed together at archeological sites. To address this issue, we explored the potential of multispectral imaging (MSI) for unsupervised fragment clustering, aiming to assess whether integrating multiple spectral bands can enhance fragment discrimination compared to using the visible band alone. As a test set, we examined five groups of wall painting fragments from a Roman domus (1st c. BC–1st c. AD) provided by the Archaeological Museum of Cremona (Italy). Images were acquired using the Hypercolorimetric Multispectral Imaging (HMI) system developed by Profilocolore® Srl (Rome, Italy). Specifically, we considered visible reflectance (VIS), infrared reflectance (IR), infrared false color (IRFC), and Ultraviolet-induced Fluorescence (UVF) images. Through a systematic benchmarking study, we compared several state-of-the-art feature extraction and clustering methods across single- and multi-band configurations. Results show that combining MSI data can substantially enhance the system’s ability to correctly separate and group fragments, indicating a promising direction for future research.

Schlagwörter

Stichwörter der Autor:innen

Roman wall paintingUV fluorescenceclusteringdeep learninginfrared reflectancemachine learningmultispectral imaging

Autor:innen und Institutionen

  • Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Via Ferrata 5, 27100 Pavia, Italy.
  • Centro Interdipartimentale di Studi e Ricerche per la Conservazione del Patrimonio Culturale (CISRiC), University of Pavia, 26100 Pavia, Italy.
  • Department of Computer Science, University of Salerno, Via Giovanni Paolo II, 132, 84084 Salerno, Italy.
  • Department of Physics, University of Pavia, Via Bassi 6, 27100 Pavia, Italy.
  • Arvedi Laboratory of Non-Invasive Diagnostics, Department of Musicology and Cultural Heritage, University of Pavia, Via Bell'Aspa 3, 26100 Cremona, Italy.
  • Independent Researcher, Via Cavour 6, 20851 Lissone, Italy.

ORCID-Profile: Piercarlo Dondi, Lucia Cascone, Chiara Delledonne, Michela Albano, Elena Mariani, Marco Malagodi, Giacomo Fiocco

Zitieren

APA

Dondi, P., Cascone, L., Delledonne, C., Albano, M., Mariani, E., Volonté, M., Malagodi, M., & Fiocco, G. (2026). Exploring the Potential of Multispectral Imaging for Automatic Clustering of Archeological Wall Painting Fragments. Sensors, 26(7), 2111. https://doi.org/10.3390/s26072111

Vancouver

Dondi P, Cascone L, Delledonne C, Albano M, Mariani E, Volonté M, et al. Exploring the Potential of Multispectral Imaging for Automatic Clustering of Archeological Wall Painting Fragments. Sensors. 2026;26(7):2111. doi:10.3390/s26072111

BibTeX
@article{Dondi2026,
  author = {Dondi, Piercarlo and Cascone, Lucia and Delledonne, Chiara and Albano, Michela and Mariani, Elena and Volonté, Marina and Malagodi, Marco and Fiocco, Giacomo},
  title = {Exploring the Potential of Multispectral Imaging for Automatic Clustering of Archeological Wall Painting Fragments},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {2111},
  doi = {10.3390/s26072111}
}
Kostenlos starten →