Next Article in Journal
Routing with Face Traversal and Auctions Algorithms for Task Allocation in WSRN
Next Article in Special Issue
Reflectance Imaging Spectroscopy (RIS) for Operation Night Watch: Challenges and Achievements of Imaging Rembrandt’s Masterpiece in the Glass Chamber at the Rijksmuseum
Previous Article in Journal
Robust Pressure Sensor in SOI Technology with Butterfly Wiring for Airfoil Integration
Previous Article in Special Issue
Low-Cost Multispectral System Design for Pigment Analysis in Works of Art
 
 
Article

Artificial Intelligence for Pigment Classification Task in the Short-Wave Infrared Range

1
Laboratoire d’Archéologie Moléculaire et Structurale (LAMS), CNRS, Sorbonne Université, 75005 Paris, France
2
Laboratoire de Chimie Physique-Matière et Rayonnement (LCPMR), UMR 7614, CNRS, Sorbonne Université, 75005 Paris, France
3
Microsoft, Bellevue, WA 98004, USA
*
Author to whom correspondence should be addressed.
Academic Editor: David W. Messinger
Sensors 2021, 21(18), 6150; https://doi.org/10.3390/s21186150
Received: 16 July 2021 / Revised: 3 September 2021 / Accepted: 9 September 2021 / Published: 13 September 2021
Hyperspectral reflectance imaging in the short-wave infrared range (SWIR, “extended NIR”, ca. 1000 to 2500 nm) has proven to provide enhanced characterization of paint materials. However, the interpretation of the results remains challenging due to the intrinsic complexity of the SWIR spectra, presenting both broad and narrow absorption features with possible overlaps. To cope with the high dimensionality and spectral complexity of such datasets acquired in the SWIR domain, one data treatment approach is tested, inspired by innovative development in the cultural heritage field: the use of a pigment spectral database (extracted from model and historical samples) combined with a deep neural network (DNN). This approach allows for multi-label pigment classification within each pixel of the data cube. Conventional Spectral Angle Mapping and DNN results obtained on both pigment reference samples and a Buddhist painting (thangka) are discussed. View Full-Text
Keywords: reflectance imaging spectroscopy; hyperspectral imaging in the short-wave infrared range; deep neural network; pigment mapping; thangkas reflectance imaging spectroscopy; hyperspectral imaging in the short-wave infrared range; deep neural network; pigment mapping; thangkas
Show Figures

Figure 1

MDPI and ACS Style

Pouyet, E.; Miteva, T.; Rohani, N.; de Viguerie, L. Artificial Intelligence for Pigment Classification Task in the Short-Wave Infrared Range. Sensors 2021, 21, 6150. https://doi.org/10.3390/s21186150

AMA Style

Pouyet E, Miteva T, Rohani N, de Viguerie L. Artificial Intelligence for Pigment Classification Task in the Short-Wave Infrared Range. Sensors. 2021; 21(18):6150. https://doi.org/10.3390/s21186150

Chicago/Turabian Style

Pouyet, Emeline, Tsveta Miteva, Neda Rohani, and Laurence de Viguerie. 2021. "Artificial Intelligence for Pigment Classification Task in the Short-Wave Infrared Range" Sensors 21, no. 18: 6150. https://doi.org/10.3390/s21186150

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop