Les Mardis de la chimie | Tsveta Miteva (LCPMR) "Artificial intelligence for hyperspectral imaging of historical paintings"

ARTIFICIAL INTELLIGENCE FOR HYPERSPECTRAL IMAGING OF HISTORICAL PAINTINGS
INTELLIGENCE ARTIFICIELLE POUR L'IMAGERIE HYPERSPECTRALE DE PEINTURES HISTORIQUES

Tsveta MITEVA

Hyperspectral imaging (HSI) in the visible and SWIR domains are fast and non-invasive imaging methods that have been adapted by the field of conservation science to study painted surfaces. By measuring the reflectance at a given pixel on a 2D surface, the resulting 3D hyperspectral data cube contains millions of recorded spectra. While processing such large amounts of spectral data poses an analytical and computational challenge, it also opens new opportunities to apply powerful methods of multivariate analysis for data evaluation. With the intent of expanding current data treatment of hyperspectral datasets, and solving the problem of nonlinear unmixing of hyperspectral reflectance data acquired on painted works of art, innovative data analysis approaches based on the use of AI have been recently developed. The efficiency and limitations of the proposed methods for painted surfaces from cultural heritage will be presented and discussed through the study of laboratory prepared paint mock-ups, and historical paintings.

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.

Biographie - Dr. Tsveta Miteva completed her PhD at the University of Heidelberg, Germany, followed by postdoctoral studies at Sorbonne University in Paris, France. Since 2018, she has been a researcher at the French National Scientific Center (CNRS), stationed at the Laboratoire de Chimie Physique-Matière et Rayonnement (LCPMR). Her research primarily delves into the theoretical simulation of ultrafast electronic decay processes following inner-shell excitation and ionization in gas and liquid phases. Furthermore, she applies her expertise in Machine Learning and Artificial Intelligence to the field of cultural heritage as well as in the analysis of algal biomass components for biofuel production.