Nonlinear Unmixing of Hyperspectral Datasets for the Study of Painted Works of Art

Neda Rohani, Émeline Pouyet, Marc Walton, Oliver Cossairt, Aggelos K. KatsaggelosAngewandte 2018 · DOI

Abstract

Nonlinear unmixing of hyperspectral reflectance data is one of the key problems in quantitative imaging of painted works of art. The approach presented is to interrogate a hyperspectral image cube by first decomposing it into a set of reflectance curves representing pure basis pigments and second to estimate the scattering and absorption coefficients of each pigment in a given pixel to produce estimates of the component fractions. This two-step algorithm uses a deep neural network to qualitatively identify the constituent pigments in any unknown spectrum and, based on the pigment(s) present and Kubelka-Munk theory to estimate the pigment concentration on a per-pixel basis. Using hyperspectral data acquired on a set of mock-up paintings and a well-characterized illuminated folio from the 15th century, the performance of the proposed algorithm is demonstrated for pigment recognition and quantitative estimation of concentration.
BibTeX
@inproceedings{rohani2018nonlinear,
  author = {Neda Rohani and Émeline Pouyet and Marc Walton and Oliver Cossairt and Aggelos K. Katsaggelos},
  title = {{Nonlinear Unmixing of Hyperspectral Datasets for the Study of Painted Works of Art}},
  booktitle = {Angewandte},
  year = {2018},
  doi = {10.1002/anie.201805135},
}

Loading related content...

Figure