Nonlinear Unmixing of Hyperspectral Datasets for the Study of Painted Works of Art |
| |
Authors: | Neda Rohani Dr. Emeline Pouyet Dr. Marc Walton Dr. Oliver Cossairt Dr. Aggelos K. Katsaggelos |
| |
Affiliation: | 1. Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL, USA;2. Center for Scientific Studies in the Art, Northwestern University, Evanston, IL, USA |
| |
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. |
| |
Keywords: | deep neural network classification heritage science nonlinear unmixing Kubelka– Munk theory visible hyperspectral imaging |
|
|