Mid-infrared fiber-optics reflectance spectroscopy: A noninvasive technique for remote analysis of painted layers. Part II: Statistical analysis of spectra
M. Fabbri et al., Mid-infrared fiber-optics reflectance spectroscopy: A noninvasive technique for remote analysis of painted layers. Part II: Statistical analysis of spectra, APPL SPECTR, 55(4), 2001, pp. 428-433
Mid-infrared fiber-optics reflectance spectroscopy supported by classificat
ion procedures based on the Mahalanobis distance in the principal component
space was applied to investigate laboratory samples simulating actual pain
tings. Tile spectral data obtained :cere analyzed by means of principal com
ponent analysis (PCA:). The application of PCA to first-derivative spectra
resulted as a robust method of processing spectral data and made it possibl
e to distinguish the binding medium and/or the pigment/dye. and to classify
test samples by means of the Mahalanobis distance discrimination method.