Independent Component Analysis-Based Algorithm for Automatic Identification of Raman Spectra Applied to Artistic Pigments and Pigment Mixtures

Abstract

A new method has been developed to automatically identify Raman spectra, whether they correspond to single- or multicomponent spectra. The method requires no user input or judgment. There are thus no parameters to be tweaked. Furthermore, it provides a reliability factor on the resulting identification, with the aim of becoming a useful support tool for the analyst in the decision-making process. The method relies on the multivariate techniques of principal component analysis (PCA) and independent component analysis (ICA), and on some metrics. It has been developed for the application of automated spectral analysis, where the analyzed spectrum is provided by a spectrometer that has no previous knowledge of the analyzed sample, meaning that the number of components in the sample is unknown. We describe the details of this method and demonstrate its efficiency by identifying both simulated spectra and real spectra. The method has been applied to artistic pigment identification. The reliable and consistent results that were obtained make the methodology a helpful tool suitable for the identification of pigments in artwork or in paint in general.

In Situ Identification of Pigment Composition and Particle Size on Wall Paintings Using Visible Spectroscopy as a Noninvasive Measurement Method

“…Required by the integrity of the invaluable and non-renewable artworks, numerous efforts have been undertaken to develop in situ noninvasive measuring tools and effective analytical methodologies that can identify the chemical composition of the mineral pigments without any contact with wall paintings. [1][2][3] Visible reflectance spectroscopy, due to the portability of its acquisition device and safety to artworks, has drawn increasing attention in recent years in the field of pigment composition identification related to artworks. [4][5][6] In order to investigate the color change of artworks induced by the environment, visible reflectance spectroscopy was introduced in artworks protection by the National Gallery in the late 1970s.…”

An overview of Principal Components Analysis approaches in Raman studies of cultural heritage materials

“…The authors pointed out that band distortion and fluorescence could negatively affect the results of identification of mixtures and that the results of identification and the reliability factor are intended to guide the analyst in spectral interpretation. González‐Vidal et al also proposed a more advanced version of automatic identification of pigments in mixtures 24 that did not rely on the operator's input and that provided a confidence factor to guide the decision‐making process. The pre‐processing required baseline correction, calibration and interpolation of the x ‐axis, and a min‐max normalization, the latter to improve reproducibility across instruments while maintaining peak intensity ratios.…”

Independent components analysis (ICA) at the “cocktail-party” in analytical chemistry

“…For example, an ICA-based method was able to differentiate between single-and multi-component mixture spectra without prior knowledge of the analyzed sample in an automated manner. The method has been applied to artistic pigment identification [44].…”