Automatic classification system of Raman spectra applied to pigments analysis

Abstract

Raman spectroscopy is one of the few non-destructive techniques capable of identifying pigments in art works. Raman spectra contain powerful information that can be used to identify unknown compounds and their chemical structures. However, the analysis of spectral data comes with some difficulties and therefore the spectral interpretation is not straightforward. Sometimes, there are very little differences in the spectral data concerning to specific identification objectives, for instance, in polymorphic discrimination or in the discrimination of natural and synthetic forms of certain pigments. Moreover, this discrimination is often performed manually so that the process can be repetitive, subjective, and particularly time-consuming. The result is an increasing motivation to automate the identification process involved in the classification of pigments in paint. In this paper, we propose a system to automatically classify the spectral data into specific and well-known classes, i.e. reference classes. The proposal is based on a combination of chemometric techniques, which provides a powerful way to achieve spectral separability so that it is possible to discriminate between very similar spectra in an automatic way. In this regard, a decision-making algorithm was specifically developed to select the corresponding reference class with no user input, which was successfully validated using simulated spectra. The implemented methodology was used to classify Raman spectra of pigments commonly present in artist's paints in experimental cases, providing reliable and consistent results. Therefore, the presented system can play a good auxiliary role in the analysts' endpoint classification.

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

“…Binary pigment mixtures were explored by Gonz alez-Vidal et al 23 They used PCA to reduce the size of the dataset (baseline corrected, intensity normalized, interpolated spectra). The reference dataset was composed of 20 inorganic and 31 SOPs.…”

Identification of Pre-1950 Synthetic Organic Pigments in Artists’ Paints. A Non-Invasive Approach Using Handheld Raman Spectroscopy

“…It should, however, be taken into account that reference spectra are mostly acquired on pure materials, like pigment powders. When compared with paint systems, differences in heat dispersion or fluorescence behaviour may lead to slight differences in the spectra [43,44]. The excitation wavelength and power of the laser can influence the reference spectra too.…”

Recent advances in linear and non‐linear Raman spectroscopy. Part XI

“…Gonzalez‐Vidal co‐workers described an automatic classification system of Raman spectra applied to pigments analysis. Their implemented methodology was used to classify Raman spectra of pigments commonly present in artist's paints in experimental cases, providing reliable and consistent results . Kupka et al described the modeling of red coral ( Corallium rubrum ) and African snail (Helixia aspersa) shell pigments by means of the comparison of measured Raman versus calculated DFT spectra.…”

“…Their implemented methodology was used to classify Raman spectra of pigments commonly present in artist's paints in experimental cases, providing reliable and consistent results. [129] Kupka et al described the modeling of red coral (Corallium rubrum) and African snail (Helixia aspersa) shell pigments by means of the comparison of measured Raman versus calculated DFT spectra. It was concluded that all-trans polyene pigments of red coral and dark parts of African snail shell contain 11-12 and 14 C=C double bond units, respectively; however, Raman spectroscopy cannot produce any clear information on the presence and nature of the end-chain substituents in the studied pigments.…”