1 INTRODUCTION

FOURIER TRANSFORM INFRARED (FT-IR) SPECTROSCOPY requires minimal sample amounts to provide reliable characterization of the major components in a mixture. With the aid of computer techniques such as spectral subtraction (Koenig, 1975) and deconvolution (Kaupinnen et.al., 1981), the intrinsic information from the spectra can be used to identify even minor components of a mixture. FT-IR has significant advantages over less accurate dispersive spectrophotometers (Low and Baer, 1977). The Fourier transform instrument produces a high resolution spectrum in a very short scan time. This rapid scan time allows for the integration of a large number of scans, thus effectively averaging any noise and yielding spectra with a very high signal-to-noise ratio. Accuracy and reproducibility of spectral band position is achieved in the FT-IR instrument by internal laser calibration (Koenig and Tabb, 1974).

The usual procedure for identifying an unknown by its infrared spectrum is to visually match band positions and their relative intensities with the spectrum of a known material. This can easily be done for a pure sample using a computer search program to rapidly compare an unknown to a digitized library of several thousand known pure compounds. However, because unknown samples are often impure, erroneous spectral matches can result. A spectrum for a mixture of materials contains the vibrational bands for each component, therefore a method for separating the bands must be used to identify the individual compounds. This can be done either by separating the mixture components prior to analysis, such as with solvent extraction (Mills, 1972), or by carefully sorting out the bands in the complicated spectra of the mixture. In the latter approach, the major infrared absorption bands are first used to identify the general class or classes of the components. Then, specific band positions of the unknown are compared with bands from reference materials (Smith, 1979).

This investigation used the method of spectral identification of compounds in a mixture by band position to study natural resins typically used in historic furniture finishes. Brachert (1978) gave detailed recipes for historical furniture finishes. The five most often used resins (shellac, sandarac, mastic, copal and rosin) were selected from Brachert's compilation of recipes (see Table 2 for frequency of use). A variety of infrared analyses was done on these five resins. First, sets of known resins were used to check the band position variability due to sample preparation, sample size, resin supplier, varnish preparation (solvent extraction and filtration) and resin aging (oxidation and deterioration). The specific bands which were most stable were then selected for an identification key for these resins. Secondly, mixtures of these five resins were prepared in formulations listed by Brachert and in test mixtures with individual concentrations as low as 1%. In these known mixtures, each component could be identified by using the infrared band position identification key along with computer methods of deconvolution and spectral subtraction. Finally, this resin identification method was applied to the analysis of finish samples from 18th century furniture to characterize their resin content. This method works well for the identification of resin types because it is solely based on band position; further information on resin genera and sources may be gained by also examining the characteristics of band intensity and band shape (Gianno, et.al., 1987).

Table 2 Identification Key For Infrared Spectra Of Natural Resins Absorption bands represented as wavenumbers (� 2.6 cm−)