Micro-Raman and X-ray fluorescence spectroscopy data fusion for the classification of ochre pigments

Two different data-fusion strategies are evaluated for the combination of the outputs of combined Raman/X-Ray fluorescence instrument. The studied application deals with the classification of ochre pigments investigated in the field of cultural heritage. The two fusion strategies are: (1) first level fusion: combines raw signals obtained from each technique and (2) second level fusion: combines extracted features provided individually by each technique. Classification tool is partial least squares-discriminant analysis (PLS-DA). Classification results obtained performing different data-fusion strategies are compared with those results obtained performing a single classification model for each data source. The results show that the combination of signal features is the most suitable for a rapid and unique processing of both types of spectra. Benefits and drawbacks of each strategy are also discussed.