Coupling hyperspectral image data having different spatial resolutions using Multiple Co-inertia Analysis

Coupling different techniques in spectroscopy is an efficient approach to characterise complex biological material. This work is carried out to characterise maize stem cell wall composition in the context of biofuel production. In this research, we propose to couple infrared, fluorescence and Raman hyperspectral images.Investigations have been attempted in coupling spectral data by means of multiblock methods. Multiblock techniques have been assumed to be equally applicable and effective in the analysis of biological samples with complex chemical composition and structure. The most commonly used methods are based on sequential approaches. In this article, we propose 1) to condition the data to be analysed towards multiblock analysis in term of pre-processing and organising the blocks from the initial hyperspectral images, 2) to apply Multiple Co-inertia Analysis (MCoA) a symmetrical method providing orthogonal loadings for spectral interpretation and score images for spatial analysis, and 3) to interpret and to analyse in one hand the common structure revealed by the three modalities and in the other hand the independent contribution to explain the variability under each block.