Using feature-vector based analysis, based on principal component analysis and independent component analysis, for analysing hyperspectral images

Abstract

A pixel in a hyperspectral image can be considered as a mixture of the reflectance spectra of several substances. The mixture coefficients correspond to the (relative) amounts of these substances. The benefit of hyperspectral imagery is that many different substances can be characterised and recognised by their spectral signatures. Independent component analysis (ICA) can be used for the blind separation of mixed statistically independent signals. Principal component analysis (PCA) also gives interesting results. The next step is to interpret and use the ICA or PCA results efficiently. This can be achieved by using a new technique called feature-vector based analysis (FVBA), which produces a number of component-feature vector pairs. The obtained feature vectors and the corresponding components represent, in this case, the spectral signatures and the corresponding image weight coefficients (the relative concentration maps) of the different constituting substances.