Investigation of the applicability of Zernike moments to the classification of SDS 2D-PAGE maps

The aim of this work is to investigate the performance of multivariate classification techniques like partial least squares-discriminant analysis (PLS-DA) and linear discriminant analysis (LDA) when using Zernike moments as global image descriptors, in the classification of sodium dodecyl sulphate (SDS) two-dimensional polyacrylamide gel electrophoresis (2D-PAGE) maps affected by different levels of deformation. Synthetic sets of images simulating real SDS 2D-PAGE maps were analysed in controlled conditions to obtain information on the robustness and limits of applicability of the classification techniques operating on the basis of a given image decomposition method.