I intend to apply the Spectral Angle Mapper (SAM), Maximum Likelihood (MLC) and Support Vector Machine (SVM) algorithms on a hyperspectral dataset in ENVI but I am slightly confused as to how to derive the endmembers (different land covers in this case) after applying Principal Component Analysis. I have performed radiometric correction and a forward PCA rotation which resulted in 3 PCA bands. However, I am slightly confused regarding endmember selection procedures when using PCA.
For example, for the MLC algorithm I understand that if I wasnt using PCA I would simply create new Regions of Interest to select the endmembers from the original radiance image.
However, when using PCA as a dimensionality reduction technique, I am not sure where to derive the endmembers from. i.e is it from the original radiance image or from the PCA components?