Comparative study on morphological principal component analysis of hyperspectral images
Abstract
This paper deals with a problem of reducing the dimension of hyperspectral images using the principal component analysis. Since hyperspectral images are always reduced before any process, we choose to do this reduction by adding spatial information that can be useful then for classification process; to do it we choose to project our data in new spaces thanks mathematical morphology.
Origin : Files produced by the author(s)
Loading...