A comparison on methods for dimensionality reduction of hyperspectral images

Feature extraction, implemented as a linear projection from a higher dimensional space to a lower dimensional subspace, is a very important issue in hyperspectral data analysis. A relevant objective of feature extraction in hyperspectral data analysis, is to reduce the dimensionality of the data maintaining the capability of discriminating object of interest from the cluttered background. This thesis is intended to develop a system that implements, for comparison purposes, different methods of dimensionality reduction to be applied on hyperspectral images. The mechanisms are unsupervised band subset selection techniques, Projection Pursuit, and Principal Component Analysis. Unsupervised band subset selection chooses automatically the most independent set of bands. Projection Pursuit automatically searches for projections that optimize a projection index. Finally they were compared with Principal Component Analysis. The methods were tested using synthetic as well as remotely sensed data. They were compared using unsupervised classification methods in a known ground-truth area.