Nonlinear feature extraction of hyperspectral data based on locally linear embedding (LLE)

Abstract

Feature extraction is an indispensable preprocessing step for information extraction from hyperspectral remote sensing data. In this paper, we introduce a nonlinear feature extraction algorithm, called Locally Linear Embedding (LLE), and customize it for hyperspectral remote sensing applications. Unlike the linear feature extraction algorithms based on… (More)
DOI: 10.1109/IGARSS.2005.1525342

6 Figures and Tables

Cite this paper

@article{Han2005NonlinearFE, title={Nonlinear feature extraction of hyperspectral data based on locally linear embedding (LLE)}, author={Tian Han and David G. Goodenough}, journal={Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05.}, year={2005}, volume={2}, pages={1237-1240} }