Share Email Print

Proceedings Paper

Accelerating hyperspectral manifold learning using graphical processing units
Author(s): Santiago Velasco-Forero; Vidya Manian
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Manifold learning has been widely studied in pattern recognition, image processing, and machine learning. A large number of nonlinear manifold learning methods have been proposed attempting to preserve a different geometrical property of the underlying manifold. In contrast, its application to hyperspectral images is computationally difficult due to the calculation of distances among spectral values in high-dimensional spaces. This paper compares feature extraction algorithms using isomap, Laplacian Eigenmaps, and local linear embedding in real hyperspectral images. They are implemented using massively parallel general purpose Graphical Processor Units (GPUs) to speed up computation. Their performance in classification of hyperspectral images and speed up of their computation is presented. Results using real and synthetic hyperspectral scenarios are presented. Additionally, a formulation including spatial information in these manifold learning algorithms is presented.

Paper Details

Date Published: 27 April 2009
PDF: 11 pages
Proc. SPIE 7334, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV, 73341R (27 April 2009); doi: 10.1117/12.820176
Show Author Affiliations
Santiago Velasco-Forero, Mines ParisTech (France)
Vidya Manian, Univ. de Puerto Rico Mayagüez (United States)

Published in SPIE Proceedings Vol. 7334:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV
Sylvia S. Shen; Paul E. Lewis, Editor(s)

© SPIE. Terms of Use
Back to Top