Share Email Print
cover

Proceedings Paper

Wavelet techniques for band selection and material classification from hyperspectral data
Author(s): Nikola S. Subotic; John D. Gorman; Brian J. Thelen
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We describe a band selection process based on wavelet analysis of hyperspectral data which naturally decomposes the data into sub-bands. Wavelet analysis allows the control of the position, resolution, and envelope of the specific spectral sub-bands which will be selected. The sub-band sets are selected to maximize the Kullback-Liebler distance between specific classes of materials for a specific dimensionality contraint or discrimination performance goal. A sequential construction of the sub-band sets is used as an approximation to the global maximization operation over all possible sub-band sets. A max/min strategy is also introduced to provide a robust framework for sub-band selection when faced with multiple materials. We show band selection and material classification results of this technique applied to Fourier transform spectrometer data.

Paper Details

Date Published: 12 June 1995
PDF: 9 pages
Proc. SPIE 2480, Imaging Spectrometry, (12 June 1995); doi: 10.1117/12.210896
Show Author Affiliations
Nikola S. Subotic, Environmental Research Institute of Michigan (United States)
John D. Gorman, Environmental Research Institute of Michigan (United States)
Brian J. Thelen, Environmental Research Institute of Michigan (United States)


Published in SPIE Proceedings Vol. 2480:
Imaging Spectrometry
Michael R. Descour; Jonathan Martin Mooney; David L. Perry; Luanna R. Illing, Editor(s)

© SPIE. Terms of Use
Back to Top