Share Email Print
cover

Proceedings Paper

An algorithm for unsupervised unmixing of hyperspectral imagery using positive matrix factorization
Author(s): Yahya M. Masalmah; Miguel Velez-Reyes; Samuel Rosario-Torres
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents an approach for simultaneous determination of endmembers and their abundances in hyperspectral imagery using a constrained positive matrix factorization. The algorithm presented here solves the constrained PMF by formulating it as a nonnegative least squares problem where the cost function is expanded with a penalty term to enforce the sum to one constraint. Preliminary results using simulated and AVIRIS-Cuprite data are presented. These results show the potential of the method to solve the unsupervised unmixing problem.

Paper Details

Date Published: 1 June 2005
PDF: 8 pages
Proc. SPIE 5806, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XI, (1 June 2005); doi: 10.1117/12.605672
Show Author Affiliations
Yahya M. Masalmah, Univ. of Puerto Rico/Mayaguez (United States)
Miguel Velez-Reyes, Univ. of Puerto Rico/Mayaguez (United States)
Samuel Rosario-Torres, Univ. of Puerto Rico/Mayaguez (United States)


Published in SPIE Proceedings Vol. 5806:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XI
Sylvia S. Shen; Paul E. Lewis, Editor(s)

© SPIE. Terms of Use
Back to Top