8 May 2006 A comparison of algorithms to compute the positive matrix factorization and their application to unsupervised unmixing
Author Affiliations +
Proceedings Volume 6233, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII; 623326 (2006); doi: 10.1117/12.667977
Event: Defense and Security Symposium, 2006, Orlando (Kissimmee), Florida, United States
Abstract
This paper presents a comparison of different algorithms to compute the constrained positive matrix factorization and their application to the unsupervised unmixing problem. We study numerical methods based on the Gauss-Newton algorithm, the Seung-Lee approach, the Gauss-Seidel algorithm, and penalty methods. Preliminary results using a Hyperion image from southwestern Puerto Rico presented. Algorithms will be compared in terms of their convergence performance, and quality of the results.
© (2006) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yahya M. Masalmah, Miguel Vélez-Reyes, "A comparison of algorithms to compute the positive matrix factorization and their application to unsupervised unmixing", Proc. SPIE 6233, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XII, 623326 (8 May 2006); doi: 10.1117/12.667977; https://doi.org/10.1117/12.667977
PROCEEDINGS
11 PAGES


SHARE
KEYWORDS
Error analysis

Algorithm development

Hyperspectral imaging

Optimization (mathematics)

Sensors

Remote sensing

Image classification

Back to Top