Nonnegative Matrix Factorization with Earth Mover's Distance Metric for Image Analysis

2011 ◽  
Vol 33 (8) ◽  
pp. 1590-1602 ◽  
Author(s):  
Roman Sandler ◽  
Michael Lindenbaum
2015 ◽  
Vol 713-715 ◽  
pp. 1540-1545
Author(s):  
Cheng Yong Zheng

Hyperspectral unmixing (HSU) plays an important role in hyperspectral image analysis, and most of the current HSU algorithms are base on linear mixing model (LMM). This paper gives a review of two linear HSU methods that have been drawn great attention recently: one is constrained nonnegative matrix factorization (CNMF) based method, the other is constrained sparse regression (CSR) based method. We carried on the systematic summary to these two types of methods, based on which, we point out some potential research topics.


2012 ◽  
Vol 45 (12) ◽  
pp. 4080-4091 ◽  
Author(s):  
Symeon Nikitidis ◽  
Anastasios Tefas ◽  
Nikos Nikolaidis ◽  
Ioannis Pitas

Sign in / Sign up

Export Citation Format

Share Document