Title :
Endmember Extraction Using a Combination of Orthogonal Projection and Genetic Algorithm
Author :
Rezaei, Y. ; Mobasheri, M.R. ; Zoej, M. J Valaddan ; Schaepman, M.E.
Author_Institution :
Fac. of Geomatics, K.N. Toosi Univ. of Technol., Tehran, Iran
fDate :
3/1/2012 12:00:00 AM
Abstract :
Common endmember extraction algorithms presume that the number of materials present is either known or may be predetermined by using spectral databases or other approaches. In this letter, we propose a new method called genetic orthogonal projection (GOP) for endmember extraction in imaging spectrometry. GOP is based on a fully unsupervised approach and uses convex geometric characteristics as well as a genetic algorithm. We compare GOP with existing endmember extraction algorithms and demonstrate that GOP partially outperforms them, without the need of a priori information.
Keywords :
convex programming; feature extraction; genetic algorithms; convex geometric characteristic; endmember extraction algorithm; genetic algorithm; genetic orthogonal projection; imaging spectrometry; spectral database; Estimation; Feature extraction; Genetic algorithms; Hyperspectral imaging; Imaging; Signal to noise ratio; Absorption features; endmember extraction; genetic algorithm (GA); linear mixing model;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2011.2162936