26 December 2016 Extracting pure endmembers using symmetric sparse representation for hyperspectral imagery
Author Affiliations +
Abstract
This article proposes a symmetric sparse representation (SSR) method to extract pure endmembers from hyperspectral imagery (HSI). The SSR combines the features of the linear unmixing model and the sparse subspace clustering model of endmembers, and it assumes that the desired endmembers and all the HSI pixel points can be sparsely represented by each other. It formulates the endmember extraction problem into a famous program of archetypal analysis, and accordingly, extracting pure endmembers can be transformed as finding the archetypes in the minimal convex hull containing all the HSI pixel points. The vector quantization scheme is adopted to help in carefully choosing the initial pure endmembers, and the archetypal analysis program is solved using the simple projected gradient algorithm. Seven state-of-the-art methods are implemented to make comparisons with the SSR on both synthetic and real hyperspectral images. Experimental results show that the SSR outperforms all the seven methods in spectral angle distance and root-mean-square error, and it can be a good alternative choice for extracting pure endmembers from HSI data.
© 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)
Weiwei Sun, Weiwei Sun, Chun Liu, Chun Liu, Yanwei Sun, Yanwei Sun, Weiyue Li, Weiyue Li, Jialin Li, Jialin Li, } "Extracting pure endmembers using symmetric sparse representation for hyperspectral imagery," Journal of Applied Remote Sensing 10(4), 045023 (26 December 2016). https://doi.org/10.1117/1.JRS.10.045023 . Submission: Received: 11 April 2016; Accepted: 6 December 2016
Received: 11 April 2016; Accepted: 6 December 2016; Published: 26 December 2016
JOURNAL ARTICLE
14 PAGES


SHARE
Back to Top