Abstract
In the hyperspectral unmixing literature, endmember extraction is addressed majorly using three methods i.e. Statistical, Sparse-regression and Geometrical. The majority of the endmember extraction algorithms are developed based on only one of the methods. Recently, GSEE (Geo-Stat Endmember Extraction) has been proposed that combines the geometrical and statistical features. In this paper, we propose a Modified GSEE (MGSEE) algorithm which considers the removal of noisy bands. In the proposed work, the Minimum Noise Fraction (MNF) is used to select high SNR bands. The strength of the MGSEE framework is scrutinized using a synthetic and real benchmark dataset. In this paper, we show that the proposed algorithm obtained from the GSEE by preceding the noise removal step greatly decreases Spectral Angle Error (SAE) and Spectral Information Divergence (SID) error thus indicating its importance to extract pure material in the unmixing problem.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
