shahdharam7/MGSEE

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.

Title

Modified GSEE algorithm for Hyperspectral Endmember Extraction

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.

Cite this paper as

D. Shah and T. Zaveri, "Modified GSEE algorithm for Hyperspectral Endmember Extraction," 2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA), Greater Noida, India, 2020, pp. 449-453, doi: 10.1109/ICCCA49541.2020.9250711.

How to run the code?

Download all the above files in zip. Extract it. And run the "demo_cuprite.m" file in MATLAB.

Authors:

• Dharambhai Shah, Nirma University ---> shahdharam7@gmail.com (For any clarification)
• Tanish Zaveri, Nirma University ---> ztanish@nirmauni.ac.in

Link for related codes:

https://sites.google.com/site/shahdharam7790/research