TY - GEN
T1 - KL-Weighted Graph Sparse Self-Representation for Unsupervised Hyperspectral Band Selection
AU - Li, Pengjie
AU - Zhao, Juan
AU - Teng, Weike
AU - Bai, Xia
AU - Wang, Shaobo
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Unsupervised band selection (BS) methods have attracted much attention in hyperspectral imagery (HSI), which can select informative bands to solve the problems of information redundancy and high computational complexity. In this paper, we propose a KL-weighted graph sparse self-representation (SSR) method for unsupervised BS, in which the dissimilarity of bands measured via KL divergence is integrated into the superpixel-based graph SSR model by weighting the sparse representation coefficient matrix. An alternating optimization algorithm is designed to obtain the optimal coefficient matrix and the representative bands are finally selected by the norm ranking of rows of the coefficient matrix. Experimental results on HIS datasets show the effectiveness of the proposed BS algorithm and it outperforms other related BS methods in selecting proper representative bands for classification.
AB - Unsupervised band selection (BS) methods have attracted much attention in hyperspectral imagery (HSI), which can select informative bands to solve the problems of information redundancy and high computational complexity. In this paper, we propose a KL-weighted graph sparse self-representation (SSR) method for unsupervised BS, in which the dissimilarity of bands measured via KL divergence is integrated into the superpixel-based graph SSR model by weighting the sparse representation coefficient matrix. An alternating optimization algorithm is designed to obtain the optimal coefficient matrix and the representative bands are finally selected by the norm ranking of rows of the coefficient matrix. Experimental results on HIS datasets show the effectiveness of the proposed BS algorithm and it outperforms other related BS methods in selecting proper representative bands for classification.
KW - Kullack-Leibler (KL) divergence
KW - band selection (BS)
KW - hyperspectral imagery (HIS)
KW - sparse self-representation (SSR)
UR - http://www.scopus.com/inward/record.url?scp=85186496300&partnerID=8YFLogxK
U2 - 10.1109/ICICML60161.2023.10424811
DO - 10.1109/ICICML60161.2023.10424811
M3 - Conference contribution
AN - SCOPUS:85186496300
T3 - 2023 International Conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023
SP - 716
EP - 720
BT - 2023 International Conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023
Y2 - 3 November 2023 through 5 November 2023
ER -