TY - GEN
T1 - Unsupervised Hyperspectral Band Selection Based on Maximum Information Entropy and Determinantal Point Process
AU - Yang, Zhijing
AU - Chen, Weizhao
AU - Yan, Yijun
AU - Cao, Faxian
AU - Cai, Nian
N1 - Copyright:
© 2018, Springer Nature Switzerland AG.
PY - 2018
Y1 - 2018
N2 - Band selection is of great important for hyperspectral image processing, which can effectively reduce the data redundancy and computation time. In the case of unknown class labels, it is very difficult to select an effective band subset. In this paper, an unsupervised band selection algorithm is proposed which can preserve the original information of the hyperspectral image and select a low-redundancy band subset. First, a search criterion is designed to effectively search the best band subset with maximum information entropy. It is challenging to select a low-redundancy spectral band subset with maximizing the search criteria since it is a NP-hard problem. To overcome this problem, a double-graph model is proposed to capture the correlations between spectral bands with full use of the spatial information. Then, an improved Determinantal Point Process algorithm is presented as the search method to find the low-redundancy band subset from the double-graph model. Experimental results verify that our algorithm achieves better performance than other state-of-the-art methods.
AB - Band selection is of great important for hyperspectral image processing, which can effectively reduce the data redundancy and computation time. In the case of unknown class labels, it is very difficult to select an effective band subset. In this paper, an unsupervised band selection algorithm is proposed which can preserve the original information of the hyperspectral image and select a low-redundancy band subset. First, a search criterion is designed to effectively search the best band subset with maximum information entropy. It is challenging to select a low-redundancy spectral band subset with maximizing the search criteria since it is a NP-hard problem. To overcome this problem, a double-graph model is proposed to capture the correlations between spectral bands with full use of the spatial information. Then, an improved Determinantal Point Process algorithm is presented as the search method to find the low-redundancy band subset from the double-graph model. Experimental results verify that our algorithm achieves better performance than other state-of-the-art methods.
KW - Determinantal Point Process (DPP)
KW - Graph model
KW - Maximum information
KW - Unsupervised band selection
UR - http://www.scopus.com/inward/record.url?scp=85055132739&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-00563-4_34
DO - 10.1007/978-3-030-00563-4_34
M3 - Conference contribution
AN - SCOPUS:85055132739
SN - 9783030005627
T3 - Lecture Notes in Computer Science
SP - 352
EP - 361
BT - Advances in Brain Inspired Cognitive Systems
A2 - Hussain, Amir
A2 - Luo, Bin
A2 - Zheng, Jiangbin
A2 - Zhao, Xinbo
A2 - Liu, Cheng-Lin
A2 - Ren, Jinchang
A2 - Zhao, Huimin
PB - Springer
CY - Switzerland
T2 - 9th International Conference on Brain-Inspired Cognitive Systems, BICS 2018
Y2 - 7 July 2018 through 8 July 2018
ER -