TY - JOUR
T1 - Dimensionality reduction based on determinantal point process and singular spectrum analysis for hyperspectral images
AU - Chen, Weizhao
AU - Yang, Zhijing
AU - Cao, Faxian
AU - Yan, Yijun
AU - Wang, Meilin
AU - Qing, Chunmei
AU - Cheng, Yongqiang
PY - 2018/9/5
Y1 - 2018/9/5
N2 - Dimensionality reduction is of high importance in hyperspectral data processing, which can effectively reduce the data redundancy and computation time for improved classification accuracy. Band selection and feature extraction methods are two widely used dimensionality reduction techniques. By integrating the advantages of the band selection and feature extraction, the authors propose a new method for reducing the dimension of hyperspectral image data. First, a new and fast band selection algorithm is proposed for hyperspectral images based on an improved determinantal point process (DPP). To reduce the amount of calculation, the dual-DPP is used for fast sampling representative pixels, followed by k-nearest neighbour-based local processing to explore more spatial information. These representative pixel points are used to construct multiple adjacency matrices to describe the correlation between bands based on mutual information. To further improve the classification accuracy, two-dimensional singular spectrum analysis is used for feature extraction from the selected bands. Experiments show that the proposed method can select a low-redundancy and representative band subset, where both data dimension and computation time can be reduced. Furthermore, it also shows that the proposed dimensionality reduction algorithm outperforms a number of state-of-the-art methods in terms of classification accuracy.
AB - Dimensionality reduction is of high importance in hyperspectral data processing, which can effectively reduce the data redundancy and computation time for improved classification accuracy. Band selection and feature extraction methods are two widely used dimensionality reduction techniques. By integrating the advantages of the band selection and feature extraction, the authors propose a new method for reducing the dimension of hyperspectral image data. First, a new and fast band selection algorithm is proposed for hyperspectral images based on an improved determinantal point process (DPP). To reduce the amount of calculation, the dual-DPP is used for fast sampling representative pixels, followed by k-nearest neighbour-based local processing to explore more spatial information. These representative pixel points are used to construct multiple adjacency matrices to describe the correlation between bands based on mutual information. To further improve the classification accuracy, two-dimensional singular spectrum analysis is used for feature extraction from the selected bands. Experiments show that the proposed method can select a low-redundancy and representative band subset, where both data dimension and computation time can be reduced. Furthermore, it also shows that the proposed dimensionality reduction algorithm outperforms a number of state-of-the-art methods in terms of classification accuracy.
KW - image representation
KW - spectral analysis
KW - feature extraction
KW - image sampling
KW - geophysical image processing
KW - hyperspectral imaging
KW - image classification
KW - learning
UR - http://digital-library.theiet.org/content/journals/iet-ipr
U2 - 10.1049/iet-ipr.2018.5419
DO - 10.1049/iet-ipr.2018.5419
M3 - Article
JO - IET Image Processing
JF - IET Image Processing
SN - 1751-9659
ER -