Abstract

In order to reduce the effect of spectral variability on calculation precision for the weighted matrix in the locality preserving projection (LPP) algorithm, an improved dimensionality reduction method named endmember extraction-based locality preserving projection (EE-LPP) is proposed in this paper. The method primarily uses the vertex component analysis (VCA) method to extract endmember spectra from hyperspectral imagery. It then calculates the similarity between pixel spectra and the endmember spectra by using the spectral angle distance, and uses it as the basis for selecting neighboring pixels in the image and constructs a weighted matrix between pixels. Finally, based on the weighted matrix, the idea of the LPP algorithm is applied to reduce the dimensions of hyperspectral image data. Experimental results of real hyperspectral data demonstrate that the low-dimensional features acquired by the proposed methods can fully reflect the characteristics of the original image and further improve target detection accuracy.

© 2016 The Author(s)

Hyperspectral agricultural mapping using Support Vector Machine-Based Endmember Extraction (SVM-BEE)

Anthony M. Filippi, Rick Archibald, Budhendra L. Bhaduri, and Edward A. Bright
Opt. Express 17(26) 23823-23842 (2009)

Stochastic spectral unmixing with enhanced endmember class separation

Michael T. Eismann and Russell C. Hardie
Appl. Opt. 43(36) 6596-6608 (2004)

Multiscale target extraction using a spectral saliency map for a hyperspectral image

Jing Zhang, Wenhao Geng, Li Zhuo, Qi Tian, and Yan Cao
Appl. Opt. 55(28) 8089-8100 (2016)

Dissimilarity sparsity-preserving projections in feature extraction for visual recognition

Fengtao Xiang, Zhengzhi Wang, and Xingsheng Yuan
Appl. Opt. 52(20) 5022-5029 (2013)

End-member extraction based on segmented vertex component analysis in hyperspectral images

Mingyu Nie, Zhi Liu, Xiaofu He, Qingchen Qiu, Yuanyuan Zhang, and Ju Chang
Appl. Opt. 56(9) 2476-2482 (2017)