A subspace kernel learning method for feature extraction of the hyperspectral image

作者：Liu Zhenlin; Gu Yanfeng^*; Zhang Ye

来源：Journal of Harbin Engineering University, 2014, 35(2): 238-244.

DOI：10.3969/j.issn.1006-7043.201309025

• Airborne visible infrared imaging spectrometer
• Data dimension reduction
• Hyper-spectral images
• Hyperspectral Imaging
• Kernel learning methods
• Kernel methods
• Kernel principal component analyses (KPCA)
• Physical characteristics

Feature extraction is quite valuable for the mining and utilization of valid information in hyperspectral remote-sensing imaging and the increase of subsequent classified applications. For improving the dimension reduction effect, a subspace-modulated kernel principal component analysis (SM-KPCA) method is proposed. With this method, the grouping natures of hyperspectral data are integrated into a uniform kernel method framework and a subspace-modulated kernel is constructed. SMK (subspace-modulated kernel) achieves a sparse modulation on the spectral waveband by means of feature grouping;in addition, it is a data-adaptive kernel for measuring the nonlinear similarities among the hyperspectral data specimens. With the proposed method, AVIRIS (airborne visible infrared imaging spectrometer) real hyperspectral imaging is applied for evaluation. Additionally, this method is compared with the conventional kernel method and the spectrally weighted kernel method. The experimental results show that the SM-KPCA method more sufficiently utilizes the complex and relevant physical characteristics between wavebands. Therefore, it outperforms both the conventional kernel methods and the spectrally weighted kernel method regarding the aspect of the classification of hyperspectral images.

• 出版日期2014