论文信息 - Generalised supervised local tangent space alignment for hyperspectral image classification

Generalised supervised local tangent space alignment for hyperspectral image classification

Providing the kernel function of the local tangent space alignment (LTSA) algorithm, the generalisation of both LTSA and supervised LTSA (SLTSA) is achieved. Moreover, using the generalised SLTSA (GSLTSA), a simplified classification algorithm is proposed for hyperspectral image data. Experimental results demonstrate that the generalisation method has good performance, and the GSLTSA is capable of exploiting the nonlinear properties of hyperspectral data to benefit the classification.

Jinwen Tian | M. Crawford | Li Ma

[1] Hongyuan Zha,et al. Principal Manifolds and Nonlinear Dimension Reduction via Local Tangent Space Alignment , 2002, ArXiv.

[2] Nicolas Le Roux,et al. Learning Eigenfunctions Links Spectral Embedding and Kernel PCA , 2004, Neural Computation.

[3] H. Zha,et al. Principal manifolds and nonlinear dimensionality reduction via tangent space alignment , 2004, SIAM J. Sci. Comput..

[4] Hongyu Li,et al. Supervised Learning on Local Tangent Space , 2005, ISNN.

[5] Jing Wang. Improve local tangent space alignment using various dimensional local coordinates , 2008, Neurocomputing.

[6] Eric O. Postma,et al. Dimensionality Reduction: A Comparative Review , 2008 .