Dimensionality Reduction of Hyperspectral Images with Wavelet-Based Empirical Mode Decomposition

This paper presents an application of the Empirical Mode Decomposition (EMD) method to wavelet based dimensionality reduction. Useful spectral information for hyperspectral image can be obtained by applying the Wavelet Transform (WT) to each hyperspectral signature and EMD helps to get a better understanding of the spatial information of the signal. In order to take advantage of both spectral and spatial information, a novel dimensionality reduction method is introduced, which relies on using the WT of EMD features. Specifically, the 2D-EMD is applied to each hyperspectral band and the 1D-DWT is applied to each EMD feature of all bands to get Wavelet-based Intrinsic Mode Function Features(WIMF). Then, new features are generated by summing up WIMF features. The superiority of the proposed method is proven by using the AVIRIS Indian Pine data. Compared to conventional wavelet-based methods, proposed method offers up to 65% dimensionality reduction for the same classification performance.