Fusion of SVMs in wavelet domain for hyperspectral data classification

Discrete wavelet transform (DWT) provides a multiresolution view of hyperspectral data. This paper proposes a method to combine the wavelet features at different layers to improve the classification accuracy of hyperspectral data, where both global and local spectral features could be exploited. After feature extraction using DWT, the wavelet feature set of each layer is processed independently by support vector machines (SVMs). Then, the probability outputs of SVMs at each layer are fused to get the final class probability, and the classification result will be the class label with the maximum final class probability. Experimented with the Washington DC Mall hyperspectral data, the results demonstrate that the proposed method can outperform the same classifier with original features, the wavelet features (without fusion), and the wavelet energy features.