Hyperspectral Image Classification via Multiple-Feature-Based Adaptive Sparse Representation

Abstract

A multiple-feature-based adaptive sparse representation (MFASR) method is proposed for the classification of hyperspectral images (HSIs). The proposed method mainly includes the following steps. First, four different features are separately extracted from the original HSI and they reflect different kinds of spectral and spatial information. Second, for each pixel, a shape adaptive (SA) spatial region is extracted. Third, an adaptive sparse representation algorithm is introduced to obtain the sparse coefficients for the multiple-feature matrix set of pixels in each SA region. Finally, these obtained coefficients are jointly used to determine the class label of each test pixel. Experimental results demonstrated that the proposed MFASR method can outperform several well-known classifiers in terms of both qualitative and quantitative results.