Dimensionality Reduction of Hyperspectral Images Based on Robust Spatial Information Using Locally Linear Embedding

In this letter, we propose an improved locally linear embedding (LLE) method based on robust spatial information (named RSLLE) for hyperspectral data dimensionality reduction. It explores and takes full account of the complexity of the spatial information for LLE. In RSLLE, when searching for spectral neighbors, a kind of spectral-spatial distance is used instead of the distance between two individual target pixels. Then, two additional steps, i.e., spatial neighbor sorting and spatial neighbor filtering, are presented to ensure the robustness of the spectral-spatial distance. Two classification experimental results indicate that the proposed RSLLE method significantly improves the performance when compared with other LLE methods, and the classification accuracy is competitive compared with other latest spectral-spatial classification methods.