Morphological feature extraction and spectral unmixing of hyperspectral images

Hyperspectral image processing has been a very active area in remote sensing and other application domains in recent years. Despite the availability of a wide range of advanced processing techniques for hyperspectral data analysis, a great majority of available techniques for this purpose are based on the consideration of spectral information separately from spatial information information, and thus the two types of information are not treated simultaneously. In this paper, we describe several innovative spatial/spectral techniques for hyperspectral image processing. The techniques described in this work cover different aspects of hyperspectral image processing such as dimensionality reduction, feature extraction, and spectral unmixing. The techniques addressed in this paper are based on concepts inspired by mathematical morphology, a theory that provides a remarkable framework to achieve the desired integration of spatial and spectral information. The proposed techniques are experimentally validated using standard hyperspectral data sets with ground-truth, and compared to traditional approaches in the hyperspectral imaging literature, revealing that the integration of spatial and spectral information can significantly improve the analysis of hyperspectral scenes when conducted in simultaneous fashion.