A variety of dimensionality reduction methods have been proposed in the literature to address the issue of information redundancy in hyperspectral images. A recent one, named superpixel-based principal components analysis (SuperPCA), integrates the superpixel segmentation algorithm and principal components analysis (PCA) to exploit contextual information in the process of feature extraction. The present letter aims at improving SuperPCA method via a band grouping technique. It also provides appropriate base images for the production of extended morphological profiles (EMPs). This proposed method was applied to two real case studies and the results proved an overall accuracy improvement of 8% over the SuperPCA. Furthermore, the EMPs resulted from our proposed method could reach to better spatial-spectral classification results in comparison to those methods that apply conventional base images for EMPs production.

Hyperspectral images are efficient tools for discriminating different types of earth's surface materials. Spectral features traditionally perform classification of hyperspectral images, but different studies have proved the efficiency of spatial features as complementary information in increasing the classification accuracy. The fractal geometry can be regarded as a potent tool for spatial data modeling. This study proposes a new classification method based on the integration of fractal and spectral features. For this purpose, three groups of fractal features, including mono-fractal, lacunarity and multi-fractal features are generated from the first few principal components of the hyperspectral image in different window sizes. These features are later stacked with spectral features and then fed to support vector machines classifier. The experiments are conducted on two real hyperspectral images Indian Pines, Pavia University. Final classification accuracy proved the superiority of the proposed classification method against the other competitive spatial-spectral methods.