Spectral-spatial classification of hyperspectral images by combining hierarchical and marker-based Minimum Spanning Forest algorithms

Many researches have demonstrated that the spatial information can play an important role in the classification of hyperspectral imagery. This study proposes a modified spectral–spatial classification approach for improving the spectral–spatial classification of hyperspectral images. In the proposed method ten spatial/texture features, using mean, standard deviation, contrast, homogeneity, correlation, dissimilarity, energy, entropy, wavelet transform and Gabor filter, are first extracted. The Weighted Genetic algorithm is then used to obtain the subspace of hyperspectral data and texture features. Finally, the hierarchical segmentation and marker-based Minimum Spanning Forest (MSF) classification algorithms are combined with the majority voting law. To evaluate the efficiency of the proposed approach two image datasets, Indiana Pine and Washington DC Mall, were used. Experimental results demonstrate that the proposed approach achieves approximately 10% and 7% better overall accuracy than the Support Vector Machine (SVM) algorithm for these datasets, respectively.