Hyperspectral Images Classification by Spectral-Spatial Processing

A spectral-spatial hyperspectral image classification is proposed in this paper. The proposed method has two main contributions. 1-It removes the useless spatial information such as noise and distortions by applying the proposed smoothing filter. 2-It adds useful spatial information such as shape and size of objects presented in scene image by applying morphological filters. Moreover, the proposed method copes with the small sample size problem by partitioning the hyperspectral image into several subsets of adjacent bands. Experimental results show that the proposed method is able to obtain higher classification accuracy compared to some state-of-the-art spectral-spatial classification methods.