Spectral-spatial classification based on integrated segmentation

A new spectral-spatial method for the classification of hyperspectral images is introduced. The proposed approach is based on two segmentation methods, Fractional-Order Darwinian Particle Swarm Optimization and Mean Shift Segmentation and one clustering method, K-means. In parallel, the input data set is classified by Support Vector Machines (SVM). Furthermore, the result of the segmentation and clustering steps are combined with the result of SVM through majority voting within each object. The final classification map is made by using majority voting between three produced classification maps. Experimental results indicate that the proposed method can significantly improve SVM and other studied methods in terms of accuracies.