Classification of Hyperspectral Image using SVM Post-Processing for Shape Preserving Filter and PCA
This paper is based on an experimentation to preserve shapes of the natural classes in a hyperspectral image post classification of the image using SVM. The classifier classifies the vegetation types present in the hyperspectral image and then estimates the crop types present in the image. In doing so it preserves the spatial shapes of the vegetation types spread in the image using an Edge-preserving filter. The shape-preserving filter was applied prior to dimension reduction where by the low information content spectral components are discarded using Principal Component Analysis. The classification of the features is performed using SVM. The result has been found very effective in characterizing significant spectral and spatial structures of objects in a scene..
