Spherical Harmonics as a Shape Descriptor for HyperspectralImage Classification

摘要

Hyperspectral images have traditionally been analyzed by pixel based methods. Invariant methods that considersurface and shape geometry have not been used with these images. However, there is a need for such methods dueto the spectral and spatial variability present in these images. In this paper, we develop a method for classifyingthese images invariant to translation and rotation. The method is based on developing shape descriptors usingspherical harmonics. These orthogonal functions have been widely used as a powerful tool for 3D shape recognitionand are better suited for hyperspectral images due to its inherent dimensionality. A spherical function defined on thesurface of a shape extracts rotation invariant features. In this case, the hyperspectral image is converted to sphericalcoordinates, decomposed as a sum of its harmonics and then converted to Cartesian coordinates. A classifier istrained with spherical harmonic descriptors computed from training samples. Support vector machines andMaximum Likelihood are considered for classification. The method is tested with hyperspectral image from AISA,AVIRIS and HYDICE sensors. The results show that the descriptors are effective in improving the accuracy ofclassification.