摘要：Hyperspectral images face the problem of high dimensionality and lowsamples number, which results in unsatisfied recognition efficiency, thus dimensionalityreduction is needed before terrain classification. A novel hyperspectral imagesfeature extraction method is presented for dimensionality reduction. Firstly,take discrete Fourier transformation (DFT) of each pixel spectral curve, andcombine the amplitude spectrum and corresponding phase spectrum; then directlinear discriminant analysis (DLDA) is performed in the combination spectrumspace to extract features. Minimum distance classifier is used to evaluate thefeature extraction performance in the achievedcombination spectrum DLDA subspace. The experimental results for airbornevisible/infrared imaging spectrometer (AVIRIS) hyperspectral image show that,comparing with the spectral DLDA subspace method, the present method canimprove the terrain classification efficiency.
