Discriminative Low-Rank Rank Gabor Filtering for Spectral Spectral–Spatial Spatial Hyperspectral Image Classification
Abstract: Spectral-spatial spatial classification of remotely sensed hyperspectral images has attracted a lot of attention in recent years. Although Gabor filtering has been used for feature extraction from hyperspectral images, its capacity to extract relevant information from both the spectral and the spatial domains of the image has not been fully explored yet. In this paper, we present a new discriminative low-rank rank Gabor filtering (DLRGF) method for spectral spectral-spatial spatial hyperspectral image classification. A main innovation of the proposed approach is that our implementation is accomplish accomplished ed by decomposing the standard 3-D 3 spectralspatial Gabor filter into eight subfilters, which correspond to different combinations of low-pass pass and bandpass single single-rank rank filters. Then, we show that only one of the subfilters (i.e., the one that performs low low-pass pass spatial filtering and bandpass spectral filtering) is actually appropriate to extract suitable features based on the characteristics of hyperspectral images. This allows us to perform spectral-spatial spatial classification in a highly discriminative and computationally comp efficient way, by significantly decreasing the computational complexity (from cubic to linear order) compared with the 33-D spectral-spatial spatial Gabor filter. In order to theoretically prove the discriminative ability of the selected subfilter, we derive d an overall classification risk bound to evaluate the discriminating abilities of the features provided by the different subfilters. Our experimental results, conducted