An efficient classification by signal subspace projection and partial filtering for hyperspectral images

摘要

In this study, we propose an efficient classification which combines signal subspace projection (SSP) and partial filtering technique for hyperspectral images. To reduce the computation complexity in image classification, we exploit high degree correlations in spectral and spatial domains. During training process, image bands are first partitioned into several groups for each desired class by Maximum Correlation Band Clustering (MCBC) approach. Then, we design partial filters for each band group by SSP approach. Finally, the SSP-based partial filtering (SSPPF) are combined using corresponding weights for each class. For real image classification, simulations validate the proposed SSPPF can achieve the performance of SSP with less computation complexity. Generally, the proposed method requires only 1/k~2 computations of SSP, if image is partitioned into k groups.