Foreword to the Special Issue on Pattern Recognition in Remote Sensing

Patch Tensor-Based Sparse and Low-Rank Graph for Hyperspectral Images Dimensionality Reduction

“…W ITH hundreds of spectral bands, hyperspectral images contain abundant land-cover information and have been successfully applied in many areas, such as classification [1], [2], target detection [3], [4], anomaly detection [5], [6] and others [7]- [9]. On the other hand, caused by a large number of spectral bands, challenges are met in the application of hyperspectral images, such as excessive storage space, large computational cost, and lack of the labeled samples.…”