Abstract
Sparsity is an important prior for various signals, and sparsity-based methods have been widely used in hyperspectral image classification. This chapter introduces the sparse representation methodology and its related techniques for hyperspectral image classification. To start with, we provide a brief review on the mechanism, models, and algorithms of sparse representation classification (SRC). We then introduce several advanced SRC methods that can improve hyperspectral image classification accuracy by incorporating spatial–spectral information into SRC models. As a case study, a hyperspectral image SRC method based on adaptive spatial context is discussed in detail to demonstrate the performance of SRC methods in hyperspectral image classification.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have