Local Collaborative Representation With Adaptive Dictionary Selection for Hyperspectral Image Classification

Abstract

Spectral-spatial representation based algorithms have been widely applied in hyperspectral image (HSI) classification, which exploit the fact that pixels in a local patch often have similar spectral reflectance values and probably belong to the same class. Collaborative representation (CR) is a typical supervised classification method for high-dimensional data, which has been widely used for spectral-spatial representation based HSI classification. However, it suffers from the degraded representation of redundant and irrelative pixels when all of the labeled pixels are used as a dictionary for representation. In this letter, a novel method, local CR with adaptive dictionary selection, is proposed to solve this problem, in which we first average the values of pixels from local patches to incorporate the contextual information of neighbors, and then, an adaptive dictionary selection method is presented to select the most similar pixels to each test pixel from the dictionary to reduce the influence of redundant and irrelevant pixels in representation. Experimental results on two HSIs show that the proposed method outperforms some spectral-spatial representation based algorithms in terms of classification accuracy.