Robust Regression-Based Markov Random Field for Hyperspectral Image Classification

Abstract

Recently, regression-based classifiers, such as the sparse representation classifier and collaborative representation classifier, have been proposed for hyperspectral image (HSI) classification. However, HSIs are typically corrupted by noise, occlusion, or data loss. Obtaining a good performance for most regression-based methods is difficult. To address this challenge, we present a novel robust regression-based nearest regularized subspace (R²NRS) for HSI classification. In our method, each band of a pixel is assigned with a regularized regression coefficient in the NRS model to reduce the influence of those bands corrupted during classification. The reconstruction error, Markov random field, and high-confidence index next jointly generate a comprehensive spatial-spectral model to perform the HSI classification. The experimental results on two HSI data sets demonstrate the superior performance of our proposed method for HSI classification for the case when some bands of the image are corrupted by noise or data loss.