Hyperspectral Mixed Noise Removal by ℓ1-Norm-Based Subspace Representation

Lina Zhuang*, Michael K. Ng

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

74 Citations (Scopus)

Abstract

This article introduces a new hyperspectral image (HSI) denoising method that is able to cope with additive mixed noise, i.e., mixture of Gaussian noise, impulse noise, and stripes, which usually corrupt hyperspectral images in the acquisition process. The proposed method fully exploits a compact and sparse HSI representation based on its low-rank and self-similarity characteristics. In order to deal with mixed noise having a complex statistical distribution, we propose to use the robust ell _1 data fidelity instead of using the ell _2 data fidelity, which is commonly employed for Gaussian noise removal. In a series of experiments with simulated and real datasets, the proposed method competes with state-of-the-art methods, yielding better results for mixed noise removal.

Original languageEnglish
Article number9040508
Pages (from-to)1143-1157
Number of pages15
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume13
DOIs
Publication statusPublished - 18 Mar 2020

User-Defined Keywords

  • High-dimensional data
  • hyperspectral destriping
  • hyperspectral restoration
  • low-rank representation
  • nonlocal patch
  • self-similarity

Fingerprint

Dive into the research topics of 'Hyperspectral Mixed Noise Removal by ℓ1-Norm-Based Subspace Representation'. Together they form a unique fingerprint.

Cite this