Hyperspectral Image Denoising via Nonconvex Logarithmic Penalty

Shuo Wang,Ruwen Zhao,Zhibin Zhu,Benxin Zhang,Ana C Teodoro

doi:10.1155/2021/5535169

Abstract

Hyperspectral images (HSIs) can help deliver more reliable representations of real scenes than traditional images and enhance the performance of many computer vision tasks. However, in real cases, an HSI is often degraded by a mixture of various types of noise, including Gaussian noise and impulse noise. In this paper, we propose a logarithmic nonconvex regularization model for HSI mixed noise removal. The logarithmic penalty function can approximate the tensor fibered rank more accurately and treats singular values differently. An alternating direction method of multipliers (ADMM) is also presented to solve the optimization problem, and each subproblem within ADMM is proven to have a closed-form solution. The experimental results demonstrate the effectiveness of the proposed method.

Highlights

A hyperspectral image (HSI) consists of multiple discrete bands at specific frequencies
The framework of the tensor singular value decomposition (t-SVD) lacks flexibility for handling different correlations along the different modes of HSIs, leading to suboptimal denoising performance. en, Zheng et al [38] proposed an HSI mixed noise removal model with tensor fibered rank, which is based on the mode-k tSVD
E three evaluation measures are the mean peak signalto-noise ratio (MPSNR), mean structure similarity (MSSIM), and spectral angle mapping (SAM). e three metrics are defined as follows to measure the quality of the denoised result: L2MN PSNR 10 ∗ log10􏽐Mx 1 􏽐Ny 1 [􏽢I(x, y) − I(x, y)]2, 1B

Summary

Introduction

A hyperspectral image (HSI) consists of multiple discrete bands at specific frequencies. Based on low tubal-rank tensor recovery, Zhang et al [37] proposed an HSI mixed noise removal model. En, Zheng et al [38] proposed an HSI mixed noise removal model with tensor fibered rank, which is based on the mode-k tSVD. By using the sum of the log function of singular values, 3DLogTNN can better approximate to the fibered rank than 3DTNN. To avoid the intrinsic difficulties, we introduce a new nonconvex logarithmic regularization model, which allows the use of nonconvex penalty function while maintaining convexity of the subproblem within ADMM.

Brief Overview of Tensor Singular Value Decomposition

A2 Fold A3

HSI Denoising Model and Its ADMM

Experiment Results

Method

Conclusion