Hybrid-Weighted Total Variation and Nonlocal Low-Rank-Based Image Compressed Sensing Reconstruction

Cheng Huang,Yanzhou Liu,Hui Zhao,Tianlong Wang

doi:10.1109/access.2020.2970158

Cheng Huang, Yanzhou Liu + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.2970158

Copy DOI

Abstract

To reconstruct natural images from compressed sensing (CS) measurements accurately and effectively, a CS image reconstruction algorithm based on hybrid-weighted total variation (HWTV) and nonlocal low-rank (NLR) is proposed. It considers the local smoothness and nonlocal self-similarity (NSS) in image, improves traditional hybrid total variation (TV) model, and constructs a new edge detection operator with mean curvature to adaptively select the TV. The HWTV combines the advantages of first-order TV and second-order TV to preserve the edges of the image and avoid the staircase effect in the smooth areas. And NLR can effectively reduce the redundant information and retain the structural information of the image. In addition, the proposed algorithm constructs prior regularization terms with improved HWTV model and NLR model, and utilizes soft threshold function and smooth but non-convex function to solve the TV and low-rank optimization problems, respectively. Finally, the alternative direction multiplier method (ADMM) iterative strategy is used to separate the target model into several sub-problems, and the most efficient methods are adopted to solve each sub-problem. Experimental results show that, compared with the state-of-the-art CS reconstruction algorithms, the proposed algorithm can achieve higher reconstruction quality, especially in the case of low sampling rates.

Highlights

Compressed sensing [1], [2] theory proposes a new sampling framework, which simultaneously samples and compresses sparse or compressible signals at a sampling rate significantly below Nyquist’s sampling theorem [3], and can perfectly reconstruct the signal from only a small number of linear measurements by the corresponding optimization algorithm
When the sampling rate is 0.05, the original image information obtained is less, but the original image can be reconstructed with high quality from less information, which fully demonstrates that the reconstruction algorithm has superior performance
The traditional compressed sensing (CS) image reconstruction algorithm only considers the single property of the image, which makes the reconstructed image less effect and the adaptability of the algorithm is weak

Summary

Introduction

Compressed sensing [1], [2] theory proposes a new sampling framework, which simultaneously samples and compresses sparse or compressible signals at a sampling rate significantly below Nyquist’s sampling theorem [3], and can perfectly reconstruct the signal from only a small number of linear measurements by the corresponding optimization algorithm. Based on the above problems, this paper proposes a new HWTV and NLR models based image CS reconstruction algorithm. The first-order TV model is weighted, and the new weight coefficient is constructed by difference curvature to improve the ability of the edge preservation and denoising performance of the algorithm.

Results

Conclusion