Adaptive hybrid threshold shrinkage using singular value decomposition

Zhai, Lin1; Dong, Linjia2,3; Liu, Yining4; Fu, Shujun5; Wang, Fengling6; Li, Yuliang7

2019

10.1117/1.JEI.28.6.063002

Journal of Electronic Imaging   影响因子和分区

1560229X

1560-229X

We present a method for image denoising based on singular value shrinkage that fuses soft and hard thresholds. The technique simply groups similar patches from a noisy image as low-rank matrices and shrinks the singular values by the combination of soft and hard thresholds. On one hand, a hard threshold approximation method based on nonlocal self-similarity and low-rank approximation is used for fast selection of hard threshold; on the other hand, a soft threshold selection method based on random matrix and asymptotic matrix reconstruction theory is designed. In addition, we also propose an adaptive backward projection algorithm based on image phase congruency and gradient calculation so that the input images participating in the iteration are adaptive. This method improves the traditional fixed coefficient backward projection method and makes the robustness of the algorithm better. The experimental results of denoising and enhancement for a number of natural images show that the proposed algorithms have significant improvement in both subjective visual effect and objective quantization index by comparing with some related state-of-the-art denoising algorithms.
© 2019 SPIE and IS&T.

image denoising image enhancement low-rank approximation singular value decomposition hybrid threshold adaptive backward projection

SCI ; EI

英语

其他

Natural Science Foundation of Shandong Province[ZR2019MF045] ; National Natural Science Foundation of China[11971269]

Engineering ; Optics ; Imaging Science & Photographic Technology

Engineering, Electrical & Electronic ; Optics ; Imaging Science & Photographic Technology

WOS:000505570400002

SPIE

20200508096580

Approximation theory ; Image enhancement ; Iterative methods ; Shrinkage ; Singular value decomposition

Information Theory and Signal Processing:716.1 ; Mathematics:921 ; Numerical Methods:921.6 ; Materials Science:951

ENGINEERING

Web of Science

1.Shenyang Aerospace University, School of Science, Shenyang, China
2.Harbin Institute of Technology, School of Mathematics, Harbin, China
3.Southern University of Science and Technology, Department of Finance, Shenzhen, China
4.Shandong University, School of Material Science and Engineering, Jinan, China
5.Shandong University, School of Mathematics, Jinan, China
6.Shandong University of Arts, College of Arts Management, Jinan, China
7.Second Hospital of Shandong University, Department of Intervention Medicine, Jinan, China

Zhai, Lin,Dong, Linjia,Liu, Yining,et al. Adaptive hybrid threshold shrinkage using singular value decomposition[J]. Journal of Electronic Imaging,2019,28(6).

Zhai, Lin,Dong, Linjia,Liu, Yining,Fu, Shujun,Wang, Fengling,&Li, Yuliang.(2019).Adaptive hybrid threshold shrinkage using singular value decomposition.Journal of Electronic Imaging,28(6).

Zhai, Lin,et al."Adaptive hybrid threshold shrinkage using singular value decomposition".Journal of Electronic Imaging 28.6(2019).