Local Adaptive Image Denoising based on Double-Density Dual-Tree Complex Wavelet

doi:null

您当前的位置：

首页 >

文章列表页 >

Local Adaptive Image Denoising based on Double-Density Dual-Tree Complex Wavelet

Article | 更新时间：2020-08-13

- Local Adaptive Image Denoising based on Double-Density Dual-Tree Complex Wavelet
- Optics and Precision Engineering Vol. 17, Issue 5, Pages: 1171-1180(2009)
- 作者机构：
  
  重庆大学光电工程学院
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Received：03 July 2008，
  
  Revised：09 September 2008，
  
  Published Online：25 May 2009，
  
  Published：25 May 2009
- 稿件说明：
移动端阅览
龚卫国,刘晓营,李伟红,李建福. 基于双密度双树复小波变换的局域自适应图像去噪[J]. 光学精密工程, 2009,17(5):1171-1180

Local Adaptive Image Denoising based on Double-Density Dual-Tree Complex Wavelet[J]. Optics and precision engineering, 2009, 17(5): 1171-1180.
龚卫国,刘晓营,李伟红,李建福. 基于双密度双树复小波变换的局域自适应图像去噪[J]. 光学精密工程, 2009,17(5):1171-1180 DOI：

Local Adaptive Image Denoising based on Double-Density Dual-Tree Complex Wavelet[J]. Optics and precision engineering, 2009, 17(5): 1171-1180. DOI：

摘要

提出一种基于双密度双树复小波变换的局域自适应图像去噪算法。首先，分析了双密度双树复小波变换的原理及特点，给出了双变量收缩函数(BSF)的推导。然后，对噪声图像并行使用四个二维双密度离散小波变换，且行和列采用不同的滤波器组，实现对噪声图像的双密度双树复小波分解。根据小波系数的统计特性以及层内和层间系数的相关性，采用结合局域方差估计的双变量收缩函数对小波系数进行处理。用收缩后的小波系数重构去噪图像。最后，将该算法用于灰度图像和彩色图像去噪。实验结果表明：在噪声方差为30时，经该算法去噪后图像与噪声图像相比，获得最高的峰值信噪比增益达11.72dB，平均结构相似度最高增加2.7倍，复合峰值信噪比增益达11.68dB。且对不同噪声方差下的不同噪声图像，该算法在滤除噪声的同时保留更多的细节，去噪图像的视觉质量得到很大的改善。

Abstract

An efficient local adaptive image denoising algorithm based on the double-density dual-tree complex wavelet transform (DD-DT CWT) is proposed. First

The principles and characteristics of DD-DT CWT are analyzed and the derivation of bivariate shrinkage function(BSF) is given. DD-DT CWT is implemented by applying four 2-D double-density DWTs in parallel to the noise images with distinct filter sets for the rows and columns. According to the statistical properties of wavelet coefficients and the dependency of inter-level and intra-level coefficients

the bivariate shrinkage function with local variance estimation is adopted to processing wavelet coefficients. The denoised images are synthesized using the wavelet coefficients after processing. Finally

The proposed algorithm is tested on some gray and color noisy images. Experimental results show that

compared with the noise images

the Peak Signal-to-Noise Ratio (PSNR) gains reach 11.72dB

Mean Structural Similarity (MSSIM)2.7 times and Composite Peak Signal-to-Noise Ratio (CPSNR) 11.68dB when the noise variance is 30. Meanwhile

the proposed algorithm is more efficient in noise removal and edge reservation for all the noise images with different noise variance

and that the visual quality of the denoised images is improved.

关键词

Keywords

references

Views

310

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image denoising with dual-directional filter bank GSM model and non-local mean filter

Adaptive image enhancement based on NSCT coefficient histogram matching

4f System Image Denoising in NSCT Domain Based On the Continuity of Image Texture*

Image denoising using non-Gaussian bivariate model based on non-aliasing Curvelet transform

Related Author

LIU Qiao-hong

LI Bin

LIN Min

ZHOU Yan

LI Qing-wu

HUO Guan-ying

徐鑫

YAN He

Related Institution

School of Mechatronic Engineering and Automation, Shanghai University

College of IOT Engineering, Hohai University

Changzhou Key Laboratory of Sensor Networks and Environmental Sensing

重庆大学通信工程学院

重庆大学光电技术及系统教育部重点实验室

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰