Nonparametric Bayesian dictionary learning algorithm based on structural similarity

Daoguang DONG; Guosheng RUI; Wenbiao TIAN; Jian KANG; Ge LIU

doi:10.11959/j.issn.1000-436x.2019015

您当前的位置：

首页 >

文章列表页 >

Nonparametric Bayesian dictionary learning algorithm based on structural similarity

Papers | 更新时间：2024-06-05

- Nonparametric Bayesian dictionary learning algorithm based on structural similarity
- Journal on Communications Vol. 40, Issue 1, Pages: 43-50(2019)
- 作者机构：
  
  海军航空大学信号与信息处理山东省重点实验室，山东烟台 264001
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(41606117);The National Natural Science Foundation of China(41476089);The National Natural Science Foundation of China(61671016)
- DOI：10.11959/j.issn.1000-436x.2019015
  CLC： TP301.6
- Online First：2019-01，
  
  Published：25 January 2019
- 稿件说明：
移动端阅览
Daoguang DONG, Guosheng RUI, Wenbiao TIAN, et al. Nonparametric Bayesian dictionary learning algorithm based on structural similarity[J]. Journal on Communications, 2019, 40(1): 43-50.
DOI：

Daoguang DONG, Guosheng RUI, Wenbiao TIAN, et al. Nonparametric Bayesian dictionary learning algorithm based on structural similarity[J]. Journal on Communications, 2019, 40(1): 43-50. DOI： 10.11959/j.issn.1000-436x.2019015.

摘要

相较于传统综合字典学习方法，非参数贝叶斯方法具有显著优势，但其对图像结构全局相似性和变异性的表示能力仍有较大提升空间。针对这个问题，提出了一种基于结构相似性的非参数贝叶斯字典学习算法，该算法基于图像结构的全局相似性对图像进行聚类处理，并在图像的字典稀疏表示中引入块结构特性，提升了字典的结构表示能力。实验表明，所提算法在图像去噪和压缩感知方面的性能均优于目前主流的几种无监督字典学习算法。

Abstract

Though nonparametric Bayesian methods possesses significant superiority with respect to traditional comprehensive dictionary learning methods

there is room for improvement of this method as it needs more consideration over the structural similarity and variability of images.To solve this problem

a nonparametric Bayesian dictionary learning algorithm based on structural similarity was proposed.The algorithm improved the structural representing ability of dictionaries by clustering images according to their non-local structural similarity and introducing block structure into sparse representing of images.Denoising and compressed sensing experiments showed that the proposed algorithm performs better than several current popular unsupervised dictionary learning algorithms.

关键词

Keywords

references

FEDOROV I , RAO B D , NGUYEN T Q . Multimodal sparse Bayesian dictionary learning applied to multimodal data classification [C ] // IEEE International Conference on Acoustics . 2017 : 2237 - 2241 .

HUANG Y , PAISLEY J , LIN Q , et al . Bayesian nonparametric dictionary learning for compressed sensing MRI [J ] . IEEE Transactions on Image Processing , 2014 , 23 ( 12 ): 5007 - 5019 .

LI S , TAO X , LU J . Variational Bayesian inference for nonparametric signal compressive sensing on structured manifolds [C ] // IEEE International Conference on Communications . 2017 : 1 - 6 .

LI Z , HUANG H , MISRA S . Compressed sensing via dictionary learning and approximate message passing for multimedia Internet of things [J ] . IEEE Internet of Things Journal , 2017 , 4 ( 2 ): 505 - 512 .

HUANG Y , PAISLEY J , LIN Q , et al . Bayesian nonparametric dictionary learning for compressed sensing MRI [J ] . IEEE Transactions on Image Processing , 2014 , 23 ( 12 ): 5007 - 5019 .

HONG P D , CHAINAIS P . A Bayesian non-parametric approach to learn dictionaries with adapted numbers of atoms [C ] // IEEE International Workshop on Machine Learning for Signal Processing . 2015 : 1 - 6 .

ZHOU M , CHEN H , PAISLEY J , et al . Nonparametric Bayesian dictionary learning for analysis of noisy and incomplete images [J ] . IEEE Transactions on Image Processing , 2012 , 21 ( 1 ): 130 - 144 .

LIU Z , YU L , ZHANG M , et al . Nonlocal structured nonparametric Bayesian dictionary learning for image denoising [C ] // IEEE International Conference on Signal Processing . 2017 : 144 - 148 .

ZHOU M , YANG H , SAPIRO G , et al . Dependent hierarchical beta process for image interpolation and denoising [J ] . Aistats , 2012 , 15 : 883 - 891 .

PAISLEY J , ZHOU M , SAPIRO G , et al . Nonparametric image interpolation and dictionary learning using spatially-dependent dirichlet and beta process priors [C ] // IEEE International Conference on Image Processing . 2010 : 1869 - 1872 .

ZHOU M , CHEN H , PAISLEY J , et al . Non-parametric Bayesian dictionary learning for sparse image representations [C ] // International Conference on Neural Information Processing Systems . 2009 , 21 ( 1 ): 2295 - 2303 .

ZHOU G , ZHU D , WANG K , et al . Wavelet image inpainting based on dictionary learning with a Beta process [C ] // Proceedings of 2010 Conference on Dependable Computing . 2010 : 83 - 88 .

ZHU L , HUANG Z , LIU Y , et al . The nonparametric Bayesian dictionary learning based interpolation method for WSN missing data [J ] . AEU-International Journal of Electronics and Communications , 2017 ( 79 ): 267 - 274 .

HE L , QI H , ZARETZKI R . Beta process joint dictionary learning for coupled feature spaces with application to single image super- resolution [J ] . Computer Vision ＆ Pattern Recognition , 2013 , 9 ( 4 ): 345 - 352 .

GUPTA S K , PHUNG D , ADAMS B , et al . A Bayesian framework for learning shared and individual subspaces from multiple data sources [C ] // Pacific-Asia Conference on Advances in Knowledge Discovery ＆ Data Mining . 2011 , 6634 ( 1 ): 136 - 147 .

GUPTA S K , PHUANG D , VENKATESH S . A Bayesian nonparametric joint factor model for learning shared and individual subspaces from multiple data sources [C ] // Proc of Siam Int Conference on Data Mining . 2013 : 200 - 212 .

LI S , TAO X , LU J . Variational inference for nonparametric subspace dictionary learning with hierarchical Beta process [C ] // IEEE International Conference on Acoustics . 2017 : 2691 - 2695 .

LI S , TAO X , DONG L . A nonparametric Bayesian approach to joint multiple dictionary learning with separate image sources [J ] . Signal ＆Information Processing , 2016 : 1155 - 1159 .

CHASPARI T , TSILIFIS P . MCMC inference of parametric dictionaries for sparse Bayesian approximations [J ] . IEEE Transactions on Signal Processing , 2016 , 64 ( 12 ): 3077 - 3092 .

Views

1513

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

RIS substructure-based direct localization algorithm with multipath suppression via compressed sensing

Massive unsourced multiple access scheme based on block sequence codebook and compressed sensing

Basis expansion model-based improved regularized orthogonal matching pursuit channel estimation for V2X fast time-varying SC-FDMA

Multi-source information transmission and classification algorithm for equipment based on compressed sensing

Compressed sensing reconstruction algorithm based on adaptive acceleration forward-backward pursuit

Related Author

Hu Nan

Zhang Yanyu

Liu Lihao

Wang Jianhui

Li Jingjing

Lin MA

Jing ZHANG

Chulong LIANG

Related Institution

College of Information Systems Engineering, Information Engineering University

Jiangsu Province Key Lab of Wireless Communications

China Post Construction Technology Co., Ltd.

School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications

ZTE Co., Ltd.

AI问答

⁰