Image deconvolution using tree-structured Bayesian group sparse modeling

Author

Ganchi Zhang ; Roberts, Timothy D. ; Kingsbury, Nick

Author_Institution

Dept. of Eng., Univ. of Cambridge, Cambridge, UK

fYear

2014

fDate

27-30 Oct. 2014

Firstpage

4537

Lastpage

4541

Abstract

In this paper, we propose to incorporate wavelet tree structures into a recently developed wavelet modeling method, called VBMM. We show that, using overlapped groups, tree-structured modeling can be integrated into the high-performance non-convex sparsity-inducing VBMM method, and can achieve significant performance gains over the coefficient-sparse version of the algorithm.

Keywords

deconvolution; discrete wavelet transforms; image processing; inference mechanisms; minimisation; trees (mathematics); variational techniques; image deconvolution; nonconvex sparsity inducing VBMM method; tree structured Bayesian group sparse modeling; tree structured modeling; variational Bayesian inference subband adaptive majorization minimization method; wavelet modeling method; wavelet tree structure; Approximation methods; Bayes methods; Computational modeling; Deconvolution; Hidden Markov models; Signal processing algorithms; Wavelet transforms; Image deconvolution; dual-tree complex wavelets; variational Bayesian; wavelet tree modeling;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2014 IEEE International Conference on

Conference_Location

Paris

Type

conf

DOI

10.1109/ICIP.2014.7025920

Filename

7025920

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=249393