Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain

Paul R Hill; Jin-Hwan Kim; Adrian Basarab; Denis Kouamé; David Bull; Alin M Achim

doi:10.1109/ICIP.2016.7532812

Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain

Paul R Hill, Jin-Hwan Kim, Adrian Basarab, Denis Kouamé, David Bull, Alin M Achim

Visual Information Laboratory

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

19 Citations (Scopus)

373 Downloads (Pure)

Abstract

Approximate Message Passing (AMP) is an iterative reconstruction algorithm that performs signal denoising within a compressive sensing framework. We propose the use of heavy tailed distribution based image denoising, specifically using a Cauchy prior based Maximum A-Posteriori (MAP) estimate within a wavelet based AMP compressive sensing structure. The use of this MAP denoising algorithm provides extremely fast convergence for image based compressive sensing. The proposed method converges approximately twice as fast as the compared AMP methods whilst providing superior final MSE results over a range of measurement rates.

Original language	English
Title of host publication	2016 IEEE International Conference on Image Processing (ICIP 2016)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	2514-2518
Number of pages	5
ISBN (Electronic)	9781467399616
ISBN (Print)	9781467399623
DOIs	https://doi.org/10.1109/ICIP.2016.7532812
Publication status	Published - Mar 2017

Publication series

Name	IEEE International Conference on Image Processing (ICIP)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)	2381-8549

Access to Document

10.1109/ICIP.2016.7532812

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at http://ieeexplore.ieee.org/document/7532812/. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 357 KB

Handle.net

Persistent link

Vision for the Future-Full
Bull, D. R. (Principal Investigator)
1/02/15 → 31/01/20
Project: Research

Cite this

Hill, P. R., Kim, J.-H., Basarab, A., Kouamé, D., Bull, D., & Achim, A. M. (2017). Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain. In 2016 IEEE International Conference on Image Processing (ICIP 2016) (pp. 2514-2518). (IEEE International Conference on Image Processing (ICIP)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICIP.2016.7532812

@inproceedings{318a2c9ab282487ba214c2d6961d981c,

title = "Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain",

abstract = "Approximate Message Passing (AMP) is an iterative reconstruction algorithm that performs signal denoising within a compressive sensing framework. We propose the use of heavy tailed distribution based image denoising, specifically using a Cauchy prior based Maximum A-Posteriori (MAP) estimate within a wavelet based AMP compressive sensing structure. The use of this MAP denoising algorithm provides extremely fast convergence for image based compressive sensing. The proposed method converges approximately twice as fast as the compared AMP methods whilst providing superior final MSE results over a range of measurement rates.",

author = "Hill, \{Paul R\} and Jin-Hwan Kim and Adrian Basarab and Denis Kouam{\'e} and David Bull and Achim, \{Alin M\}",

year = "2017",

month = mar,

doi = "10.1109/ICIP.2016.7532812",

language = "English",

isbn = "9781467399623",

series = "IEEE International Conference on Image Processing (ICIP)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "2514--2518",

booktitle = "2016 IEEE International Conference on Image Processing (ICIP 2016)",

address = "United States",

}

Hill, PR, Kim, J-H, Basarab, A, Kouamé, D, Bull, D & Achim, AM 2017, Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain. in 2016 IEEE International Conference on Image Processing (ICIP 2016). IEEE International Conference on Image Processing (ICIP), Institute of Electrical and Electronics Engineers (IEEE), pp. 2514-2518. https://doi.org/10.1109/ICIP.2016.7532812

Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain. / Hill, Paul R; Kim, Jin-Hwan; Basarab, Adrian et al.
2016 IEEE International Conference on Image Processing (ICIP 2016). Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 2514-2518 (IEEE International Conference on Image Processing (ICIP)).

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain

AU - Hill, Paul R

AU - Kim, Jin-Hwan

AU - Basarab, Adrian

AU - Kouamé, Denis

AU - Bull, David

AU - Achim, Alin M

PY - 2017/3

Y1 - 2017/3

N2 - Approximate Message Passing (AMP) is an iterative reconstruction algorithm that performs signal denoising within a compressive sensing framework. We propose the use of heavy tailed distribution based image denoising, specifically using a Cauchy prior based Maximum A-Posteriori (MAP) estimate within a wavelet based AMP compressive sensing structure. The use of this MAP denoising algorithm provides extremely fast convergence for image based compressive sensing. The proposed method converges approximately twice as fast as the compared AMP methods whilst providing superior final MSE results over a range of measurement rates.

AB - Approximate Message Passing (AMP) is an iterative reconstruction algorithm that performs signal denoising within a compressive sensing framework. We propose the use of heavy tailed distribution based image denoising, specifically using a Cauchy prior based Maximum A-Posteriori (MAP) estimate within a wavelet based AMP compressive sensing structure. The use of this MAP denoising algorithm provides extremely fast convergence for image based compressive sensing. The proposed method converges approximately twice as fast as the compared AMP methods whilst providing superior final MSE results over a range of measurement rates.

U2 - 10.1109/ICIP.2016.7532812

DO - 10.1109/ICIP.2016.7532812

M3 - Conference Contribution (Conference Proceeding)

SN - 9781467399623

T3 - IEEE International Conference on Image Processing (ICIP)

SP - 2514

EP - 2518

BT - 2016 IEEE International Conference on Image Processing (ICIP 2016)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Hill PR, Kim JH, Basarab A, Kouamé D, Bull D , Achim AM. Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain. In 2016 IEEE International Conference on Image Processing (ICIP 2016). Institute of Electrical and Electronics Engineers (IEEE). 2017. p. 2514-2518. (IEEE International Conference on Image Processing (ICIP)). Epub 2016 Aug 19. doi: 10.1109/ICIP.2016.7532812

Compressive imaging using approximate message passing and a Cauchy prior in the wavelet domain

Abstract

Publication series

Access to Document

Handle.net

Fingerprint

Projects

Vision for the Future-Full

Cite this