Unsupervised restoration of subsampled images constructed from geometric and binomial data

Yoann Altmann; Stephen McLaughlin; Miles J. Padgett

doi:10.1109/CAMSAP.2017.8313187

Unsupervised restoration of subsampled images constructed from geometric and binomial data

Yoann Altmann, Stephen McLaughlin, Miles J. Padgett

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

77 Downloads (Pure)

Abstract

In this paper, we investigate a new imaging denoising algorithm for single-photon applications where the classical Poisson noise assumption does not hold. Precisely, we consider two different acquisition scenarios where the unknown intensity profile is to be recovered from subsampled measurements following binomial or geometric distributions, whose parameters are nonlinearly related to the intensities of interest. Adopting a Bayesian approach, a flexible prior model is assigned to the unknown intensity field and an adaptive Markov chain Monte Carlo methods is used to perform Bayesian inference. In particular, it allows us to automatically adjust the amount of regularisation required for satisfactory image inpainting/restoration. The performance of the proposed model/method is assessed quantitatively through a series of experiments conducted with controlled data and the results obtained are very promising for future analysis of multidimensional single-photon images.

Original language	English
Title of host publication	2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)
Publisher	IEEE
Pages	1-5
Number of pages	5
ISBN (Electronic)	9781538612514
ISBN (Print)	9781538612521
DOIs	https://doi.org/10.1109/CAMSAP.2017.8313187
Publication status	Published - 12 Mar 2018
Event	7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing 2017 - Curacao, Curaçao Duration: 10 Dec 2017 → 13 Dec 2017 http://www.cs.huji.ac.il/conferences/CAMSAP17/

Conference

Conference	7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing 2017
Abbreviated title	CAMSAP 2017
Country/Territory	Curaçao
City	Curacao
Period	10/12/17 → 13/12/17
Internet address	http://www.cs.huji.ac.il/conferences/CAMSAP17/

Keywords

single-photon counting
Image processing
Bayesian inference

Access to Document

10.1109/CAMSAP.2017.8313187

Download pdf
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 791 KBLicence: All Rights Reserved

Cite this

@inproceedings{4439393907ea4130a299131f86bbd8e2,

title = "Unsupervised restoration of subsampled images constructed from geometric and binomial data",

abstract = "In this paper, we investigate a new imaging denoising algorithm for single-photon applications where the classical Poisson noise assumption does not hold. Precisely, we consider two different acquisition scenarios where the unknown intensity profile is to be recovered from subsampled measurements following binomial or geometric distributions, whose parameters are nonlinearly related to the intensities of interest. Adopting a Bayesian approach, a flexible prior model is assigned to the unknown intensity field and an adaptive Markov chain Monte Carlo methods is used to perform Bayesian inference. In particular, it allows us to automatically adjust the amount of regularisation required for satisfactory image inpainting/restoration. The performance of the proposed model/method is assessed quantitatively through a series of experiments conducted with controlled data and the results obtained are very promising for future analysis of multidimensional single-photon images.",

keywords = "single-photon counting, Image processing, Bayesian inference",

author = "Yoann Altmann and Stephen McLaughlin and Padgett, {Miles J.}",

year = "2018",

month = mar,

day = "12",

doi = "10.1109/CAMSAP.2017.8313187",

language = "English",

isbn = "9781538612521",

pages = "1--5",

booktitle = "2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)",

publisher = "IEEE",

address = "United States",

note = "7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing 2017, CAMSAP 2017 ; Conference date: 10-12-2017 Through 13-12-2017",

url = "http://www.cs.huji.ac.il/conferences/CAMSAP17/",

}

Altmann, Y , McLaughlin, S & Padgett, MJ 2018, Unsupervised restoration of subsampled images constructed from geometric and binomial data. in 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP). IEEE, pp. 1-5, 7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing 2017, Curacao, Curaçao, 10/12/17. https://doi.org/10.1109/CAMSAP.2017.8313187

TY - GEN

T1 - Unsupervised restoration of subsampled images constructed from geometric and binomial data

AU - Altmann, Yoann

AU - McLaughlin, Stephen

AU - Padgett, Miles J.

PY - 2018/3/12

Y1 - 2018/3/12

N2 - In this paper, we investigate a new imaging denoising algorithm for single-photon applications where the classical Poisson noise assumption does not hold. Precisely, we consider two different acquisition scenarios where the unknown intensity profile is to be recovered from subsampled measurements following binomial or geometric distributions, whose parameters are nonlinearly related to the intensities of interest. Adopting a Bayesian approach, a flexible prior model is assigned to the unknown intensity field and an adaptive Markov chain Monte Carlo methods is used to perform Bayesian inference. In particular, it allows us to automatically adjust the amount of regularisation required for satisfactory image inpainting/restoration. The performance of the proposed model/method is assessed quantitatively through a series of experiments conducted with controlled data and the results obtained are very promising for future analysis of multidimensional single-photon images.

AB - In this paper, we investigate a new imaging denoising algorithm for single-photon applications where the classical Poisson noise assumption does not hold. Precisely, we consider two different acquisition scenarios where the unknown intensity profile is to be recovered from subsampled measurements following binomial or geometric distributions, whose parameters are nonlinearly related to the intensities of interest. Adopting a Bayesian approach, a flexible prior model is assigned to the unknown intensity field and an adaptive Markov chain Monte Carlo methods is used to perform Bayesian inference. In particular, it allows us to automatically adjust the amount of regularisation required for satisfactory image inpainting/restoration. The performance of the proposed model/method is assessed quantitatively through a series of experiments conducted with controlled data and the results obtained are very promising for future analysis of multidimensional single-photon images.

KW - single-photon counting

KW - Image processing

KW - Bayesian inference

UR - http://www.scopus.com/inward/record.url?scp=85050734368&partnerID=8YFLogxK

U2 - 10.1109/CAMSAP.2017.8313187

DO - 10.1109/CAMSAP.2017.8313187

M3 - Conference contribution

SN - 9781538612521

SP - 1

EP - 5

BT - 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)

PB - IEEE

T2 - 7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing 2017

Y2 - 10 December 2017 through 13 December 2017

ER -

Unsupervised restoration of subsampled images constructed from geometric and binomial data

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this