Pixel recovery VIA ℓ 1 minimization in the wavelet domain

Ivan W. Selesnick; Richard Van Slyke; Onur G. Guleryuz

doi:10.1109/ICIP.2004.1421429

Pixel recovery VIA ℓ ₁ minimization in the wavelet domain

Ivan W. Selesnick, Richard Van Slyke, Onur G. Guleryuz

Electrical and Computer Engineering

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

Abstract

This paper uses probability models on expansive wavelet transform coefficients with interpolation constraints to estimate missing blocks in images. We use simple probability models on wavelet coefficients to formulate the estimation process as a linear programming problem and solve it to recover the missing pixels. Our formulation is general and can be augmented with more sophisticated probability models to obtain even better estimates on a variety of image regions. The presented approach has many parallels to recently introduced dictionary based signal representations with which it shares certain optimality properties. We provide simulation examples over edge regions using both critically-sampled and expansive (over-complete) wavelet transforms.

Original language	English (US)
Title of host publication	2004 International Conference on Image Processing, ICIP 2004
Pages	1819-1822
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2004.1421429
State	Published - 2004
Event	2004 International Conference on Image Processing, ICIP 2004 - , Singapore Duration: Oct 18 2004 → Oct 21 2004

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	3
ISSN (Print)	1522-4880

Other

Other	2004 International Conference on Image Processing, ICIP 2004
Country/Territory	Singapore
Period	10/18/04 → 10/21/04

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/ICIP.2004.1421429

Cite this

Selesnick, IW, Van Slyke, R & Guleryuz, OG 2004, Pixel recovery VIA ℓ ₁ minimization in the wavelet domain. in 2004 International Conference on Image Processing, ICIP 2004. Proceedings - International Conference on Image Processing, ICIP, vol. 3, pp. 1819-1822, 2004 International Conference on Image Processing, ICIP 2004, Singapore, 10/18/04. https://doi.org/10.1109/ICIP.2004.1421429

@inproceedings{e1eb012579ed464683a14ffc7f0f61d9,

title = "Pixel recovery VIA ℓ 1 minimization in the wavelet domain",

abstract = "This paper uses probability models on expansive wavelet transform coefficients with interpolation constraints to estimate missing blocks in images. We use simple probability models on wavelet coefficients to formulate the estimation process as a linear programming problem and solve it to recover the missing pixels. Our formulation is general and can be augmented with more sophisticated probability models to obtain even better estimates on a variety of image regions. The presented approach has many parallels to recently introduced dictionary based signal representations with which it shares certain optimality properties. We provide simulation examples over edge regions using both critically-sampled and expansive (over-complete) wavelet transforms.",

author = "Selesnick, {Ivan W.} and {Van Slyke}, Richard and Guleryuz, {Onur G.}",

year = "2004",

doi = "10.1109/ICIP.2004.1421429",

language = "English (US)",

isbn = "0780385543",

series = "Proceedings - International Conference on Image Processing, ICIP",

pages = "1819--1822",

booktitle = "2004 International Conference on Image Processing, ICIP 2004",

note = "2004 International Conference on Image Processing, ICIP 2004 ; Conference date: 18-10-2004 Through 21-10-2004",

}

TY - GEN

T1 - Pixel recovery VIA ℓ 1 minimization in the wavelet domain

AU - Selesnick, Ivan W.

AU - Van Slyke, Richard

AU - Guleryuz, Onur G.

PY - 2004

Y1 - 2004

N2 - This paper uses probability models on expansive wavelet transform coefficients with interpolation constraints to estimate missing blocks in images. We use simple probability models on wavelet coefficients to formulate the estimation process as a linear programming problem and solve it to recover the missing pixels. Our formulation is general and can be augmented with more sophisticated probability models to obtain even better estimates on a variety of image regions. The presented approach has many parallels to recently introduced dictionary based signal representations with which it shares certain optimality properties. We provide simulation examples over edge regions using both critically-sampled and expansive (over-complete) wavelet transforms.

AB - This paper uses probability models on expansive wavelet transform coefficients with interpolation constraints to estimate missing blocks in images. We use simple probability models on wavelet coefficients to formulate the estimation process as a linear programming problem and solve it to recover the missing pixels. Our formulation is general and can be augmented with more sophisticated probability models to obtain even better estimates on a variety of image regions. The presented approach has many parallels to recently introduced dictionary based signal representations with which it shares certain optimality properties. We provide simulation examples over edge regions using both critically-sampled and expansive (over-complete) wavelet transforms.

UR - http://www.scopus.com/inward/record.url?scp=20444461170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20444461170&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2004.1421429

DO - 10.1109/ICIP.2004.1421429

M3 - Conference contribution

AN - SCOPUS:20444461170

SN - 0780385543

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1819

EP - 1822

BT - 2004 International Conference on Image Processing, ICIP 2004

T2 - 2004 International Conference on Image Processing, ICIP 2004

Y2 - 18 October 2004 through 21 October 2004

ER -