Boosted dictionaries for image restoration based on sparse representations

Karthikeyan Natesan Ramamurthy, Jayaraman J. Thiagarajan, Andreas Spanias, Prasanna Sattigeri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Sparse representations using learned dictionaries have been successful in several image processing applications. However, using a single dictionary model in inverse problems may lead to instability in estimation. In this paper, we propose to perform image restoration using an ensemble of weak dictionaries that incorporate prior knowledge about the form of linear corruption. The dictionary learned in each round of the training procedure is optimized for the training examples having high reconstruction error in the previous round. The weak dictionaries are either obtained using a weighted K-Means or an example-selection approach. The final restored data is computed as a convex combination of data restored in individual rounds. Results with compressed recovery of standard images show that the proposed dictionaries result in a better performance compared to using a single dictionary obtained with a traditional alternating minimization approach.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages1583-1587
Number of pages5
DOIs
StatePublished - Oct 18 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: May 26 2013May 31 2013

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CountryCanada
CityVancouver, BC
Period5/26/135/31/13

Fingerprint

Glossaries
Image reconstruction
Inverse problems
Image processing
Recovery

Keywords

  • Boosting
  • Dictionary learning
  • Image restoration
  • Sparse representations

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Natesan Ramamurthy, K., Thiagarajan, J. J., Spanias, A., & Sattigeri, P. (2013). Boosted dictionaries for image restoration based on sparse representations. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 1583-1587). [6637918] https://doi.org/10.1109/ICASSP.2013.6637918

Boosted dictionaries for image restoration based on sparse representations. / Natesan Ramamurthy, Karthikeyan; Thiagarajan, Jayaraman J.; Spanias, Andreas; Sattigeri, Prasanna.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 1583-1587 6637918.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Natesan Ramamurthy, K, Thiagarajan, JJ, Spanias, A & Sattigeri, P 2013, Boosted dictionaries for image restoration based on sparse representations. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6637918, pp. 1583-1587, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, 5/26/13. https://doi.org/10.1109/ICASSP.2013.6637918
Natesan Ramamurthy K, Thiagarajan JJ, Spanias A, Sattigeri P. Boosted dictionaries for image restoration based on sparse representations. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 1583-1587. 6637918 https://doi.org/10.1109/ICASSP.2013.6637918
Natesan Ramamurthy, Karthikeyan ; Thiagarajan, Jayaraman J. ; Spanias, Andreas ; Sattigeri, Prasanna. / Boosted dictionaries for image restoration based on sparse representations. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. pp. 1583-1587
@inproceedings{f53958ad1e6343928a144c64814e6ea4,
title = "Boosted dictionaries for image restoration based on sparse representations",
abstract = "Sparse representations using learned dictionaries have been successful in several image processing applications. However, using a single dictionary model in inverse problems may lead to instability in estimation. In this paper, we propose to perform image restoration using an ensemble of weak dictionaries that incorporate prior knowledge about the form of linear corruption. The dictionary learned in each round of the training procedure is optimized for the training examples having high reconstruction error in the previous round. The weak dictionaries are either obtained using a weighted K-Means or an example-selection approach. The final restored data is computed as a convex combination of data restored in individual rounds. Results with compressed recovery of standard images show that the proposed dictionaries result in a better performance compared to using a single dictionary obtained with a traditional alternating minimization approach.",
keywords = "Boosting, Dictionary learning, Image restoration, Sparse representations",
author = "{Natesan Ramamurthy}, Karthikeyan and Thiagarajan, {Jayaraman J.} and Andreas Spanias and Prasanna Sattigeri",
year = "2013",
month = "10",
day = "18",
doi = "10.1109/ICASSP.2013.6637918",
language = "English (US)",
isbn = "9781479903566",
pages = "1583--1587",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Boosted dictionaries for image restoration based on sparse representations

AU - Natesan Ramamurthy, Karthikeyan

AU - Thiagarajan, Jayaraman J.

AU - Spanias, Andreas

AU - Sattigeri, Prasanna

PY - 2013/10/18

Y1 - 2013/10/18

N2 - Sparse representations using learned dictionaries have been successful in several image processing applications. However, using a single dictionary model in inverse problems may lead to instability in estimation. In this paper, we propose to perform image restoration using an ensemble of weak dictionaries that incorporate prior knowledge about the form of linear corruption. The dictionary learned in each round of the training procedure is optimized for the training examples having high reconstruction error in the previous round. The weak dictionaries are either obtained using a weighted K-Means or an example-selection approach. The final restored data is computed as a convex combination of data restored in individual rounds. Results with compressed recovery of standard images show that the proposed dictionaries result in a better performance compared to using a single dictionary obtained with a traditional alternating minimization approach.

AB - Sparse representations using learned dictionaries have been successful in several image processing applications. However, using a single dictionary model in inverse problems may lead to instability in estimation. In this paper, we propose to perform image restoration using an ensemble of weak dictionaries that incorporate prior knowledge about the form of linear corruption. The dictionary learned in each round of the training procedure is optimized for the training examples having high reconstruction error in the previous round. The weak dictionaries are either obtained using a weighted K-Means or an example-selection approach. The final restored data is computed as a convex combination of data restored in individual rounds. Results with compressed recovery of standard images show that the proposed dictionaries result in a better performance compared to using a single dictionary obtained with a traditional alternating minimization approach.

KW - Boosting

KW - Dictionary learning

KW - Image restoration

KW - Sparse representations

UR - http://www.scopus.com/inward/record.url?scp=84890500577&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890500577&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2013.6637918

DO - 10.1109/ICASSP.2013.6637918

M3 - Conference contribution

AN - SCOPUS:84890500577

SN - 9781479903566

SP - 1583

EP - 1587

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -