Learning flipping and rotation invariant sparsifying transforms

Bihan Wen, Saiprasad Ravishankar, Yoram Bresler

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

Abstract

Adaptive sparse representation has been heavily exploited in signal processing and computer vision. Recently, sparsifying transform learning received interest for its cheap computation and optimal updates in the alternating algorithms. In this work, we develop a methodology for learning a Flipping and Rotation Invariant Sparsifying Transform, dubbed FRIST, to better represent natural images that contain textures with various geometrical directions. The proposed alternating learning algorithm involves efficient optimal updates. We demonstrate empirical convergence behavior of the proposed learning algorithm. Preliminary experiments show the usefulness of FRIST for image sparse representation, segmentation, robust inpainting, and MRI reconstruction with promising performances.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
PublisherIEEE Computer Society
Pages3857-3861
Number of pages5
ISBN (Electronic)9781467399616
DOIs
StatePublished - Aug 3 2016
Event23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States
Duration: Sep 25 2016Sep 28 2016

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2016-August
ISSN (Print)1522-4880

Other

Other23rd IEEE International Conference on Image Processing, ICIP 2016
CountryUnited States
CityPhoenix
Period9/25/169/28/16

Fingerprint

Learning algorithms
Magnetic resonance imaging
Computer vision
Signal processing
Textures
Mathematical transformations
Experiments

Keywords

  • Clustering
  • Inpainting
  • Magnetic resonance imaging
  • Sparse representation
  • Sparsifying transform

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Wen, B., Ravishankar, S., & Bresler, Y. (2016). Learning flipping and rotation invariant sparsifying transforms. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings (pp. 3857-3861). [7533082] (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August). IEEE Computer Society. https://doi.org/10.1109/ICIP.2016.7533082

Learning flipping and rotation invariant sparsifying transforms. / Wen, Bihan; Ravishankar, Saiprasad; Bresler, Yoram.

2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. IEEE Computer Society, 2016. p. 3857-3861 7533082 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2016-August).

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

Wen, B, Ravishankar, S & Bresler, Y 2016, Learning flipping and rotation invariant sparsifying transforms. in 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings., 7533082, Proceedings - International Conference on Image Processing, ICIP, vol. 2016-August, IEEE Computer Society, pp. 3857-3861, 23rd IEEE International Conference on Image Processing, ICIP 2016, Phoenix, United States, 9/25/16. https://doi.org/10.1109/ICIP.2016.7533082
Wen B, Ravishankar S, Bresler Y. Learning flipping and rotation invariant sparsifying transforms. In 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. IEEE Computer Society. 2016. p. 3857-3861. 7533082. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2016.7533082
Wen, Bihan ; Ravishankar, Saiprasad ; Bresler, Yoram. / Learning flipping and rotation invariant sparsifying transforms. 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings. IEEE Computer Society, 2016. pp. 3857-3861 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{c8423bc644d84ae8bd954e1f4e3376b1,
title = "Learning flipping and rotation invariant sparsifying transforms",
abstract = "Adaptive sparse representation has been heavily exploited in signal processing and computer vision. Recently, sparsifying transform learning received interest for its cheap computation and optimal updates in the alternating algorithms. In this work, we develop a methodology for learning a Flipping and Rotation Invariant Sparsifying Transform, dubbed FRIST, to better represent natural images that contain textures with various geometrical directions. The proposed alternating learning algorithm involves efficient optimal updates. We demonstrate empirical convergence behavior of the proposed learning algorithm. Preliminary experiments show the usefulness of FRIST for image sparse representation, segmentation, robust inpainting, and MRI reconstruction with promising performances.",
keywords = "Clustering, Inpainting, Magnetic resonance imaging, Sparse representation, Sparsifying transform",
author = "Bihan Wen and Saiprasad Ravishankar and Yoram Bresler",
year = "2016",
month = "8",
day = "3",
doi = "10.1109/ICIP.2016.7533082",
language = "English (US)",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "3857--3861",
booktitle = "2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings",

}

TY - GEN

T1 - Learning flipping and rotation invariant sparsifying transforms

AU - Wen, Bihan

AU - Ravishankar, Saiprasad

AU - Bresler, Yoram

PY - 2016/8/3

Y1 - 2016/8/3

N2 - Adaptive sparse representation has been heavily exploited in signal processing and computer vision. Recently, sparsifying transform learning received interest for its cheap computation and optimal updates in the alternating algorithms. In this work, we develop a methodology for learning a Flipping and Rotation Invariant Sparsifying Transform, dubbed FRIST, to better represent natural images that contain textures with various geometrical directions. The proposed alternating learning algorithm involves efficient optimal updates. We demonstrate empirical convergence behavior of the proposed learning algorithm. Preliminary experiments show the usefulness of FRIST for image sparse representation, segmentation, robust inpainting, and MRI reconstruction with promising performances.

AB - Adaptive sparse representation has been heavily exploited in signal processing and computer vision. Recently, sparsifying transform learning received interest for its cheap computation and optimal updates in the alternating algorithms. In this work, we develop a methodology for learning a Flipping and Rotation Invariant Sparsifying Transform, dubbed FRIST, to better represent natural images that contain textures with various geometrical directions. The proposed alternating learning algorithm involves efficient optimal updates. We demonstrate empirical convergence behavior of the proposed learning algorithm. Preliminary experiments show the usefulness of FRIST for image sparse representation, segmentation, robust inpainting, and MRI reconstruction with promising performances.

KW - Clustering

KW - Inpainting

KW - Magnetic resonance imaging

KW - Sparse representation

KW - Sparsifying transform

UR - http://www.scopus.com/inward/record.url?scp=85006788279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006788279&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2016.7533082

DO - 10.1109/ICIP.2016.7533082

M3 - Conference contribution

AN - SCOPUS:85006788279

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 3857

EP - 3861

BT - 2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings

PB - IEEE Computer Society

ER -