Learning flipping and rotation invariant sparsifying transforms

Bihan Wen; Saiprasad Ravishankar; Yoram Bresler

doi:10.1109/ICIP.2016.7533082

Learning flipping and rotation invariant sparsifying transforms

Bihan Wen, Saiprasad Ravishankar, Yoram Bresler

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English (US)
Title of host publication	2016 IEEE International Conference on Image Processing, ICIP 2016 - Proceedings
Publisher	IEEE Computer Society
Pages	3857-3861
Number of pages	5
ISBN (Electronic)	9781467399616
DOIs	https://doi.org/10.1109/ICIP.2016.7533082
State	Published - Aug 3 2016
Event	23rd IEEE International Conference on Image Processing, ICIP 2016 - Phoenix, United States Duration: Sep 25 2016 → Sep 28 2016

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2016-August
ISSN (Print)	1522-4880

Other

Other	23rd IEEE International Conference on Image Processing, ICIP 2016
Country	United States
City	Phoenix
Period	9/25/16 → 9/28/16

Keywords

Clustering
Inpainting
Magnetic resonance imaging
Sparse representation
Sparsifying transform

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP.2016.7533082

Fingerprint Dive into the research topics of 'Learning flipping and rotation invariant sparsifying transforms'. Together they form a unique fingerprint.

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 proceeding › Conference 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

@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",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; 23rd IEEE International Conference on Image Processing, ICIP 2016 ; Conference date: 25-09-2016 Through 28-09-2016",

year = "2016",

month = aug,

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

T2 - 23rd IEEE International Conference on Image Processing, ICIP 2016

Y2 - 25 September 2016 through 28 September 2016

ER -