LRTV: MR Image Super-Resolution with Low-Rank and Total Variation Regularizations

Feng Shi, Jian Cheng, Li Wang, Pew Thian Yap, Dinggang Shen

Research output: Contribution to journalArticle

67 Citations (Scopus)

Abstract

Image super-resolution (SR) aims to recover high-resolution images from their low-resolution counterparts for improving image analysis and visualization. Interpolation methods, widely used for this purpose, often result in images with blurred edges and blocking effects. More advanced methods such as total variation (TV) retain edge sharpness during image recovery. However, these methods only utilize information from local neighborhoods, neglecting useful information from remote voxels. In this paper, we propose a novel image SR method that integrates both local and global information for effective image recovery. This is achieved by, in addition to TV, low-rank regularization that enables utilization of information throughout the image. The optimization problem can be solved effectively via alternating direction method of multipliers (ADMM). Experiments on MR images of both adult and pediatric subjects demonstrate that the proposed method enhances the details in the recovered high-resolution images, and outperforms methods such as the nearest-neighbor interpolation, cubic interpolation, iterative back projection (IBP), non-local means (NLM), and TV-based up-sampling.

Original languageEnglish
Article number7113897
Pages (from-to)2459-2466
Number of pages8
JournalIEEE Transactions on Medical Imaging
Volume34
Issue number12
DOIs
Publication statusPublished - 2015 Dec 1

Fingerprint

Interpolation
Optical resolving power
Image resolution
Recovery
Pediatrics
Image analysis
Visualization
Sampling
Experiments

Keywords

  • Image enhancement
  • image sampling
  • matrix completion
  • sparse learning
  • spatial resolution

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software

Cite this

LRTV : MR Image Super-Resolution with Low-Rank and Total Variation Regularizations. / Shi, Feng; Cheng, Jian; Wang, Li; Yap, Pew Thian; Shen, Dinggang.

In: IEEE Transactions on Medical Imaging, Vol. 34, No. 12, 7113897, 01.12.2015, p. 2459-2466.

Research output: Contribution to journalArticle

Shi, Feng ; Cheng, Jian ; Wang, Li ; Yap, Pew Thian ; Shen, Dinggang. / LRTV : MR Image Super-Resolution with Low-Rank and Total Variation Regularizations. In: IEEE Transactions on Medical Imaging. 2015 ; Vol. 34, No. 12. pp. 2459-2466.
@article{23d40379a38b455aa70cdccbe2f51fd9,
title = "LRTV: MR Image Super-Resolution with Low-Rank and Total Variation Regularizations",
abstract = "Image super-resolution (SR) aims to recover high-resolution images from their low-resolution counterparts for improving image analysis and visualization. Interpolation methods, widely used for this purpose, often result in images with blurred edges and blocking effects. More advanced methods such as total variation (TV) retain edge sharpness during image recovery. However, these methods only utilize information from local neighborhoods, neglecting useful information from remote voxels. In this paper, we propose a novel image SR method that integrates both local and global information for effective image recovery. This is achieved by, in addition to TV, low-rank regularization that enables utilization of information throughout the image. The optimization problem can be solved effectively via alternating direction method of multipliers (ADMM). Experiments on MR images of both adult and pediatric subjects demonstrate that the proposed method enhances the details in the recovered high-resolution images, and outperforms methods such as the nearest-neighbor interpolation, cubic interpolation, iterative back projection (IBP), non-local means (NLM), and TV-based up-sampling.",
keywords = "Image enhancement, image sampling, matrix completion, sparse learning, spatial resolution",
author = "Feng Shi and Jian Cheng and Li Wang and Yap, {Pew Thian} and Dinggang Shen",
year = "2015",
month = "12",
day = "1",
doi = "10.1109/TMI.2015.2437894",
language = "English",
volume = "34",
pages = "2459--2466",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

TY - JOUR

T1 - LRTV

T2 - MR Image Super-Resolution with Low-Rank and Total Variation Regularizations

AU - Shi, Feng

AU - Cheng, Jian

AU - Wang, Li

AU - Yap, Pew Thian

AU - Shen, Dinggang

PY - 2015/12/1

Y1 - 2015/12/1

N2 - Image super-resolution (SR) aims to recover high-resolution images from their low-resolution counterparts for improving image analysis and visualization. Interpolation methods, widely used for this purpose, often result in images with blurred edges and blocking effects. More advanced methods such as total variation (TV) retain edge sharpness during image recovery. However, these methods only utilize information from local neighborhoods, neglecting useful information from remote voxels. In this paper, we propose a novel image SR method that integrates both local and global information for effective image recovery. This is achieved by, in addition to TV, low-rank regularization that enables utilization of information throughout the image. The optimization problem can be solved effectively via alternating direction method of multipliers (ADMM). Experiments on MR images of both adult and pediatric subjects demonstrate that the proposed method enhances the details in the recovered high-resolution images, and outperforms methods such as the nearest-neighbor interpolation, cubic interpolation, iterative back projection (IBP), non-local means (NLM), and TV-based up-sampling.

AB - Image super-resolution (SR) aims to recover high-resolution images from their low-resolution counterparts for improving image analysis and visualization. Interpolation methods, widely used for this purpose, often result in images with blurred edges and blocking effects. More advanced methods such as total variation (TV) retain edge sharpness during image recovery. However, these methods only utilize information from local neighborhoods, neglecting useful information from remote voxels. In this paper, we propose a novel image SR method that integrates both local and global information for effective image recovery. This is achieved by, in addition to TV, low-rank regularization that enables utilization of information throughout the image. The optimization problem can be solved effectively via alternating direction method of multipliers (ADMM). Experiments on MR images of both adult and pediatric subjects demonstrate that the proposed method enhances the details in the recovered high-resolution images, and outperforms methods such as the nearest-neighbor interpolation, cubic interpolation, iterative back projection (IBP), non-local means (NLM), and TV-based up-sampling.

KW - Image enhancement

KW - image sampling

KW - matrix completion

KW - sparse learning

KW - spatial resolution

UR - http://www.scopus.com/inward/record.url?scp=84960119344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960119344&partnerID=8YFLogxK

U2 - 10.1109/TMI.2015.2437894

DO - 10.1109/TMI.2015.2437894

M3 - Article

C2 - 26641727

AN - SCOPUS:84960119344

VL - 34

SP - 2459

EP - 2466

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 12

M1 - 7113897

ER -