Patch-based image warping for content-aware retargeting

Shih Syun Lin, I. Cheng Yeh, Chao Hung Lin, Tong Yee Lee

Research output: Contribution to journalArticle

65 Citations (Scopus)

Abstract

Image retargeting is the process of adapting images to fit displays with various aspect ratios and sizes. Most studies on image retargeting focus on shape preservation, but they do not fully consider the preservation of structure lines, which are sensitive to human visual system. In this paper, a patch-based retargeting scheme with an extended significance measurement is introduced to preserve shapes of both visually salient objects and structure lines while minimizing visual distortions. In the proposed scheme, a similarity transformation constraint is used to force visually salient content to undergo as-rigid-as-possible deformation, while an optimization process is performed to smoothly propagate distortions. These processes enable our approach to yield pleasing content-aware warping and retargeting. Experimental results and a user study show that our results are better than those generated by state-of-the-art approaches.

Original languageEnglish
Article number6357312
Pages (from-to)359-368
Number of pages10
JournalIEEE Transactions on Multimedia
Volume15
Issue number2
DOIs
Publication statusPublished - 2013 Jan 28

Fingerprint

Aspect ratio
Display devices

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Media Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

@article{196cf0a65fa04662ad14d5b1cedb94d1,
title = "Patch-based image warping for content-aware retargeting",
abstract = "Image retargeting is the process of adapting images to fit displays with various aspect ratios and sizes. Most studies on image retargeting focus on shape preservation, but they do not fully consider the preservation of structure lines, which are sensitive to human visual system. In this paper, a patch-based retargeting scheme with an extended significance measurement is introduced to preserve shapes of both visually salient objects and structure lines while minimizing visual distortions. In the proposed scheme, a similarity transformation constraint is used to force visually salient content to undergo as-rigid-as-possible deformation, while an optimization process is performed to smoothly propagate distortions. These processes enable our approach to yield pleasing content-aware warping and retargeting. Experimental results and a user study show that our results are better than those generated by state-of-the-art approaches.",
author = "Lin, {Shih Syun} and Yeh, {I. Cheng} and Lin, {Chao Hung} and Lee, {Tong Yee}",
year = "2013",
month = "1",
day = "28",
doi = "10.1109/TMM.2012.2228475",
language = "English",
volume = "15",
pages = "359--368",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Patch-based image warping for content-aware retargeting. / Lin, Shih Syun; Yeh, I. Cheng; Lin, Chao Hung; Lee, Tong Yee.

In: IEEE Transactions on Multimedia, Vol. 15, No. 2, 6357312, 28.01.2013, p. 359-368.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Patch-based image warping for content-aware retargeting

AU - Lin, Shih Syun

AU - Yeh, I. Cheng

AU - Lin, Chao Hung

AU - Lee, Tong Yee

PY - 2013/1/28

Y1 - 2013/1/28

N2 - Image retargeting is the process of adapting images to fit displays with various aspect ratios and sizes. Most studies on image retargeting focus on shape preservation, but they do not fully consider the preservation of structure lines, which are sensitive to human visual system. In this paper, a patch-based retargeting scheme with an extended significance measurement is introduced to preserve shapes of both visually salient objects and structure lines while minimizing visual distortions. In the proposed scheme, a similarity transformation constraint is used to force visually salient content to undergo as-rigid-as-possible deformation, while an optimization process is performed to smoothly propagate distortions. These processes enable our approach to yield pleasing content-aware warping and retargeting. Experimental results and a user study show that our results are better than those generated by state-of-the-art approaches.

AB - Image retargeting is the process of adapting images to fit displays with various aspect ratios and sizes. Most studies on image retargeting focus on shape preservation, but they do not fully consider the preservation of structure lines, which are sensitive to human visual system. In this paper, a patch-based retargeting scheme with an extended significance measurement is introduced to preserve shapes of both visually salient objects and structure lines while minimizing visual distortions. In the proposed scheme, a similarity transformation constraint is used to force visually salient content to undergo as-rigid-as-possible deformation, while an optimization process is performed to smoothly propagate distortions. These processes enable our approach to yield pleasing content-aware warping and retargeting. Experimental results and a user study show that our results are better than those generated by state-of-the-art approaches.

UR - http://www.scopus.com/inward/record.url?scp=84872709880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872709880&partnerID=8YFLogxK

U2 - 10.1109/TMM.2012.2228475

DO - 10.1109/TMM.2012.2228475

M3 - Article

AN - SCOPUS:84872709880

VL - 15

SP - 359

EP - 368

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

IS - 2

M1 - 6357312

ER -