Image retargeting by texture-aware synthesis

Weiming Dong, Fuzhang Wu, Yan Kong, Xing Mei, Tong Yee Lee, Xiaopeng Zhang

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Real-world images usually contain vivid contents and rich textural details, which will complicate the manipulation on them. In this paper, we design a new framework based on exampled-based texture synthesis to enhance content-aware image retargeting. By detecting the textural regions in an image, the textural image content can be synthesized rather than simply distorted or cropped. This method enables the manipulation of textural & non-textural regions with different strategies since they have different natures. We propose to retarget the textural regions by example-based synthesis and non-textural regions by fast multi-operator. To achieve practical retargeting applications for general images, we develop an automatic and fast texture detection method that can detect multiple disjoint textural regions. We adjust the saliency of the image according to the features of the textural regions. To validate the proposed method, comparisons with state-of-the-art image retargeting techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method.

Original languageEnglish
Article number7117450
Pages (from-to)1088-1101
Number of pages14
JournalIEEE Transactions on Visualization and Computer Graphics
Volume22
Issue number2
DOIs
Publication statusPublished - 2016 Feb

Fingerprint

Textures

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Cite this

Dong, Weiming ; Wu, Fuzhang ; Kong, Yan ; Mei, Xing ; Lee, Tong Yee ; Zhang, Xiaopeng. / Image retargeting by texture-aware synthesis. In: IEEE Transactions on Visualization and Computer Graphics. 2016 ; Vol. 22, No. 2. pp. 1088-1101.
@article{12776f46aa48462cbbdbc8efc14e560b,
title = "Image retargeting by texture-aware synthesis",
abstract = "Real-world images usually contain vivid contents and rich textural details, which will complicate the manipulation on them. In this paper, we design a new framework based on exampled-based texture synthesis to enhance content-aware image retargeting. By detecting the textural regions in an image, the textural image content can be synthesized rather than simply distorted or cropped. This method enables the manipulation of textural & non-textural regions with different strategies since they have different natures. We propose to retarget the textural regions by example-based synthesis and non-textural regions by fast multi-operator. To achieve practical retargeting applications for general images, we develop an automatic and fast texture detection method that can detect multiple disjoint textural regions. We adjust the saliency of the image according to the features of the textural regions. To validate the proposed method, comparisons with state-of-the-art image retargeting techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method.",
author = "Weiming Dong and Fuzhang Wu and Yan Kong and Xing Mei and Lee, {Tong Yee} and Xiaopeng Zhang",
year = "2016",
month = "2",
doi = "10.1109/TVCG.2015.2440255",
language = "English",
volume = "22",
pages = "1088--1101",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "2",

}

Image retargeting by texture-aware synthesis. / Dong, Weiming; Wu, Fuzhang; Kong, Yan; Mei, Xing; Lee, Tong Yee; Zhang, Xiaopeng.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 22, No. 2, 7117450, 02.2016, p. 1088-1101.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Image retargeting by texture-aware synthesis

AU - Dong, Weiming

AU - Wu, Fuzhang

AU - Kong, Yan

AU - Mei, Xing

AU - Lee, Tong Yee

AU - Zhang, Xiaopeng

PY - 2016/2

Y1 - 2016/2

N2 - Real-world images usually contain vivid contents and rich textural details, which will complicate the manipulation on them. In this paper, we design a new framework based on exampled-based texture synthesis to enhance content-aware image retargeting. By detecting the textural regions in an image, the textural image content can be synthesized rather than simply distorted or cropped. This method enables the manipulation of textural & non-textural regions with different strategies since they have different natures. We propose to retarget the textural regions by example-based synthesis and non-textural regions by fast multi-operator. To achieve practical retargeting applications for general images, we develop an automatic and fast texture detection method that can detect multiple disjoint textural regions. We adjust the saliency of the image according to the features of the textural regions. To validate the proposed method, comparisons with state-of-the-art image retargeting techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method.

AB - Real-world images usually contain vivid contents and rich textural details, which will complicate the manipulation on them. In this paper, we design a new framework based on exampled-based texture synthesis to enhance content-aware image retargeting. By detecting the textural regions in an image, the textural image content can be synthesized rather than simply distorted or cropped. This method enables the manipulation of textural & non-textural regions with different strategies since they have different natures. We propose to retarget the textural regions by example-based synthesis and non-textural regions by fast multi-operator. To achieve practical retargeting applications for general images, we develop an automatic and fast texture detection method that can detect multiple disjoint textural regions. We adjust the saliency of the image according to the features of the textural regions. To validate the proposed method, comparisons with state-of-the-art image retargeting techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84978701741&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978701741&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2015.2440255

DO - 10.1109/TVCG.2015.2440255

M3 - Article

AN - SCOPUS:84978701741

VL - 22

SP - 1088

EP - 1101

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 2

M1 - 7117450

ER -