Fast content-aware image resizing scheme in the compressed domain

Kang S. Choi, Sung-Jea Ko

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Since consumer devices have different resolution sizes of display panels, digital images are frequently required to be resized for each display adaptation. In this paper, we define DCT-based distortion measures to quantitatively evaluate both scaling distortion and shape distortion generated by downsizing. By utilizing the distortion measures, we propose a novel content-aware image retargeting algorithm. The proposed algorithm can not only satisfy demands of users without the loss of semantic information in images but also is computationally efficient since the digital images are typically stored in DCT-based compression format. Experimental results show that the proposed method can achieve higher subjective quality with significantly reduced computational loads as compared with existing methods.

Original languageEnglish
Pages (from-to)1514-1521
Number of pages8
JournalIEEE Transactions on Consumer Electronics
Volume55
Issue number3
DOIs
Publication statusPublished - 2009 Oct 29

Fingerprint

Display devices
Semantics

Keywords

  • Compressed domain processing
  • Content-aware image manipulation
  • DCT
  • Display devices
  • Image resizing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology

Cite this

Fast content-aware image resizing scheme in the compressed domain. / Choi, Kang S.; Ko, Sung-Jea.

In: IEEE Transactions on Consumer Electronics, Vol. 55, No. 3, 29.10.2009, p. 1514-1521.

Research output: Contribution to journalArticle

@article{a9c06efdc3214e6e85effc5a046b1f3b,
title = "Fast content-aware image resizing scheme in the compressed domain",
abstract = "Since consumer devices have different resolution sizes of display panels, digital images are frequently required to be resized for each display adaptation. In this paper, we define DCT-based distortion measures to quantitatively evaluate both scaling distortion and shape distortion generated by downsizing. By utilizing the distortion measures, we propose a novel content-aware image retargeting algorithm. The proposed algorithm can not only satisfy demands of users without the loss of semantic information in images but also is computationally efficient since the digital images are typically stored in DCT-based compression format. Experimental results show that the proposed method can achieve higher subjective quality with significantly reduced computational loads as compared with existing methods.",
keywords = "Compressed domain processing, Content-aware image manipulation, DCT, Display devices, Image resizing",
author = "Choi, {Kang S.} and Sung-Jea Ko",
year = "2009",
month = "10",
day = "29",
doi = "10.1109/TCE.2009.5278021",
language = "English",
volume = "55",
pages = "1514--1521",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Fast content-aware image resizing scheme in the compressed domain

AU - Choi, Kang S.

AU - Ko, Sung-Jea

PY - 2009/10/29

Y1 - 2009/10/29

N2 - Since consumer devices have different resolution sizes of display panels, digital images are frequently required to be resized for each display adaptation. In this paper, we define DCT-based distortion measures to quantitatively evaluate both scaling distortion and shape distortion generated by downsizing. By utilizing the distortion measures, we propose a novel content-aware image retargeting algorithm. The proposed algorithm can not only satisfy demands of users without the loss of semantic information in images but also is computationally efficient since the digital images are typically stored in DCT-based compression format. Experimental results show that the proposed method can achieve higher subjective quality with significantly reduced computational loads as compared with existing methods.

AB - Since consumer devices have different resolution sizes of display panels, digital images are frequently required to be resized for each display adaptation. In this paper, we define DCT-based distortion measures to quantitatively evaluate both scaling distortion and shape distortion generated by downsizing. By utilizing the distortion measures, we propose a novel content-aware image retargeting algorithm. The proposed algorithm can not only satisfy demands of users without the loss of semantic information in images but also is computationally efficient since the digital images are typically stored in DCT-based compression format. Experimental results show that the proposed method can achieve higher subjective quality with significantly reduced computational loads as compared with existing methods.

KW - Compressed domain processing

KW - Content-aware image manipulation

KW - DCT

KW - Display devices

KW - Image resizing

UR - http://www.scopus.com/inward/record.url?scp=70350284587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350284587&partnerID=8YFLogxK

U2 - 10.1109/TCE.2009.5278021

DO - 10.1109/TCE.2009.5278021

M3 - Article

AN - SCOPUS:70350284587

VL - 55

SP - 1514

EP - 1521

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 3

ER -