Adaptive image and video retargeting technique based on fourier analysis

Jun Seong Kim, Jin Hwan Kim, Chang-Su Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

64 Citations (Scopus)

Abstract

An adaptive image and video retargeting algorithm based on Fourier analysis is proposed in this work. We first divide an input image into several strips using the gradient information so that each strip consists of textures of similar complexities. Then, we scale each strip adaptively according to its importance measure. More specifically, the distortions, generated by the scaling procedure, are formulated in the frequency domain using the Fourier transform. Then, the objective is to determine the sizes of scaled strips to minimize the sum of distortions, subject to the constraint that the sum of their sizes should equal the size of the target output image. We solve this constrained optimization problem using the Lagrangian multiplier technique. Moreover, we extend the approach to the retargeting of video sequences. Simulation results demonstrate that the proposed algorithm provides reliable retargeting performance efficiently.

Original languageEnglish
Title of host publication2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
Pages1730-1737
Number of pages8
DOIs
Publication statusPublished - 2009 Nov 27
Event2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 - Miami, FL, United States
Duration: 2009 Jun 202009 Jun 25

Other

Other2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
CountryUnited States
CityMiami, FL
Period09/6/2009/6/25

Fingerprint

Fourier analysis
Constrained optimization
Fourier transforms
Textures

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Biomedical Engineering

Cite this

Kim, J. S., Kim, J. H., & Kim, C-S. (2009). Adaptive image and video retargeting technique based on fourier analysis. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009 (pp. 1730-1737). [5206666] https://doi.org/10.1109/CVPRW.2009.5206666

Adaptive image and video retargeting technique based on fourier analysis. / Kim, Jun Seong; Kim, Jin Hwan; Kim, Chang-Su.

2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. 2009. p. 1730-1737 5206666.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, JS, Kim, JH & Kim, C-S 2009, Adaptive image and video retargeting technique based on fourier analysis. in 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009., 5206666, pp. 1730-1737, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009, Miami, FL, United States, 09/6/20. https://doi.org/10.1109/CVPRW.2009.5206666
Kim JS, Kim JH, Kim C-S. Adaptive image and video retargeting technique based on fourier analysis. In 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. 2009. p. 1730-1737. 5206666 https://doi.org/10.1109/CVPRW.2009.5206666
Kim, Jun Seong ; Kim, Jin Hwan ; Kim, Chang-Su. / Adaptive image and video retargeting technique based on fourier analysis. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009. 2009. pp. 1730-1737
@inproceedings{3c69fccf97d04809a823aa2b29f1a0e8,
title = "Adaptive image and video retargeting technique based on fourier analysis",
abstract = "An adaptive image and video retargeting algorithm based on Fourier analysis is proposed in this work. We first divide an input image into several strips using the gradient information so that each strip consists of textures of similar complexities. Then, we scale each strip adaptively according to its importance measure. More specifically, the distortions, generated by the scaling procedure, are formulated in the frequency domain using the Fourier transform. Then, the objective is to determine the sizes of scaled strips to minimize the sum of distortions, subject to the constraint that the sum of their sizes should equal the size of the target output image. We solve this constrained optimization problem using the Lagrangian multiplier technique. Moreover, we extend the approach to the retargeting of video sequences. Simulation results demonstrate that the proposed algorithm provides reliable retargeting performance efficiently.",
author = "Kim, {Jun Seong} and Kim, {Jin Hwan} and Chang-Su Kim",
year = "2009",
month = "11",
day = "27",
doi = "10.1109/CVPRW.2009.5206666",
language = "English",
isbn = "9781424439935",
pages = "1730--1737",
booktitle = "2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009",

}

TY - GEN

T1 - Adaptive image and video retargeting technique based on fourier analysis

AU - Kim, Jun Seong

AU - Kim, Jin Hwan

AU - Kim, Chang-Su

PY - 2009/11/27

Y1 - 2009/11/27

N2 - An adaptive image and video retargeting algorithm based on Fourier analysis is proposed in this work. We first divide an input image into several strips using the gradient information so that each strip consists of textures of similar complexities. Then, we scale each strip adaptively according to its importance measure. More specifically, the distortions, generated by the scaling procedure, are formulated in the frequency domain using the Fourier transform. Then, the objective is to determine the sizes of scaled strips to minimize the sum of distortions, subject to the constraint that the sum of their sizes should equal the size of the target output image. We solve this constrained optimization problem using the Lagrangian multiplier technique. Moreover, we extend the approach to the retargeting of video sequences. Simulation results demonstrate that the proposed algorithm provides reliable retargeting performance efficiently.

AB - An adaptive image and video retargeting algorithm based on Fourier analysis is proposed in this work. We first divide an input image into several strips using the gradient information so that each strip consists of textures of similar complexities. Then, we scale each strip adaptively according to its importance measure. More specifically, the distortions, generated by the scaling procedure, are formulated in the frequency domain using the Fourier transform. Then, the objective is to determine the sizes of scaled strips to minimize the sum of distortions, subject to the constraint that the sum of their sizes should equal the size of the target output image. We solve this constrained optimization problem using the Lagrangian multiplier technique. Moreover, we extend the approach to the retargeting of video sequences. Simulation results demonstrate that the proposed algorithm provides reliable retargeting performance efficiently.

UR - http://www.scopus.com/inward/record.url?scp=70450202485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70450202485&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2009.5206666

DO - 10.1109/CVPRW.2009.5206666

M3 - Conference contribution

AN - SCOPUS:70450202485

SN - 9781424439935

SP - 1730

EP - 1737

BT - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009

ER -