Fast image retargeting via axis-aligned importance scaling

Sunghwan Choi, Bumsub Ham, Kwanghoon Sohn

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

1 Citation (Scopus)

Abstract

In this paper, we propose an image retargeting method that resizes an image by the axis-aligned importance scaling. The proposed method operates on the axis-aligned deformation space, where the mesh structure is parameterized in the 1D vector, i.e., quads on the same column (or row) share the single parameter. The unknown variables are thus dependent on the grid resolution only, allowing a fast and simple implementation on a moderate CPU. The optimal parameters are inferred in an iterative manner: these parameters are updated by scaling initial ones according to the deformation error. It is measured at each iteration by aggregating the transition cost for the deformed quad. Experimental results show that the proposed method preserves visually salient features without foldover artifacts better than competing methods. In addition, the optimal parameters can be calculated within 0.02 ms on a single-core CPU.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages1061-1065
Number of pages5
DOIs
Publication statusPublished - 2013 Dec 1
Event2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia
Duration: 2013 Sep 152013 Sep 18

Other

Other2013 20th IEEE International Conference on Image Processing, ICIP 2013
CountryAustralia
CityMelbourne, VIC
Period13/9/1513/9/18

Fingerprint

Program processors
Costs

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Choi, S., Ham, B., & Sohn, K. (2013). Fast image retargeting via axis-aligned importance scaling. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings (pp. 1061-1065). [6738219] https://doi.org/10.1109/ICIP.2013.6738219
Choi, Sunghwan ; Ham, Bumsub ; Sohn, Kwanghoon. / Fast image retargeting via axis-aligned importance scaling. 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. pp. 1061-1065
@inproceedings{db98a580d6ce4ed5825df614957219d4,
title = "Fast image retargeting via axis-aligned importance scaling",
abstract = "In this paper, we propose an image retargeting method that resizes an image by the axis-aligned importance scaling. The proposed method operates on the axis-aligned deformation space, where the mesh structure is parameterized in the 1D vector, i.e., quads on the same column (or row) share the single parameter. The unknown variables are thus dependent on the grid resolution only, allowing a fast and simple implementation on a moderate CPU. The optimal parameters are inferred in an iterative manner: these parameters are updated by scaling initial ones according to the deformation error. It is measured at each iteration by aggregating the transition cost for the deformed quad. Experimental results show that the proposed method preserves visually salient features without foldover artifacts better than competing methods. In addition, the optimal parameters can be calculated within 0.02 ms on a single-core CPU.",
author = "Sunghwan Choi and Bumsub Ham and Kwanghoon Sohn",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/ICIP.2013.6738219",
language = "English",
isbn = "9781479923410",
pages = "1061--1065",
booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

}

Choi, S, Ham, B & Sohn, K 2013, Fast image retargeting via axis-aligned importance scaling. in 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings., 6738219, pp. 1061-1065, 2013 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, VIC, Australia, 13/9/15. https://doi.org/10.1109/ICIP.2013.6738219

Fast image retargeting via axis-aligned importance scaling. / Choi, Sunghwan; Ham, Bumsub; Sohn, Kwanghoon.

2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 1061-1065 6738219.

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

TY - GEN

T1 - Fast image retargeting via axis-aligned importance scaling

AU - Choi, Sunghwan

AU - Ham, Bumsub

AU - Sohn, Kwanghoon

PY - 2013/12/1

Y1 - 2013/12/1

N2 - In this paper, we propose an image retargeting method that resizes an image by the axis-aligned importance scaling. The proposed method operates on the axis-aligned deformation space, where the mesh structure is parameterized in the 1D vector, i.e., quads on the same column (or row) share the single parameter. The unknown variables are thus dependent on the grid resolution only, allowing a fast and simple implementation on a moderate CPU. The optimal parameters are inferred in an iterative manner: these parameters are updated by scaling initial ones according to the deformation error. It is measured at each iteration by aggregating the transition cost for the deformed quad. Experimental results show that the proposed method preserves visually salient features without foldover artifacts better than competing methods. In addition, the optimal parameters can be calculated within 0.02 ms on a single-core CPU.

AB - In this paper, we propose an image retargeting method that resizes an image by the axis-aligned importance scaling. The proposed method operates on the axis-aligned deformation space, where the mesh structure is parameterized in the 1D vector, i.e., quads on the same column (or row) share the single parameter. The unknown variables are thus dependent on the grid resolution only, allowing a fast and simple implementation on a moderate CPU. The optimal parameters are inferred in an iterative manner: these parameters are updated by scaling initial ones according to the deformation error. It is measured at each iteration by aggregating the transition cost for the deformed quad. Experimental results show that the proposed method preserves visually salient features without foldover artifacts better than competing methods. In addition, the optimal parameters can be calculated within 0.02 ms on a single-core CPU.

UR - http://www.scopus.com/inward/record.url?scp=84897765107&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897765107&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738219

DO - 10.1109/ICIP.2013.6738219

M3 - Conference contribution

SN - 9781479923410

SP - 1061

EP - 1065

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

ER -

Choi S, Ham B, Sohn K. Fast image retargeting via axis-aligned importance scaling. In 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings. 2013. p. 1061-1065. 6738219 https://doi.org/10.1109/ICIP.2013.6738219