Seam merging for image resizing with structure preservation

Kazu Mishiba, Masaaki Ikehara

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

11 Citations (Scopus)

Abstract

In image resizing process, preserving structure on an image is important to produce plausible results. We proposed seam merging, a seam-carving-based image resizing method, and a new energy criterion for structure preservation. Seam merging reduces the size of an image by merging a two-pixel-width seam into a one-pixel width seam. To find the optimal seam that minimizes structural distortion after merging, we introduce an energy function which has a large value when the merging breaks the structure. We further show the way to find the optimal seam using dynamic programming. Experimental results demonstrate that our proposal algorithm can produce fewer artifacts and successfully preserve structure.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages1001-1004
Number of pages4
DOIs
Publication statusPublished - 2011
Event36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Prague, Czech Republic
Duration: 2011 May 222011 May 27

Other

Other36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
CountryCzech Republic
CityPrague
Period11/5/2211/5/27

Fingerprint

Merging
Pixels
Dynamic programming

Keywords

  • image resizing
  • seam carving
  • structure preserving

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Mishiba, K., & Ikehara, M. (2011). Seam merging for image resizing with structure preservation. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 1001-1004). [5946575] https://doi.org/10.1109/ICASSP.2011.5946575

Seam merging for image resizing with structure preservation. / Mishiba, Kazu; Ikehara, Masaaki.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. p. 1001-1004 5946575.

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

Mishiba, K & Ikehara, M 2011, Seam merging for image resizing with structure preservation. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 5946575, pp. 1001-1004, 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague, Czech Republic, 11/5/22. https://doi.org/10.1109/ICASSP.2011.5946575
Mishiba K, Ikehara M. Seam merging for image resizing with structure preservation. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. p. 1001-1004. 5946575 https://doi.org/10.1109/ICASSP.2011.5946575
Mishiba, Kazu ; Ikehara, Masaaki. / Seam merging for image resizing with structure preservation. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2011. pp. 1001-1004
@inproceedings{a9d9601eb55e42f8963985dbd2203614,
title = "Seam merging for image resizing with structure preservation",
abstract = "In image resizing process, preserving structure on an image is important to produce plausible results. We proposed seam merging, a seam-carving-based image resizing method, and a new energy criterion for structure preservation. Seam merging reduces the size of an image by merging a two-pixel-width seam into a one-pixel width seam. To find the optimal seam that minimizes structural distortion after merging, we introduce an energy function which has a large value when the merging breaks the structure. We further show the way to find the optimal seam using dynamic programming. Experimental results demonstrate that our proposal algorithm can produce fewer artifacts and successfully preserve structure.",
keywords = "image resizing, seam carving, structure preserving",
author = "Kazu Mishiba and Masaaki Ikehara",
year = "2011",
doi = "10.1109/ICASSP.2011.5946575",
language = "English",
isbn = "9781457705397",
pages = "1001--1004",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Seam merging for image resizing with structure preservation

AU - Mishiba, Kazu

AU - Ikehara, Masaaki

PY - 2011

Y1 - 2011

N2 - In image resizing process, preserving structure on an image is important to produce plausible results. We proposed seam merging, a seam-carving-based image resizing method, and a new energy criterion for structure preservation. Seam merging reduces the size of an image by merging a two-pixel-width seam into a one-pixel width seam. To find the optimal seam that minimizes structural distortion after merging, we introduce an energy function which has a large value when the merging breaks the structure. We further show the way to find the optimal seam using dynamic programming. Experimental results demonstrate that our proposal algorithm can produce fewer artifacts and successfully preserve structure.

AB - In image resizing process, preserving structure on an image is important to produce plausible results. We proposed seam merging, a seam-carving-based image resizing method, and a new energy criterion for structure preservation. Seam merging reduces the size of an image by merging a two-pixel-width seam into a one-pixel width seam. To find the optimal seam that minimizes structural distortion after merging, we introduce an energy function which has a large value when the merging breaks the structure. We further show the way to find the optimal seam using dynamic programming. Experimental results demonstrate that our proposal algorithm can produce fewer artifacts and successfully preserve structure.

KW - image resizing

KW - seam carving

KW - structure preserving

UR - http://www.scopus.com/inward/record.url?scp=80051609129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051609129&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2011.5946575

DO - 10.1109/ICASSP.2011.5946575

M3 - Conference contribution

SN - 9781457705397

SP - 1001

EP - 1004

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

ER -