Feature-preserving thumbnail generation based on graph cuts

Seong Gyun Jeong, Chang-Su Kim

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

Abstract

A novel algorithm for thumbnail generation, which preserves characteristic features of a source image including blurs and textures, is proposed in this work. When a source image is subsampled to generate a thumbnail, important visible cues, such as blurs and noises, are lost. To overcome this drawback, we first create multiple thumbnail candidates that accentuate three classes of image features: focal blur, motion blur, and detail. Then, we obtain the final thumbnail by composing these candidates adaptively. Assuming that image features are spatially varying but locally static, we formulate the composition task as a labeling problem, and employ the graph-cut optimization technique to solve the problem. Simulation results demonstrate that the proposed algorithm provides feature-preserving thumbnails efficiently.

Original languageEnglish
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages1081-1084
Number of pages4
DOIs
Publication statusPublished - 2011 Dec 1
Event2011 18th IEEE International Conference on Image Processing, ICIP 2011 - Brussels, Belgium
Duration: 2011 Sep 112011 Sep 14

Other

Other2011 18th IEEE International Conference on Image Processing, ICIP 2011
CountryBelgium
CityBrussels
Period11/9/1111/9/14

Fingerprint

Labeling
Textures
Chemical analysis

Keywords

  • blur analysis
  • detail enhancement
  • graph cuts
  • image resampling
  • Thumbnail generation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Jeong, S. G., & Kim, C-S. (2011). Feature-preserving thumbnail generation based on graph cuts. In Proceedings - International Conference on Image Processing, ICIP (pp. 1081-1084). [6115613] https://doi.org/10.1109/ICIP.2011.6115613

Feature-preserving thumbnail generation based on graph cuts. / Jeong, Seong Gyun; Kim, Chang-Su.

Proceedings - International Conference on Image Processing, ICIP. 2011. p. 1081-1084 6115613.

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

Jeong, SG & Kim, C-S 2011, Feature-preserving thumbnail generation based on graph cuts. in Proceedings - International Conference on Image Processing, ICIP., 6115613, pp. 1081-1084, 2011 18th IEEE International Conference on Image Processing, ICIP 2011, Brussels, Belgium, 11/9/11. https://doi.org/10.1109/ICIP.2011.6115613
Jeong SG, Kim C-S. Feature-preserving thumbnail generation based on graph cuts. In Proceedings - International Conference on Image Processing, ICIP. 2011. p. 1081-1084. 6115613 https://doi.org/10.1109/ICIP.2011.6115613
Jeong, Seong Gyun ; Kim, Chang-Su. / Feature-preserving thumbnail generation based on graph cuts. Proceedings - International Conference on Image Processing, ICIP. 2011. pp. 1081-1084
@inproceedings{d9f5b4382ca4440d89e7f2425be27926,
title = "Feature-preserving thumbnail generation based on graph cuts",
abstract = "A novel algorithm for thumbnail generation, which preserves characteristic features of a source image including blurs and textures, is proposed in this work. When a source image is subsampled to generate a thumbnail, important visible cues, such as blurs and noises, are lost. To overcome this drawback, we first create multiple thumbnail candidates that accentuate three classes of image features: focal blur, motion blur, and detail. Then, we obtain the final thumbnail by composing these candidates adaptively. Assuming that image features are spatially varying but locally static, we formulate the composition task as a labeling problem, and employ the graph-cut optimization technique to solve the problem. Simulation results demonstrate that the proposed algorithm provides feature-preserving thumbnails efficiently.",
keywords = "blur analysis, detail enhancement, graph cuts, image resampling, Thumbnail generation",
author = "Jeong, {Seong Gyun} and Chang-Su Kim",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/ICIP.2011.6115613",
language = "English",
isbn = "9781457713033",
pages = "1081--1084",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Feature-preserving thumbnail generation based on graph cuts

AU - Jeong, Seong Gyun

AU - Kim, Chang-Su

PY - 2011/12/1

Y1 - 2011/12/1

N2 - A novel algorithm for thumbnail generation, which preserves characteristic features of a source image including blurs and textures, is proposed in this work. When a source image is subsampled to generate a thumbnail, important visible cues, such as blurs and noises, are lost. To overcome this drawback, we first create multiple thumbnail candidates that accentuate three classes of image features: focal blur, motion blur, and detail. Then, we obtain the final thumbnail by composing these candidates adaptively. Assuming that image features are spatially varying but locally static, we formulate the composition task as a labeling problem, and employ the graph-cut optimization technique to solve the problem. Simulation results demonstrate that the proposed algorithm provides feature-preserving thumbnails efficiently.

AB - A novel algorithm for thumbnail generation, which preserves characteristic features of a source image including blurs and textures, is proposed in this work. When a source image is subsampled to generate a thumbnail, important visible cues, such as blurs and noises, are lost. To overcome this drawback, we first create multiple thumbnail candidates that accentuate three classes of image features: focal blur, motion blur, and detail. Then, we obtain the final thumbnail by composing these candidates adaptively. Assuming that image features are spatially varying but locally static, we formulate the composition task as a labeling problem, and employ the graph-cut optimization technique to solve the problem. Simulation results demonstrate that the proposed algorithm provides feature-preserving thumbnails efficiently.

KW - blur analysis

KW - detail enhancement

KW - graph cuts

KW - image resampling

KW - Thumbnail generation

UR - http://www.scopus.com/inward/record.url?scp=84863072495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863072495&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2011.6115613

DO - 10.1109/ICIP.2011.6115613

M3 - Conference contribution

AN - SCOPUS:84863072495

SN - 9781457713033

SP - 1081

EP - 1084

BT - Proceedings - International Conference on Image Processing, ICIP

ER -