Summarization-based image resizing by intelligent object carving

Weiming Dong, Ning Zhou, Tong Yee Lee, Fuzhang Wu, Yan Kong, Xiaopeng Zhang

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Image resizing can be more effectively achieved with a better understanding of image semantics. In this paper, similar patterns that exist in many real-world images are analyzed. By interactively detecting similar objects in an image, the image content can be summarized rather than simply distorted or cropped. This method enables the manipulation of image pixels or patches as well as semantic objects in the scene during image resizing process. Given the special nature of similar objects in a general image, the integration of a novel object carving (OC) operator with the multi-operator framework is proposed for summarizing similar objects. The object removal sequence in the summarization strategy directly affects resizing quality. The method by which to evaluate the visual importance of the object as well as to optimally select the candidates for object carving is demonstrated. To achieve practical resizing applications for general images, a template matching-based method is developed. This method can detect similar objects even when they are of various colors, transformed in terms of perspective, or partially occluded. To validate the proposed method, comparisons with state-of-the-art resizing techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method.

Original languageEnglish
Article number6565987
Pages (from-to)111-124
Number of pages14
JournalIEEE Transactions on Visualization and Computer Graphics
Volume20
Issue number1
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Semantics
Template matching
Mathematical operators
Pixels
Color

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Cite this

Dong, Weiming ; Zhou, Ning ; Lee, Tong Yee ; Wu, Fuzhang ; Kong, Yan ; Zhang, Xiaopeng. / Summarization-based image resizing by intelligent object carving. In: IEEE Transactions on Visualization and Computer Graphics. 2014 ; Vol. 20, No. 1. pp. 111-124.
@article{92cb9fd8a5a943e0bf2b2772e1cc95a5,
title = "Summarization-based image resizing by intelligent object carving",
abstract = "Image resizing can be more effectively achieved with a better understanding of image semantics. In this paper, similar patterns that exist in many real-world images are analyzed. By interactively detecting similar objects in an image, the image content can be summarized rather than simply distorted or cropped. This method enables the manipulation of image pixels or patches as well as semantic objects in the scene during image resizing process. Given the special nature of similar objects in a general image, the integration of a novel object carving (OC) operator with the multi-operator framework is proposed for summarizing similar objects. The object removal sequence in the summarization strategy directly affects resizing quality. The method by which to evaluate the visual importance of the object as well as to optimally select the candidates for object carving is demonstrated. To achieve practical resizing applications for general images, a template matching-based method is developed. This method can detect similar objects even when they are of various colors, transformed in terms of perspective, or partially occluded. To validate the proposed method, comparisons with state-of-the-art resizing techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method.",
author = "Weiming Dong and Ning Zhou and Lee, {Tong Yee} and Fuzhang Wu and Yan Kong and Xiaopeng Zhang",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/TVCG.2013.103",
language = "English",
volume = "20",
pages = "111--124",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "1",

}

Summarization-based image resizing by intelligent object carving. / Dong, Weiming; Zhou, Ning; Lee, Tong Yee; Wu, Fuzhang; Kong, Yan; Zhang, Xiaopeng.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 20, No. 1, 6565987, 01.01.2014, p. 111-124.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Summarization-based image resizing by intelligent object carving

AU - Dong, Weiming

AU - Zhou, Ning

AU - Lee, Tong Yee

AU - Wu, Fuzhang

AU - Kong, Yan

AU - Zhang, Xiaopeng

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Image resizing can be more effectively achieved with a better understanding of image semantics. In this paper, similar patterns that exist in many real-world images are analyzed. By interactively detecting similar objects in an image, the image content can be summarized rather than simply distorted or cropped. This method enables the manipulation of image pixels or patches as well as semantic objects in the scene during image resizing process. Given the special nature of similar objects in a general image, the integration of a novel object carving (OC) operator with the multi-operator framework is proposed for summarizing similar objects. The object removal sequence in the summarization strategy directly affects resizing quality. The method by which to evaluate the visual importance of the object as well as to optimally select the candidates for object carving is demonstrated. To achieve practical resizing applications for general images, a template matching-based method is developed. This method can detect similar objects even when they are of various colors, transformed in terms of perspective, or partially occluded. To validate the proposed method, comparisons with state-of-the-art resizing techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method.

AB - Image resizing can be more effectively achieved with a better understanding of image semantics. In this paper, similar patterns that exist in many real-world images are analyzed. By interactively detecting similar objects in an image, the image content can be summarized rather than simply distorted or cropped. This method enables the manipulation of image pixels or patches as well as semantic objects in the scene during image resizing process. Given the special nature of similar objects in a general image, the integration of a novel object carving (OC) operator with the multi-operator framework is proposed for summarizing similar objects. The object removal sequence in the summarization strategy directly affects resizing quality. The method by which to evaluate the visual importance of the object as well as to optimally select the candidates for object carving is demonstrated. To achieve practical resizing applications for general images, a template matching-based method is developed. This method can detect similar objects even when they are of various colors, transformed in terms of perspective, or partially occluded. To validate the proposed method, comparisons with state-of-the-art resizing techniques and a user study were conducted. Convincing visual results are shown to demonstrate the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84890420502&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890420502&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2013.103

DO - 10.1109/TVCG.2013.103

M3 - Article

AN - SCOPUS:84890420502

VL - 20

SP - 111

EP - 124

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 1

M1 - 6565987

ER -