A patch analysis approach for seam-carved image detection

Jyh Da Wei*, Yu Ju Lin, Yi Jing Wu, Li Wei Kang

*Corresponding author for this work

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

4 Citations (Scopus)

Abstract

Seam carving is a content-Aware image resizing method [Shamir and Avidan 2007], which assigns Sobel-operator-based energy to each pixel and describes seams as the eight-connected paths of pixels. Successive removal of the optimal seams, i.e., those seams with the lowest sum of energy, allows reduction in image size. Pixels with lower energy are generally removed earlier; implying that (1) the modifications to the image are difficult to identify and (2) low energy can be deliberately assigned to particular objects so that they can be removed from the image. These two observations reveal that, although difficult, it is important to design a seam carving detection method.

Original languageEnglish
Title of host publicationACM SIGGRAPH 2013 Posters, SIGGRAPH 2013
DOIs
Publication statusPublished - 2013
Externally publishedYes
EventACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2013 - Anaheim, CA, United States
Duration: 2013 Jul 212013 Jul 25

Publication series

NameACM SIGGRAPH 2013 Posters, SIGGRAPH 2013

Conference

ConferenceACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2013
Country/TerritoryUnited States
CityAnaheim, CA
Period2013/07/212013/07/25

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'A patch analysis approach for seam-carved image detection'. Together they form a unique fingerprint.

Cite this