One-sided object cutout using principal-channels

Lior Gavish*, Lior Shapira, Lior Wolf, Daniel Cohen-Or

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

We introduce principal-channels for cutting out objects from an image by one-sided scribbles. We demonstrate that few scribbles, all from within the object of interest, are sufficient to mark it out. One-sided scribbles provide significantly less information than two-sided ones. Thus, it is required to maximize the use of image-information. Our approach is to first analyze the image with a large filter bank and generate a high-dimensional feature space. We then extract a set of principal-channels that discern one object from another. We show that by applying an iterative graph-cut optimization over the principal-channels, we can cut out the object of interest.

Original languageEnglish
Title of host publicationProceedings - 2009 11th IEEE International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2009
Pages448-451
Number of pages4
DOIs
StatePublished - 2009
Event2009 11th IEEE International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2009 - Huangshan, China
Duration: 19 Aug 200921 Aug 2009

Publication series

NameProceedings - 2009 11th IEEE International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2009

Conference

Conference2009 11th IEEE International Conference on Computer-Aided Design and Computer Graphics, CAD/Graphics 2009
Country/TerritoryChina
CityHuangshan
Period19/08/0921/08/09

Fingerprint

Dive into the research topics of 'One-sided object cutout using principal-channels'. Together they form a unique fingerprint.

Cite this