Skip to main navigation Skip to search Skip to main content

Digital image matting based on hybrid distance transformation

  • Silesian University of Technology

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

2 Citations (Scopus)

Abstract

In this paper we present a novel semi-automatic method for image segmentation and matting, that utilizes the newly proposed generalized distance transform to determine the dissimilarity between the foreground and background regions within an image. These distance transform values are used to estimate the alpha matting coefficients needed for composing a new image by blending the foreground objects with a new background image scene. The effectiveness of the proposed algorithm allows the user to work interactively and to obtain the desired results promptly after marking the regions by scribbling the image. We show that the method yields satisfactory results for gray scale and color images.

Original languageEnglish
Title of host publicationProceedings of the 13th WSEAS International Conference on Computers - Held as part of the 13th WSEAS CSCC Multiconference
Pages277-282
Number of pages6
Publication statusPublished - 2009
Event13th WSEAS International Conference on Computers - Held as part of the 13th WSEAS CSCC Multiconference - Rodos, Greece
Duration: 23 Jul 200925 Jul 2009

Publication series

NameProceedings of the 13th WSEAS International Conference on Computers - Held as part of the 13th WSEAS CSCC Multiconference

Conference

Conference13th WSEAS International Conference on Computers - Held as part of the 13th WSEAS CSCC Multiconference
Country/TerritoryGreece
CityRodos
Period23/07/0925/07/09

Keywords

  • Color image processing
  • Compositing
  • Distance transform
  • Matting

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Digital image matting based on hybrid distance transformation'. Together they form a unique fingerprint.

Cite this