L1 matting

Philip Greggory Lee, Ying Wu

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

3 Scopus citations

Abstract

Natural image matting continues to play a large role in a wide variety of applications. As an ill-posed problem, matting is a very difficult to solve due to its underconstrained nature. Current approaches can require a lot of user input, restrict themselves to a sparse subset of the image, and often make assumptions that are unlikely to hold. In this paper, we pose a way to better satisfy smoothness assumptions of some of these methods utilizing the nonlinear median filter which arises naturally from the L1 norm. The median has the property that it tends to smooth the foreground and background of the image while leaving any edges relatively unaltered. We then show that such an image is often more suitable as input than the original image, even when user interaction is minimal, suggesting that our method is more amenable to automatic matting.

Original languageEnglish (US)
Title of host publication2010 IEEE International Conference on Image Processing, ICIP 2010 - Proceedings
Pages4665-4668
Number of pages4
DOIs
StatePublished - Dec 1 2010
Event2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong, Hong Kong
Duration: Sep 26 2010Sep 29 2010

Other

Other2010 17th IEEE International Conference on Image Processing, ICIP 2010
CountryHong Kong
CityHong Kong
Period9/26/109/29/10

Keywords

  • Alpha
  • Matting
  • Median
  • Norm

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'L<sub>1</sub> matting'. Together they form a unique fingerprint.

Cite this