Spectral matting

Anat Levin; Alex Rav-Acha; Dani Lischinski

doi:10.1109/TPAMI.2008.168

Spectral matting

Anat Levin^*
, Alex Rav-Acha
, Dani Lischinski

^*Corresponding author for this work

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Contribution to journal › Article › peer-review

284 Scopus citations

Abstract

We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.

Original language	English
Pages (from-to)	1699-1712
Number of pages	14
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	30
Issue number	10
DOIs	https://doi.org/10.1109/TPAMI.2008.168
State	Published - 2008

Keywords

Image matting
Spectral analysis
Unsupervised segmentation

Access to Document

10.1109/TPAMI.2008.168

Cite this

@article{7c75ac996f1044868b559dfc19a8d6e1,

title = "Spectral matting",

abstract = "We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.",

keywords = "Image matting, Spectral analysis, Unsupervised segmentation",

author = "Anat Levin and Alex Rav-Acha and Dani Lischinski",

year = "2008",

doi = "10.1109/TPAMI.2008.168",

language = "אנגלית",

volume = "30",

pages = "1699--1712",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "10",

}

TY - JOUR

T1 - Spectral matting

AU - Levin, Anat

AU - Rav-Acha, Alex

AU - Lischinski, Dani

PY - 2008

Y1 - 2008

N2 - We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.

AB - We present spectral matting: a new approach to natural image matting that automatically computes a basis set of fuzzy matting components from the smallest eigenvectors of a suitably defined Laplacian matrix. Thus, our approach extends spectral segmentation techniques, whose goal is to extract hard segments, to the extraction of soft matting components. These components may then be used as building blocks to easily construct semantically meaningful foreground mattes, either in an unsupervised fashion, or based on a small amount of user input.

KW - Image matting

KW - Spectral analysis

KW - Unsupervised segmentation

UR - https://www.scopus.com/pages/publications/50249161297

U2 - 10.1109/TPAMI.2008.168

DO - 10.1109/TPAMI.2008.168

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 18703825

AN - SCOPUS:50249161297

SN - 0162-8828

VL - 30

SP - 1699

EP - 1712

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 10

ER -

Spectral matting

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this