Matting through variational inpainting

Kangyu Ni; Sheshadri R. Thiruvenkadam; Tony F. Chan

Matting through variational inpainting

Kangyu Ni^*, Sheshadri R. Thiruvenkadam, Tony F. Chan

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

While current matting algorithms work very well for some natural images, their performance is questionable in the presence of sharp discontinuities in the foreground and background regions. To counter the above problem, we propose to use variational PDE based inpainting techniques within the matting problem, that are largely successful in inpainting geometric features into unknown regions.

Original language	English (US)
Title of host publication	Proceedings of the 9th IASTED International Conference on Signal and Image Processing, SIP 2007
Pages	179-184
Number of pages	6
State	Published - Dec 1 2007
Externally published	Yes
Event	9th IASTED International Conference on Signal and Image Processing, SIP 2007 - Honolulu, HI, United States Duration: Aug 20 2007 → Aug 22 2007

Conference

Conference	9th IASTED International Conference on Signal and Image Processing, SIP 2007
Country/Territory	United States
City	Honolulu, HI
Period	08/20/07 → 08/22/07

Keywords

Matting
Variational inpainting

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Signal Processing

Cite this

@inproceedings{667e60859b86417782ea912905c653dc,

title = "Matting through variational inpainting",

abstract = "While current matting algorithms work very well for some natural images, their performance is questionable in the presence of sharp discontinuities in the foreground and background regions. To counter the above problem, we propose to use variational PDE based inpainting techniques within the matting problem, that are largely successful in inpainting geometric features into unknown regions.",

keywords = "Matting, Variational inpainting",

author = "Kangyu Ni and Thiruvenkadam, {Sheshadri R.} and Chan, {Tony F.}",

year = "2007",

month = dec,

day = "1",

language = "English (US)",

isbn = "9780889866751",

pages = "179--184",

booktitle = "Proceedings of the 9th IASTED International Conference on Signal and Image Processing, SIP 2007",

note = "9th IASTED International Conference on Signal and Image Processing, SIP 2007 ; Conference date: 20-08-2007 Through 22-08-2007",

}

TY - GEN

T1 - Matting through variational inpainting

AU - Ni, Kangyu

AU - Thiruvenkadam, Sheshadri R.

AU - Chan, Tony F.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - While current matting algorithms work very well for some natural images, their performance is questionable in the presence of sharp discontinuities in the foreground and background regions. To counter the above problem, we propose to use variational PDE based inpainting techniques within the matting problem, that are largely successful in inpainting geometric features into unknown regions.

AB - While current matting algorithms work very well for some natural images, their performance is questionable in the presence of sharp discontinuities in the foreground and background regions. To counter the above problem, we propose to use variational PDE based inpainting techniques within the matting problem, that are largely successful in inpainting geometric features into unknown regions.

KW - Matting

KW - Variational inpainting

UR - http://www.scopus.com/inward/record.url?scp=56149126370&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:56149126370

SN - 9780889866751

SP - 179

EP - 184

BT - Proceedings of the 9th IASTED International Conference on Signal and Image Processing, SIP 2007

T2 - 9th IASTED International Conference on Signal and Image Processing, SIP 2007

Y2 - 20 August 2007 through 22 August 2007

ER -

Matting through variational inpainting

Abstract

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this