The W-Penalty and its Application to Alpha Matting with Sparse Labels

Stephen Tierney; Junbin Gao; Yi Guo

doi:10.1109/DICTA.2014.7008132

The W-Penalty and its Application to Alpha Matting with Sparse Labels

Stephen Tierney, Junbin Gao, Yi Guo

Research output: Book chapter/Published conference paper › Conference paper › peer-review

Abstract

Alpha matting is an ill-posed problem, as such the user must supply dense partial labels for an acceptable solution to be reached. Unfortunately this labelling can be time consuming. In this paper we introduce the w-penalty function, which when incorporated into existing matting techniques allows users to supply extremely sparse input. The formulated objective function encourages driving matte values to 0 and 1. The experiments demonstrate the proposed model outperforms the state-of-the-art KNN matting algorithm. MATLAB code for our proposed method is freely available in the MatteKit package1..

Original language	English
Title of host publication	Proceedings of the 2014 International Conference on Digital Image Computing: Techniques and Applications
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1-7
Number of pages	7
ISBN (Electronic)	9781479954094
DOIs	https://doi.org/10.1109/DICTA.2014.7008132
Publication status	Published - 2014
Event	2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA) - Novotel Wollongong Northbeach Hotel, Wollongong, Australia Duration: 25 Nov 2014 → 27 Nov 2014 https://ssl.informatics.uow.edu.au/dicta2014/

Conference

Conference	2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
Country/Territory	Australia
City	Wollongong
Period	25/11/14 → 27/11/14
Other	The International Conference on Digital Image Computing: Techniques and Applications (DICTA) is an International Conference on computer vision, image processing, pattern recognition, and related areas. DICTA was established as a biennial conference in 1991 and became an annual event in 2007. It is the premier conference of the Australian Pattern Recognition Society (APRS).
Internet address	https://ssl.informatics.uow.edu.au/dicta2014/

Access to Document

10.1109/DICTA.2014.7008132

Cite this

@inproceedings{2bd05870a0a84ec2836ffd23c06ae6cf,

title = "The W-Penalty and its Application to Alpha Matting with Sparse Labels",

abstract = "Alpha matting is an ill-posed problem, as such the user must supply dense partial labels for an acceptable solution to be reached. Unfortunately this labelling can be time consuming. In this paper we introduce the w-penalty function, which when incorporated into existing matting techniques allows users to supply extremely sparse input. The formulated objective function encourages driving matte values to 0 and 1. The experiments demonstrate the proposed model outperforms the state-of-the-art KNN matting algorithm. MATLAB code for our proposed method is freely available in the MatteKit package1..",

keywords = "Alpha matting is an ill-posed problem, as such the user must supply dense partial labels for an acceptable solution to be reached. Unfortunately this labelling can be time consuming. In this paper we introduce the w-penalty function, which when incorporated into existing matting techniques allows users to supply extremely sparse input. The formulated objective function encourages driving matte values to 0 and 1. The experiments demonstrate the proposed model outperforms the state-of-the-art KNN matting algorithm. MATLAB code for our proposed method is freely available in the MatteKit package.",

author = "Stephen Tierney and Junbin Gao and Yi Guo",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = United States: Electrical and Electronics Engineers, 2014. editor/s (773b) = Phung S L ,Bouzerdoum A ,Ogunbona P ,Li W ,Wang L ; Event dates (773o) = 25-27 Nov. 2014; Parent title (773t) = International Conference on Digital Image Computing: Techniques and Applications.; 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA) ; Conference date: 25-11-2014 Through 27-11-2014",

year = "2014",

doi = "10.1109/DICTA.2014.7008132",

language = "English",

pages = "1--7",

booktitle = "Proceedings of the 2014 International Conference on Digital Image Computing: Techniques and Applications",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

url = "https://ssl.informatics.uow.edu.au/dicta2014/",

}

Tierney, S, Gao, J & Guo, Y 2014, The W-Penalty and its Application to Alpha Matting with Sparse Labels. in Proceedings of the 2014 International Conference on Digital Image Computing: Techniques and Applications. IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 1-7, 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Wollongong, New South Wales, Australia, 25/11/14. https://doi.org/10.1109/DICTA.2014.7008132

The W-Penalty and its Application to Alpha Matting with Sparse Labels. / Tierney, Stephen; Gao, Junbin; Guo, Yi.

Proceedings of the 2014 International Conference on Digital Image Computing: Techniques and Applications. United States : IEEE, Institute of Electrical and Electronics Engineers, 2014. p. 1-7.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - The W-Penalty and its Application to Alpha Matting with Sparse Labels

AU - Tierney, Stephen

AU - Gao, Junbin

AU - Guo, Yi

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = United States: Electrical and Electronics Engineers, 2014. editor/s (773b) = Phung S L ,Bouzerdoum A ,Ogunbona P ,Li W ,Wang L ; Event dates (773o) = 25-27 Nov. 2014; Parent title (773t) = International Conference on Digital Image Computing: Techniques and Applications.

PY - 2014

Y1 - 2014

N2 - Alpha matting is an ill-posed problem, as such the user must supply dense partial labels for an acceptable solution to be reached. Unfortunately this labelling can be time consuming. In this paper we introduce the w-penalty function, which when incorporated into existing matting techniques allows users to supply extremely sparse input. The formulated objective function encourages driving matte values to 0 and 1. The experiments demonstrate the proposed model outperforms the state-of-the-art KNN matting algorithm. MATLAB code for our proposed method is freely available in the MatteKit package1..

AB - Alpha matting is an ill-posed problem, as such the user must supply dense partial labels for an acceptable solution to be reached. Unfortunately this labelling can be time consuming. In this paper we introduce the w-penalty function, which when incorporated into existing matting techniques allows users to supply extremely sparse input. The formulated objective function encourages driving matte values to 0 and 1. The experiments demonstrate the proposed model outperforms the state-of-the-art KNN matting algorithm. MATLAB code for our proposed method is freely available in the MatteKit package1..

KW - Alpha matting is an ill-posed problem, as such the user must supply dense partial labels for an acceptable solution to be reached. Unfortunately this labelling can be time consuming. In this paper we introduce the w-penalty function, which when incorporat

U2 - 10.1109/DICTA.2014.7008132

DO - 10.1109/DICTA.2014.7008132

M3 - Conference paper

SP - 1

EP - 7

BT - Proceedings of the 2014 International Conference on Digital Image Computing: Techniques and Applications

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA)

Y2 - 25 November 2014 through 27 November 2014

ER -

The W-Penalty and its Application to Alpha Matting with Sparse Labels

Abstract

Conference

Access to Document

Fingerprint

Cite this