A geodesic active contour framework for finding glass

Kenton McHenry; Jean Ponce

doi:10.1109/CVPR.2006.28

A geodesic active contour framework for finding glass

Kenton McHenry, Jean Ponce

National Center for Supercomputing Applications (NCSA)

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

Abstract

This paper addresses the problem of finding objects made of glass (or other transparent materials) in images. Since the appearance of glass objects depends for the most part on what lies behind them, we propose to use binary criteria ("are these two regions made of the same material?") rather than unary ones ("is this glass?") to guide the segmentation process. Concretely, we combine two complementary measures of affinity between regions made of the same material and discrepancy between regions made of different ones into a single objective function, and use the geodesic active contour framework to minimize this function over pixel labels. The proposed approach has been implemented, and qualitative and quantitative experimental results are presented.

Original language	English (US)
Title of host publication	Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages	1038-1044
Number of pages	7
DOIs	https://doi.org/10.1109/CVPR.2006.28
State	Published - 2006
Event	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States Duration: Jun 17 2006 → Jun 22 2006

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	1
ISSN (Print)	1063-6919

Other

Other	2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Country/Territory	United States
City	New York, NY
Period	6/17/06 → 6/22/06

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Online availability

10.1109/CVPR.2006.28

Library availability

Discover UIUC Full Text

Cite this

McHenry, K., & Ponce, J. (2006). A geodesic active contour framework for finding glass. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 (pp. 1038-1044). Article 1640865 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 1). https://doi.org/10.1109/CVPR.2006.28

A geodesic active contour framework for finding glass. / McHenry, Kenton; Ponce, Jean.
Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 1038-1044 1640865 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 1).

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

McHenry, K & Ponce, J 2006, A geodesic active contour framework for finding glass. in Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006., 1640865, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 1038-1044, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, NY, United States, 6/17/06. https://doi.org/10.1109/CVPR.2006.28

@inproceedings{9b7970b6f34f4536b8feee48a202233a,

title = "A geodesic active contour framework for finding glass",

abstract = "This paper addresses the problem of finding objects made of glass (or other transparent materials) in images. Since the appearance of glass objects depends for the most part on what lies behind them, we propose to use binary criteria ({"}are these two regions made of the same material?{"}) rather than unary ones ({"}is this glass?{"}) to guide the segmentation process. Concretely, we combine two complementary measures of affinity between regions made of the same material and discrepancy between regions made of different ones into a single objective function, and use the geodesic active contour framework to minimize this function over pixel labels. The proposed approach has been implemented, and qualitative and quantitative experimental results are presented.",

author = "Kenton McHenry and Jean Ponce",

year = "2006",

doi = "10.1109/CVPR.2006.28",

language = "English (US)",

isbn = "0769525970",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

pages = "1038--1044",

booktitle = "Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006",

note = "2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 ; Conference date: 17-06-2006 Through 22-06-2006",

}

TY - GEN

T1 - A geodesic active contour framework for finding glass

AU - McHenry, Kenton

AU - Ponce, Jean

PY - 2006

Y1 - 2006

N2 - This paper addresses the problem of finding objects made of glass (or other transparent materials) in images. Since the appearance of glass objects depends for the most part on what lies behind them, we propose to use binary criteria ("are these two regions made of the same material?") rather than unary ones ("is this glass?") to guide the segmentation process. Concretely, we combine two complementary measures of affinity between regions made of the same material and discrepancy between regions made of different ones into a single objective function, and use the geodesic active contour framework to minimize this function over pixel labels. The proposed approach has been implemented, and qualitative and quantitative experimental results are presented.

AB - This paper addresses the problem of finding objects made of glass (or other transparent materials) in images. Since the appearance of glass objects depends for the most part on what lies behind them, we propose to use binary criteria ("are these two regions made of the same material?") rather than unary ones ("is this glass?") to guide the segmentation process. Concretely, we combine two complementary measures of affinity between regions made of the same material and discrepancy between regions made of different ones into a single objective function, and use the geodesic active contour framework to minimize this function over pixel labels. The proposed approach has been implemented, and qualitative and quantitative experimental results are presented.

UR - http://www.scopus.com/inward/record.url?scp=33845591068&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845591068&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2006.28

DO - 10.1109/CVPR.2006.28

M3 - Conference contribution

AN - SCOPUS:33845591068

SN - 0769525970

SN - 9780769525976

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1038

EP - 1044

BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

T2 - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

Y2 - 17 June 2006 through 22 June 2006

ER -

A geodesic active contour framework for finding glass

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this