Visual surface reconstruction and boundary detection using stochastic models

Bilge Günsel; Anil K. Jain

doi:10.1109/ICPR.1992.201995

Visual surface reconstruction and boundary detection using stochastic models

Bilge Günsel, Anil K. Jain

Department of Electronics and Communication Engineering

Michigan State University

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

8 Citations (Scopus)

Abstract

The specification of regularization parameters is one of the difficult problems in using the weak membrane models for visual surface reconstruction and boundary detection. The gradient limit effect is a fundamental limitation of these models. In this study, we reduce the gradient limit effect by fusing the intensity and the range image of the same scene utilizing the Markov Random Field (MRF) models. In order to improve the reconstruction we propose an extended weak membrane model that exhibits more complex interactions of the line process as well as the intensity and the depth processes. Consequently, the feasible regularization parameter space becomes larger, resulting in a considerably independent reconstruction on the model parameters. The performance of the introduced model has been quantitatively evaluated by using a Kolmogorov-Smirnov (KS) difference measure.

Original language	English
Title of host publication	IAPR 1992 - 11th IAPR International Conference on Pattern Recognition
Subtitle of host publication	Image, Speech, and Signal Analysis
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	343-346
Number of pages	4
ISBN (Electronic)	0818629207
DOIs	https://doi.org/10.1109/ICPR.1992.201995
Publication status	Published - 1992
Event	11th IAPR International Conference on Pattern Recognition, IAPR 1992 - The Hague, Netherlands Duration: 30 Aug 1992 → 1 Sept 1992

Publication series

Name	Proceedings - International Conference on Pattern Recognition
Volume	3
ISSN (Print)	1051-4651

Conference

Conference	11th IAPR International Conference on Pattern Recognition, IAPR 1992
Country/Territory	Netherlands
City	The Hague
Period	30/08/92 → 1/09/92

Bibliographical note

Publisher Copyright:
© 1992 IEEE.

Access to Document

10.1109/ICPR.1992.201995

Cite this

Günsel, B., & Jain, A. K. (1992). Visual surface reconstruction and boundary detection using stochastic models. In IAPR 1992 - 11th IAPR International Conference on Pattern Recognition: Image, Speech, and Signal Analysis (pp. 343-346). Article 201995 (Proceedings - International Conference on Pattern Recognition; Vol. 3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.1992.201995

@inproceedings{e6394d741f0f4dfc949469c40cb6703f,

title = "Visual surface reconstruction and boundary detection using stochastic models",

abstract = "The specification of regularization parameters is one of the difficult problems in using the weak membrane models for visual surface reconstruction and boundary detection. The gradient limit effect is a fundamental limitation of these models. In this study, we reduce the gradient limit effect by fusing the intensity and the range image of the same scene utilizing the Markov Random Field (MRF) models. In order to improve the reconstruction we propose an extended weak membrane model that exhibits more complex interactions of the line process as well as the intensity and the depth processes. Consequently, the feasible regularization parameter space becomes larger, resulting in a considerably independent reconstruction on the model parameters. The performance of the introduced model has been quantitatively evaluated by using a Kolmogorov-Smirnov (KS) difference measure.",

author = "Bilge G{\"u}nsel and Jain, {Anil K.}",

note = "Publisher Copyright: {\textcopyright} 1992 IEEE.; 11th IAPR International Conference on Pattern Recognition, IAPR 1992 ; Conference date: 30-08-1992 Through 01-09-1992",

year = "1992",

doi = "10.1109/ICPR.1992.201995",

language = "English",

series = "Proceedings - International Conference on Pattern Recognition",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "343--346",

booktitle = "IAPR 1992 - 11th IAPR International Conference on Pattern Recognition",

address = "United States",

}

Günsel, B & Jain, AK 1992, Visual surface reconstruction and boundary detection using stochastic models. in IAPR 1992 - 11th IAPR International Conference on Pattern Recognition: Image, Speech, and Signal Analysis., 201995, Proceedings - International Conference on Pattern Recognition, vol. 3, Institute of Electrical and Electronics Engineers Inc., pp. 343-346, 11th IAPR International Conference on Pattern Recognition, IAPR 1992, The Hague, Netherlands, 30/08/92. https://doi.org/10.1109/ICPR.1992.201995

Visual surface reconstruction and boundary detection using stochastic models. / Günsel, Bilge; Jain, Anil K.
IAPR 1992 - 11th IAPR International Conference on Pattern Recognition: Image, Speech, and Signal Analysis. Institute of Electrical and Electronics Engineers Inc., 1992. p. 343-346 201995 (Proceedings - International Conference on Pattern Recognition; Vol. 3).

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

TY - GEN

T1 - Visual surface reconstruction and boundary detection using stochastic models

AU - Günsel, Bilge

AU - Jain, Anil K.

PY - 1992

Y1 - 1992

N2 - The specification of regularization parameters is one of the difficult problems in using the weak membrane models for visual surface reconstruction and boundary detection. The gradient limit effect is a fundamental limitation of these models. In this study, we reduce the gradient limit effect by fusing the intensity and the range image of the same scene utilizing the Markov Random Field (MRF) models. In order to improve the reconstruction we propose an extended weak membrane model that exhibits more complex interactions of the line process as well as the intensity and the depth processes. Consequently, the feasible regularization parameter space becomes larger, resulting in a considerably independent reconstruction on the model parameters. The performance of the introduced model has been quantitatively evaluated by using a Kolmogorov-Smirnov (KS) difference measure.

AB - The specification of regularization parameters is one of the difficult problems in using the weak membrane models for visual surface reconstruction and boundary detection. The gradient limit effect is a fundamental limitation of these models. In this study, we reduce the gradient limit effect by fusing the intensity and the range image of the same scene utilizing the Markov Random Field (MRF) models. In order to improve the reconstruction we propose an extended weak membrane model that exhibits more complex interactions of the line process as well as the intensity and the depth processes. Consequently, the feasible regularization parameter space becomes larger, resulting in a considerably independent reconstruction on the model parameters. The performance of the introduced model has been quantitatively evaluated by using a Kolmogorov-Smirnov (KS) difference measure.

UR - http://www.scopus.com/inward/record.url?scp=0005719828&partnerID=8YFLogxK

U2 - 10.1109/ICPR.1992.201995

DO - 10.1109/ICPR.1992.201995

M3 - Conference contribution

AN - SCOPUS:0005719828

T3 - Proceedings - International Conference on Pattern Recognition

SP - 343

EP - 346

BT - IAPR 1992 - 11th IAPR International Conference on Pattern Recognition

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th IAPR International Conference on Pattern Recognition, IAPR 1992

Y2 - 30 August 1992 through 1 September 1992

ER -

Günsel B, Jain AK. Visual surface reconstruction and boundary detection using stochastic models. In IAPR 1992 - 11th IAPR International Conference on Pattern Recognition: Image, Speech, and Signal Analysis. Institute of Electrical and Electronics Engineers Inc. 1992. p. 343-346. 201995. (Proceedings - International Conference on Pattern Recognition). doi: 10.1109/ICPR.1992.201995

Visual surface reconstruction and boundary detection using stochastic models

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this