Recovery of hierarchical part structure of 3-D shape from range image

Y. Sato, Jun Ohya, K. Ishii

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A formulation of the part decomposition problem motived by the minimum-description-length (MDL) criteria is presented. Unlike previous MDL approaches which use analytic functions, a general geometric constraint, convexity, is used as a part constraint. Therefore, the method is suitable for complex natural shapes such as human faces. The recovery process consists of a bottom-up grouping process and a subsequent optimization process based on the MDL criteria. The definite causal relations of part structure between different sensitivity levels are used to recover the hierarchy of part structure. Part decomposition experiments involving real 3-D range images are reported.

Original languageEnglish
Title of host publicationProceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition
PublisherIEEE Computer Society
Pages699-702
Number of pages4
ISBN (Electronic)0818628553
DOIs
Publication statusPublished - 1992 Jan 1
Externally publishedYes
Event1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992 - Champaign, United States
Duration: 1992 Jun 151992 Jun 18

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1992-June
ISSN (Print)1063-6919

Conference

Conference1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992
CountryUnited States
CityChampaign
Period92/6/1592/6/18

Fingerprint

Decomposition
Recovery
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Sato, Y., Ohya, J., & Ishii, K. (1992). Recovery of hierarchical part structure of 3-D shape from range image. In Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 699-702). [223197] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 1992-June). IEEE Computer Society. https://doi.org/10.1109/CVPR.1992.223197

Recovery of hierarchical part structure of 3-D shape from range image. / Sato, Y.; Ohya, Jun; Ishii, K.

Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 1992. p. 699-702 223197 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 1992-June).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sato, Y, Ohya, J & Ishii, K 1992, Recovery of hierarchical part structure of 3-D shape from range image. in Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 223197, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1992-June, IEEE Computer Society, pp. 699-702, 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 1992, Champaign, United States, 92/6/15. https://doi.org/10.1109/CVPR.1992.223197
Sato Y, Ohya J, Ishii K. Recovery of hierarchical part structure of 3-D shape from range image. In Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society. 1992. p. 699-702. 223197. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.1992.223197
Sato, Y. ; Ohya, Jun ; Ishii, K. / Recovery of hierarchical part structure of 3-D shape from range image. Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 1992. pp. 699-702 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{2b9cc6afc8104116937014d2c88640fc,
title = "Recovery of hierarchical part structure of 3-D shape from range image",
abstract = "A formulation of the part decomposition problem motived by the minimum-description-length (MDL) criteria is presented. Unlike previous MDL approaches which use analytic functions, a general geometric constraint, convexity, is used as a part constraint. Therefore, the method is suitable for complex natural shapes such as human faces. The recovery process consists of a bottom-up grouping process and a subsequent optimization process based on the MDL criteria. The definite causal relations of part structure between different sensitivity levels are used to recover the hierarchy of part structure. Part decomposition experiments involving real 3-D range images are reported.",
author = "Y. Sato and Jun Ohya and K. Ishii",
year = "1992",
month = "1",
day = "1",
doi = "10.1109/CVPR.1992.223197",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "699--702",
booktitle = "Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Recovery of hierarchical part structure of 3-D shape from range image

AU - Sato, Y.

AU - Ohya, Jun

AU - Ishii, K.

PY - 1992/1/1

Y1 - 1992/1/1

N2 - A formulation of the part decomposition problem motived by the minimum-description-length (MDL) criteria is presented. Unlike previous MDL approaches which use analytic functions, a general geometric constraint, convexity, is used as a part constraint. Therefore, the method is suitable for complex natural shapes such as human faces. The recovery process consists of a bottom-up grouping process and a subsequent optimization process based on the MDL criteria. The definite causal relations of part structure between different sensitivity levels are used to recover the hierarchy of part structure. Part decomposition experiments involving real 3-D range images are reported.

AB - A formulation of the part decomposition problem motived by the minimum-description-length (MDL) criteria is presented. Unlike previous MDL approaches which use analytic functions, a general geometric constraint, convexity, is used as a part constraint. Therefore, the method is suitable for complex natural shapes such as human faces. The recovery process consists of a bottom-up grouping process and a subsequent optimization process based on the MDL criteria. The definite causal relations of part structure between different sensitivity levels are used to recover the hierarchy of part structure. Part decomposition experiments involving real 3-D range images are reported.

UR - http://www.scopus.com/inward/record.url?scp=85027632340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027632340&partnerID=8YFLogxK

U2 - 10.1109/CVPR.1992.223197

DO - 10.1109/CVPR.1992.223197

M3 - Conference contribution

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

SP - 699

EP - 702

BT - Proceedings CVPR 1992 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition

PB - IEEE Computer Society

ER -