Diffusion-geometric maximally stable component detection in deformable shapes

Roee Litman; Alexander M. Bronstein; Michael M. Bronstein

doi:10.1016/j.cag.2011.03.011

Diffusion-geometric maximally stable component detection in deformable shapes

Roee Litman^*, Alexander M. Bronstein, Michael M. Bronstein

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Maximally stable component detection is a very popular method for feature analysis in images, mainly due to its low computation cost and high repeatability. With the recent advance of feature-based methods in geometric shape analysis, there is significant interest in finding analogous approaches in the 3D world. In this paper, we formulate a diffusion-geometric framework for stable component detection in non-rigid 3D shapes, which can be used for geometric feature detection and description. A quantitative evaluation of our method on the SHREC'10 feature detection benchmark shows its potential as a source of high-quality features.

Original language	English
Pages (from-to)	549-560
Number of pages	12
Journal	Computers and Graphics
Volume	35
Issue number	3
DOIs	https://doi.org/10.1016/j.cag.2011.03.011
State	Published - Jun 2011
Externally published	Yes

Keywords

Component tree
Deformable shapes
Diffusion geometry
Feature detection
Level sets
MSER

Access to Document

10.1016/j.cag.2011.03.011

Cite this

@article{92febd90677e419c8d981cbc9adb1150,

title = "Diffusion-geometric maximally stable component detection in deformable shapes",

abstract = "Maximally stable component detection is a very popular method for feature analysis in images, mainly due to its low computation cost and high repeatability. With the recent advance of feature-based methods in geometric shape analysis, there is significant interest in finding analogous approaches in the 3D world. In this paper, we formulate a diffusion-geometric framework for stable component detection in non-rigid 3D shapes, which can be used for geometric feature detection and description. A quantitative evaluation of our method on the SHREC'10 feature detection benchmark shows its potential as a source of high-quality features.",

keywords = "Component tree, Deformable shapes, Diffusion geometry, Feature detection, Level sets, MSER",

author = "Roee Litman and Bronstein, {Alexander M.} and Bronstein, {Michael M.}",

note = "Funding Information: Michael Bronstein is supported by the Swiss High-Performance and High-Productivity Computing (HP2C). ",

year = "2011",

month = jun,

doi = "10.1016/j.cag.2011.03.011",

language = "אנגלית",

volume = "35",

pages = "549--560",

journal = "Computers and Graphics",

issn = "0097-8493",

publisher = "Elsevier Ltd.",

number = "3",

}

TY - JOUR

T1 - Diffusion-geometric maximally stable component detection in deformable shapes

AU - Litman, Roee

AU - Bronstein, Alexander M.

AU - Bronstein, Michael M.

N1 - Funding Information: Michael Bronstein is supported by the Swiss High-Performance and High-Productivity Computing (HP2C).

PY - 2011/6

Y1 - 2011/6

N2 - Maximally stable component detection is a very popular method for feature analysis in images, mainly due to its low computation cost and high repeatability. With the recent advance of feature-based methods in geometric shape analysis, there is significant interest in finding analogous approaches in the 3D world. In this paper, we formulate a diffusion-geometric framework for stable component detection in non-rigid 3D shapes, which can be used for geometric feature detection and description. A quantitative evaluation of our method on the SHREC'10 feature detection benchmark shows its potential as a source of high-quality features.

AB - Maximally stable component detection is a very popular method for feature analysis in images, mainly due to its low computation cost and high repeatability. With the recent advance of feature-based methods in geometric shape analysis, there is significant interest in finding analogous approaches in the 3D world. In this paper, we formulate a diffusion-geometric framework for stable component detection in non-rigid 3D shapes, which can be used for geometric feature detection and description. A quantitative evaluation of our method on the SHREC'10 feature detection benchmark shows its potential as a source of high-quality features.

KW - Component tree

KW - Deformable shapes

KW - Diffusion geometry

KW - Feature detection

KW - Level sets

KW - MSER

UR - http://www.scopus.com/inward/record.url?scp=79957810528&partnerID=8YFLogxK

U2 - 10.1016/j.cag.2011.03.011

DO - 10.1016/j.cag.2011.03.011

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:79957810528

SN - 0097-8493

VL - 35

SP - 549

EP - 560

JO - Computers and Graphics

JF - Computers and Graphics

IS - 3

ER -

Diffusion-geometric maximally stable component detection in deformable shapes

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this