Automatic Keypoint Detection on 3D Faces Using a Dictionary of Local Shapes

Clement Creusot; Nick Pears; Jim Austin

doi:http://dx.doi.org/10.1109/3DIMPVT.2011.33

Automatic Keypoint Detection on 3D Faces Using a Dictionary of Local Shapes

Clement Creusot, Nick Pears, Jim Austin

Computer Science

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

Abstract

Key points on 3D surfaces are points that can be extracted repeatably over a wide range of 3D imaging conditions. They are used in many 3D shape processing applications, for example, to establish a set of initial correspondences across a pair of surfaces to be matched. Typically, key points are extracted using extremal values of a function over the 3D surface, such as the descriptor map for Gaussian curvature. That approach works well for salient points, such as the nose-tip, but can not be used with other less pronounced local shapes. In this paper, we present an automatic method to detect key points on 3D faces, where these key points are locally similar to a set of previously learnt shapes, constituting a 'local shape dictionary'. The local shapes are learnt at a set of 14 manually-placed landmark positions on the human face. Local shapes are characterised by a set of 10 shape descriptors computed over a range of scales. For each landmark, the proportion of face meshes that have an associated key point detection is used as a performance indicator. Repeatability of the extracted key points is measured across the FRGC v2 database.

Original language	Undefined/Unknown
Title of host publication	Proceedings of the 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission
Place of Publication	Washington, DC, USA
Publisher	IEEE Computer Society
Pages	204-211
Number of pages	8
DOIs	https://doi.org/10.1109/3DIMPVT.2011.33
Publication status	Published - 2011

Publication series

Name	3DIMPVT '11
Publisher	IEEE Computer Society

Keywords

3D face, keypoint detection, local 3D descriptors

Access to Document

http://dx.doi.org/10.1109/3DIMPVT.2011.33

http://dx.doi.org/10.1109/3DIMPVT.2011.33

Cite this

@inproceedings{85df35bba2374c548e6a2071aa760097,

title = "Automatic Keypoint Detection on 3D Faces Using a Dictionary of Local Shapes",

abstract = "Key points on 3D surfaces are points that can be extracted repeatably over a wide range of 3D imaging conditions. They are used in many 3D shape processing applications, for example, to establish a set of initial correspondences across a pair of surfaces to be matched. Typically, key points are extracted using extremal values of a function over the 3D surface, such as the descriptor map for Gaussian curvature. That approach works well for salient points, such as the nose-tip, but can not be used with other less pronounced local shapes. In this paper, we present an automatic method to detect key points on 3D faces, where these key points are locally similar to a set of previously learnt shapes, constituting a 'local shape dictionary'. The local shapes are learnt at a set of 14 manually-placed landmark positions on the human face. Local shapes are characterised by a set of 10 shape descriptors computed over a range of scales. For each landmark, the proportion of face meshes that have an associated key point detection is used as a performance indicator. Repeatability of the extracted key points is measured across the FRGC v2 database.",

keywords = "3D face, keypoint detection, local 3D descriptors",

author = "Clement Creusot and Nick Pears and Jim Austin",

year = "2011",

doi = "http://dx.doi.org/10.1109/3DIMPVT.2011.33",

language = "Undefined/Unknown",

series = "3DIMPVT '11",

publisher = "IEEE Computer Society",

pages = "204--211",

booktitle = "Proceedings of the 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission",

address = "United States",

}

Automatic Keypoint Detection on 3D Faces Using a Dictionary of Local Shapes. / Creusot, Clement ; Pears, Nick ; Austin, Jim.
Proceedings of the 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission. Washington, DC, USA: IEEE Computer Society, 2011. p. 204-211 (3DIMPVT '11).

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

TY - GEN

T1 - Automatic Keypoint Detection on 3D Faces Using a Dictionary of Local Shapes

AU - Creusot, Clement

AU - Pears, Nick

AU - Austin, Jim

PY - 2011

Y1 - 2011

N2 - Key points on 3D surfaces are points that can be extracted repeatably over a wide range of 3D imaging conditions. They are used in many 3D shape processing applications, for example, to establish a set of initial correspondences across a pair of surfaces to be matched. Typically, key points are extracted using extremal values of a function over the 3D surface, such as the descriptor map for Gaussian curvature. That approach works well for salient points, such as the nose-tip, but can not be used with other less pronounced local shapes. In this paper, we present an automatic method to detect key points on 3D faces, where these key points are locally similar to a set of previously learnt shapes, constituting a 'local shape dictionary'. The local shapes are learnt at a set of 14 manually-placed landmark positions on the human face. Local shapes are characterised by a set of 10 shape descriptors computed over a range of scales. For each landmark, the proportion of face meshes that have an associated key point detection is used as a performance indicator. Repeatability of the extracted key points is measured across the FRGC v2 database.

AB - Key points on 3D surfaces are points that can be extracted repeatably over a wide range of 3D imaging conditions. They are used in many 3D shape processing applications, for example, to establish a set of initial correspondences across a pair of surfaces to be matched. Typically, key points are extracted using extremal values of a function over the 3D surface, such as the descriptor map for Gaussian curvature. That approach works well for salient points, such as the nose-tip, but can not be used with other less pronounced local shapes. In this paper, we present an automatic method to detect key points on 3D faces, where these key points are locally similar to a set of previously learnt shapes, constituting a 'local shape dictionary'. The local shapes are learnt at a set of 14 manually-placed landmark positions on the human face. Local shapes are characterised by a set of 10 shape descriptors computed over a range of scales. For each landmark, the proportion of face meshes that have an associated key point detection is used as a performance indicator. Repeatability of the extracted key points is measured across the FRGC v2 database.

KW - 3D face, keypoint detection, local 3D descriptors

UR - http://www.scopus.com/inward/record.url?scp=80052016148&partnerID=8YFLogxK

U2 - http://dx.doi.org/10.1109/3DIMPVT.2011.33

DO - http://dx.doi.org/10.1109/3DIMPVT.2011.33

M3 - Conference contribution

T3 - 3DIMPVT '11

SP - 204

EP - 211

BT - Proceedings of the 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission

PB - IEEE Computer Society

CY - Washington, DC, USA

ER -

Automatic Keypoint Detection on 3D Faces Using a Dictionary of Local Shapes

Abstract

Publication series

Keywords

Access to Document

Other files and links

Cite this