Determining correspondences for statistical models of facial appearance

K. N. Walker; T. F. Cootes; C. J. Taylor

doi:10.1109/AFGR.2000.840646

Determining correspondences for statistical models of facial appearance

K. N. Walker, T. F. Cootes, C. J. Taylor

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

Abstract

In order to build a statistical model of facial appearance we require a set of images, each with a consistent set of landmarks. We address the problem of automatically placing a set of landmarks to define the correspondences across an image set. We can estimate correspondences between any pair of images by locating salient points on one and finding their corresponding position in the second. However, we wish to determine a globally consistent set of correspondences across all the images. We present an iterative scheme in which these pairwise correspondences are used to determine a global correspondence across the entire set. We show results on several training sets, and demonstrate that an appearance model trained on the correspondences is of higher quality than one built from hand-marked images. © 2000 IEEE.

Original language	English
Title of host publication	Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000\|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG
Publisher	IEEE Computer Society
Pages	271-276
Number of pages	5
ISBN (Print)	0769505805, 9780769505800
DOIs	https://doi.org/10.1109/AFGR.2000.840646
Publication status	Published - 2000
Event	4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000 - Grenoble Duration: 1 Jul 2000 → …

Conference

Conference	4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000
City	Grenoble
Period	1/07/00 → …

Keywords

Peer Reviewed Conference

Access to Document

10.1109/AFGR.2000.840646

Cite this

@inproceedings{1d3df84fa0824e14bf6382e5a0e1a75e,

title = "Determining correspondences for statistical models of facial appearance",

abstract = "In order to build a statistical model of facial appearance we require a set of images, each with a consistent set of landmarks. We address the problem of automatically placing a set of landmarks to define the correspondences across an image set. We can estimate correspondences between any pair of images by locating salient points on one and finding their corresponding position in the second. However, we wish to determine a globally consistent set of correspondences across all the images. We present an iterative scheme in which these pairwise correspondences are used to determine a global correspondence across the entire set. We show results on several training sets, and demonstrate that an appearance model trained on the correspondences is of higher quality than one built from hand-marked images. {\textcopyright} 2000 IEEE.",

keywords = "Peer Reviewed Conference",

author = "Walker, {K. N.} and Cootes, {T. F.} and Taylor, {C. J.}",

year = "2000",

doi = "10.1109/AFGR.2000.840646",

language = "English",

isbn = "0769505805",

pages = "271--276",

booktitle = "Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG",

publisher = "IEEE Computer Society ",

address = "United States",

note = "4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000 ; Conference date: 01-07-2000",

}

Walker, KN, Cootes, TF & Taylor, CJ 2000, Determining correspondences for statistical models of facial appearance. in Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG. IEEE Computer Society , pp. 271-276, 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000, Grenoble, 1/07/00. https://doi.org/10.1109/AFGR.2000.840646

Determining correspondences for statistical models of facial appearance. / Walker, K. N.; Cootes, T. F.; Taylor, C. J.
Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG. IEEE Computer Society , 2000. p. 271-276.

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

TY - GEN

T1 - Determining correspondences for statistical models of facial appearance

AU - Walker, K. N.

AU - Cootes, T. F.

AU - Taylor, C. J.

PY - 2000

Y1 - 2000

N2 - In order to build a statistical model of facial appearance we require a set of images, each with a consistent set of landmarks. We address the problem of automatically placing a set of landmarks to define the correspondences across an image set. We can estimate correspondences between any pair of images by locating salient points on one and finding their corresponding position in the second. However, we wish to determine a globally consistent set of correspondences across all the images. We present an iterative scheme in which these pairwise correspondences are used to determine a global correspondence across the entire set. We show results on several training sets, and demonstrate that an appearance model trained on the correspondences is of higher quality than one built from hand-marked images. © 2000 IEEE.

AB - In order to build a statistical model of facial appearance we require a set of images, each with a consistent set of landmarks. We address the problem of automatically placing a set of landmarks to define the correspondences across an image set. We can estimate correspondences between any pair of images by locating salient points on one and finding their corresponding position in the second. However, we wish to determine a globally consistent set of correspondences across all the images. We present an iterative scheme in which these pairwise correspondences are used to determine a global correspondence across the entire set. We show results on several training sets, and demonstrate that an appearance model trained on the correspondences is of higher quality than one built from hand-marked images. © 2000 IEEE.

KW - Peer Reviewed Conference

U2 - 10.1109/AFGR.2000.840646

DO - 10.1109/AFGR.2000.840646

M3 - Conference contribution

SN - 0769505805

SN - 9780769505800

SP - 271

EP - 276

BT - Proceedings - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG

PB - IEEE Computer Society

T2 - 4th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2000

Y2 - 1 July 2000

ER -

Determining correspondences for statistical models of facial appearance

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this