Interpreting face images using active appearance models

G. J. Edwards; C. J. Taylor; T. F. Cootes

doi:10.1109/AFGR.1998.670965

Interpreting face images using active appearance models

G. J. Edwards, C. J. Taylor, T. F. Cootes

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

Abstract

We demonstrate a fast, robust method of interpreting face images using an Active Appearance Model (AAM). An AAM contains a statistical model of shape and grey level appearance which can generalise to almost any face. Matching to an image involves finding model parameters which minimise the difference between the image and a synthesised face. We observe that displacing each model parameter from the correct value induces a particular pattern in the residuals. In a training phase, the AAM learns a linear model of the correlation between parameter displacements and the induced residuals. During search it measures the residuals and uses this model to correct the current parameters, leading to a better fit. A good overall match is obtained in a few iterations, even from poor starting estimates. We describe the technique in detail and show it matching to new face images. © 1998 IEEE.

Original language	English
Title of host publication	Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998\|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG
Place of Publication	Berlin
Publisher	IEEE Computer Society
Pages	300-305
Number of pages	5
ISBN (Print)	0818683449, 9780818683442
DOIs	https://doi.org/10.1109/AFGR.1998.670965
Publication status	Published - 1998
Event	3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 - Nara Duration: 1 Jul 1998 → …

Conference

Conference	3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
City	Nara
Period	1/07/98 → …

Keywords

Peer Reviewed Conference

Access to Document

10.1109/AFGR.1998.670965

Cite this

@inproceedings{43cfadedea4f40359c137e1246e79c17,

title = "Interpreting face images using active appearance models",

abstract = "We demonstrate a fast, robust method of interpreting face images using an Active Appearance Model (AAM). An AAM contains a statistical model of shape and grey level appearance which can generalise to almost any face. Matching to an image involves finding model parameters which minimise the difference between the image and a synthesised face. We observe that displacing each model parameter from the correct value induces a particular pattern in the residuals. In a training phase, the AAM learns a linear model of the correlation between parameter displacements and the induced residuals. During search it measures the residuals and uses this model to correct the current parameters, leading to a better fit. A good overall match is obtained in a few iterations, even from poor starting estimates. We describe the technique in detail and show it matching to new face images. {\textcopyright} 1998 IEEE.",

keywords = "Peer Reviewed Conference",

author = "Edwards, {G. J.} and Taylor, {C. J.} and Cootes, {T. F.}",

year = "1998",

doi = "10.1109/AFGR.1998.670965",

language = "English",

isbn = "0818683449",

pages = "300--305",

booktitle = "Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG",

publisher = "IEEE Computer Society ",

address = "United States",

note = "3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 ; Conference date: 01-07-1998",

}

Edwards, GJ, Taylor, CJ & Cootes, TF 1998, Interpreting face images using active appearance models. in Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG. IEEE Computer Society , Berlin, pp. 300-305, 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998, Nara, 1/07/98. https://doi.org/10.1109/AFGR.1998.670965

Interpreting face images using active appearance models. / Edwards, G. J.; Taylor, C. J.; Cootes, T. F.
Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG. Berlin: IEEE Computer Society , 1998. p. 300-305.

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

TY - GEN

T1 - Interpreting face images using active appearance models

AU - Edwards, G. J.

AU - Taylor, C. J.

AU - Cootes, T. F.

PY - 1998

Y1 - 1998

N2 - We demonstrate a fast, robust method of interpreting face images using an Active Appearance Model (AAM). An AAM contains a statistical model of shape and grey level appearance which can generalise to almost any face. Matching to an image involves finding model parameters which minimise the difference between the image and a synthesised face. We observe that displacing each model parameter from the correct value induces a particular pattern in the residuals. In a training phase, the AAM learns a linear model of the correlation between parameter displacements and the induced residuals. During search it measures the residuals and uses this model to correct the current parameters, leading to a better fit. A good overall match is obtained in a few iterations, even from poor starting estimates. We describe the technique in detail and show it matching to new face images. © 1998 IEEE.

AB - We demonstrate a fast, robust method of interpreting face images using an Active Appearance Model (AAM). An AAM contains a statistical model of shape and grey level appearance which can generalise to almost any face. Matching to an image involves finding model parameters which minimise the difference between the image and a synthesised face. We observe that displacing each model parameter from the correct value induces a particular pattern in the residuals. In a training phase, the AAM learns a linear model of the correlation between parameter displacements and the induced residuals. During search it measures the residuals and uses this model to correct the current parameters, leading to a better fit. A good overall match is obtained in a few iterations, even from poor starting estimates. We describe the technique in detail and show it matching to new face images. © 1998 IEEE.

KW - Peer Reviewed Conference

U2 - 10.1109/AFGR.1998.670965

DO - 10.1109/AFGR.1998.670965

M3 - Conference contribution

SN - 0818683449

SN - 9780818683442

SP - 300

EP - 305

BT - Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998|Proc. - IEEE Int. Conf. Autom. Face Gesture Recogn., FG

PB - IEEE Computer Society

CY - Berlin

T2 - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998

Y2 - 1 July 1998

ER -

Interpreting face images using active appearance models

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this