View-based active appearance models

T. F. Cootes; G. V. Wheeler; K. N. Walker; C. J. Taylor

doi:10.1016/S0262-8856(02)00055-0

View-based active appearance models

T. F. Cootes, G. V. Wheeler, K. N. Walker, C. J. Taylor

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

Abstract

We demonstrate that a small number of 2D linear statistical models are sufficient to capture the shape and appearance of a face from a wide range of viewpoints. Such models can be used to estimate head orientation and track faces through large angles. Given multiple images of the same face we can learn a coupled model describing the relationship between the frontal appearance and the profile of a face. This relationship can be used to predict new views of a face seen from one view and to constrain search algorithms which seek to locate a face in multiple views simultaneously. © 2002 Elsevier Science B.V. All rights reserved.

Original language	English
Pages (from-to)	657-664
Number of pages	7
Journal	Image and Vision Computing
Volume	20
Issue number	9-10
DOIs	https://doi.org/10.1016/S0262-8856(02)00055-0
Publication status	Published - 1 Aug 2002

Keywords

Active appearance models
Appearance models
View-based models

Access to Document

10.1016/S0262-8856(02)00055-0

Cite this

@article{c9358ed31c4e4f96960dc0639327e091,

title = "View-based active appearance models",

abstract = "We demonstrate that a small number of 2D linear statistical models are sufficient to capture the shape and appearance of a face from a wide range of viewpoints. Such models can be used to estimate head orientation and track faces through large angles. Given multiple images of the same face we can learn a coupled model describing the relationship between the frontal appearance and the profile of a face. This relationship can be used to predict new views of a face seen from one view and to constrain search algorithms which seek to locate a face in multiple views simultaneously. {\textcopyright} 2002 Elsevier Science B.V. All rights reserved.",

keywords = "Active appearance models, Appearance models, View-based models",

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

year = "2002",

month = aug,

day = "1",

doi = "10.1016/S0262-8856(02)00055-0",

language = "English",

volume = "20",

pages = "657--664",

journal = "Image and Vision Computing",

issn = "0262-8856",

publisher = "Elsevier BV",

number = "9-10",

}

TY - JOUR

T1 - View-based active appearance models

AU - Cootes, T. F.

AU - Wheeler, G. V.

AU - Walker, K. N.

AU - Taylor, C. J.

PY - 2002/8/1

Y1 - 2002/8/1

N2 - We demonstrate that a small number of 2D linear statistical models are sufficient to capture the shape and appearance of a face from a wide range of viewpoints. Such models can be used to estimate head orientation and track faces through large angles. Given multiple images of the same face we can learn a coupled model describing the relationship between the frontal appearance and the profile of a face. This relationship can be used to predict new views of a face seen from one view and to constrain search algorithms which seek to locate a face in multiple views simultaneously. © 2002 Elsevier Science B.V. All rights reserved.

AB - We demonstrate that a small number of 2D linear statistical models are sufficient to capture the shape and appearance of a face from a wide range of viewpoints. Such models can be used to estimate head orientation and track faces through large angles. Given multiple images of the same face we can learn a coupled model describing the relationship between the frontal appearance and the profile of a face. This relationship can be used to predict new views of a face seen from one view and to constrain search algorithms which seek to locate a face in multiple views simultaneously. © 2002 Elsevier Science B.V. All rights reserved.

KW - Active appearance models

KW - Appearance models

KW - View-based models

U2 - 10.1016/S0262-8856(02)00055-0

DO - 10.1016/S0262-8856(02)00055-0

M3 - Article

SN - 0262-8856

VL - 20

SP - 657

EP - 664

JO - Image and Vision Computing

JF - Image and Vision Computing

IS - 9-10

ER -

View-based active appearance models

Abstract

Keywords

Access to Document

Fingerprint

Cite this