View-based active appearance models

被引：157

作者：

Cootes, TF

Wheeler, GV

Walker, KN

Taylor, CJ

机构：

[1] Univ Manchester, Div Imaging Sci & Biomed Engn, Manchester M13 9PT, Lancs, England

[2] Image Petr PLC, Stockport SK4 3LE, Lancs, England

来源：

IMAGE AND VISION COMPUTING | 2002年 / 20卷 / 9-10期

关键词：

appearance models; view-based models; active appearance models;

D O I：

10.1016/S0262-8856(02)00055-0

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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. (C) 2002 Elsevier Science B.V. All rights reserved.

引用

页码：657 / 664

页数：8

共 23 条

[1]

Cootes T., 1998, Proc. ECCV, V2, P484

[2]

DAVIES R, 2001, 17 C INF PROC MED IM, P50

[3] Interpreting face images using Active Appearance Models [J].

Edwards, GJ ;

Taylor, CJ ;

Cootes, TF .

AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS, 1998, :300-305

[4]

FUA P, 1998, 5 EUR C COMP VIS SPR, V1, P188

[5] Face recognition from unfamiliar views: Subspace methods and pose dependency [J].

Graham, DB ;

Allinson, NM .

AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS, 1998, :348-353

[6] Multidimensional morphable models: A framework for representing and matching object classes [J].

Jones, MJ ;

Poggio, T .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 1998, 29 (02) :107-131

[7] An algorithm for the learning of weights in discrimination functions using a priori constraints [J].

Kruger, N .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (07) :764-768

[8]

KWONG J, 1999, 10 BRIT MACH VIS C, V2, P503

[9] Fast, reliable head tracking under varying illumination: An approach based on registration of texture-mapped 3D models [J].

La Cascia, M ;

Sclaroff, S ;

Athitsos, V .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (04) :322-336

[10] Automatic interpretation and coding of face images using flexible models [J].

Lanitis, A ;

Taylor, CJ ;

Cootes, TF .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1997, 19 (07) :743-756

← 1 2 3 →