Active Morphable Model: An efficient method for face analysis

Xun Xu, Changshui Zhang, Thomas S Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Multidimensional Morphable Model is a powerful model to analyze and synthesize human faces. However, the stochastic gradient descent algorithm adopted to match the Morphable Model to a novel face image is not efficient enough. In this paper, a very efficient optimization method devised for Morphable Model matching is proposed, called Active Morphable Model (AMM). The kernel of AMM is an iterative algorithm directly utilizing the heuristic information provided by the novel image, and updating the model parameters in a computationally economic fashion. AMM is more efficient than general optimization methods in matching a Morphable Model, it has much higher convergent rate and matching speed. Furthermore, it is insensitive to the initial estimation of the face pose, and is robust when used to match novel faces with large variations in translation, rotation and scaling. Experimental results are given to validate the efficiency and robustness of the proposed method.

Original languageEnglish (US)
Title of host publicationProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004
Pages837-842
Number of pages6
StatePublished - Sep 24 2004
EventProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 - Seoul, Korea, Republic of
Duration: May 17 2004May 19 2004

Publication series

NameProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition

Other

OtherProceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004
CountryKorea, Republic of
CitySeoul
Period5/17/045/19/04

Fingerprint

Economics

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Xu, X., Zhang, C., & Huang, T. S. (2004). Active Morphable Model: An efficient method for face analysis. In Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004 (pp. 837-842). (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition).

Active Morphable Model : An efficient method for face analysis. / Xu, Xun; Zhang, Changshui; Huang, Thomas S.

Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. 2004. p. 837-842 (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xu, X, Zhang, C & Huang, TS 2004, Active Morphable Model: An efficient method for face analysis. in Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 837-842, Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004, Seoul, Korea, Republic of, 5/17/04.
Xu X, Zhang C, Huang TS. Active Morphable Model: An efficient method for face analysis. In Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. 2004. p. 837-842. (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition).
Xu, Xun ; Zhang, Changshui ; Huang, Thomas S. / Active Morphable Model : An efficient method for face analysis. Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004. 2004. pp. 837-842 (Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition).
@inproceedings{3ff0d764130841dead60bef99ee2b18c,
title = "Active Morphable Model: An efficient method for face analysis",
abstract = "Multidimensional Morphable Model is a powerful model to analyze and synthesize human faces. However, the stochastic gradient descent algorithm adopted to match the Morphable Model to a novel face image is not efficient enough. In this paper, a very efficient optimization method devised for Morphable Model matching is proposed, called Active Morphable Model (AMM). The kernel of AMM is an iterative algorithm directly utilizing the heuristic information provided by the novel image, and updating the model parameters in a computationally economic fashion. AMM is more efficient than general optimization methods in matching a Morphable Model, it has much higher convergent rate and matching speed. Furthermore, it is insensitive to the initial estimation of the face pose, and is robust when used to match novel faces with large variations in translation, rotation and scaling. Experimental results are given to validate the efficiency and robustness of the proposed method.",
author = "Xun Xu and Changshui Zhang and Huang, {Thomas S}",
year = "2004",
month = "9",
day = "24",
language = "English (US)",
isbn = "0769521223",
series = "Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition",
pages = "837--842",
booktitle = "Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004",

}

TY - GEN

T1 - Active Morphable Model

T2 - An efficient method for face analysis

AU - Xu, Xun

AU - Zhang, Changshui

AU - Huang, Thomas S

PY - 2004/9/24

Y1 - 2004/9/24

N2 - Multidimensional Morphable Model is a powerful model to analyze and synthesize human faces. However, the stochastic gradient descent algorithm adopted to match the Morphable Model to a novel face image is not efficient enough. In this paper, a very efficient optimization method devised for Morphable Model matching is proposed, called Active Morphable Model (AMM). The kernel of AMM is an iterative algorithm directly utilizing the heuristic information provided by the novel image, and updating the model parameters in a computationally economic fashion. AMM is more efficient than general optimization methods in matching a Morphable Model, it has much higher convergent rate and matching speed. Furthermore, it is insensitive to the initial estimation of the face pose, and is robust when used to match novel faces with large variations in translation, rotation and scaling. Experimental results are given to validate the efficiency and robustness of the proposed method.

AB - Multidimensional Morphable Model is a powerful model to analyze and synthesize human faces. However, the stochastic gradient descent algorithm adopted to match the Morphable Model to a novel face image is not efficient enough. In this paper, a very efficient optimization method devised for Morphable Model matching is proposed, called Active Morphable Model (AMM). The kernel of AMM is an iterative algorithm directly utilizing the heuristic information provided by the novel image, and updating the model parameters in a computationally economic fashion. AMM is more efficient than general optimization methods in matching a Morphable Model, it has much higher convergent rate and matching speed. Furthermore, it is insensitive to the initial estimation of the face pose, and is robust when used to match novel faces with large variations in translation, rotation and scaling. Experimental results are given to validate the efficiency and robustness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=4544357321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544357321&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:4544357321

SN - 0769521223

T3 - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition

SP - 837

EP - 842

BT - Proceedings - Sixth IEEE International Conference on Automatic Face and Gesture Recognition FGR 2004

ER -