Face Alignment Using Boosting and Evolutionary Search

Hua Zhang, Duanduan Liu, Mannes Poel, Antinus Nijholt

  • 1 Citations

Abstract

In this paper, we present a face alignment approach using granular features, boosting, and an evolutionary search algorithm. Active Appearance Models (AAM) integrate a shape-texture-combined morphable face model into an efficient fitting strategy, then Boosting Appearance Models (BAM) consider the face alignment problem as a process of maximizing the response from a boosting classifier. Enlightened by AAM and BAM, we present a framework which implements improved boosting classifiers based on more discriminative features and exhaustive search strategies. In this paper, we utilize granular features to replace the conventional rectangular Haar-like features, to improve discriminability, computational efficiency, and a larger search space. At the same time, we adopt the evolutionary search process to solve the deficiency of searching in the large feature space. Finally, we test our approach on a series of challenging data sets, to show the accuracy and efficiency on versatile face images.
Original languageUndefined
Title of host publicationNinth Asian Conference on Computer Vision (ACCV 2009). Part II
EditorsH. Zha, R.-I. Taniguchi, S. Maybank
Place of PublicationBerlin
PublisherSpringer Verlag
Pages110-119
Number of pages10
ISBN (Print)978-3-642-12303-0
DOIs
StatePublished - 25 Apr 2010
Event9th Asian Conference on Computer Vision, ACCV 2009 - Xi'an, China

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume5995

Conference

Conference9th Asian Conference on Computer Vision, ACCV 2009
Abbreviated titleACCV
CountryChina
CityXi'an
Period23/09/0927/09/09

Fingerprint

Classifiers
Computational efficiency
Textures

Keywords

  • METIS-270691
  • IR-71163
  • evolutionary search
  • Face alignment
  • EWI-16061
  • granular features
  • boosting appearance models
  • HMI-MI: MULTIMODAL INTERACTIONS
  • EC Grant Agreement nr.: FP6/033812

Cite this

Zhang, H., Liu, D., Poel, M., & Nijholt, A. (2010). Face Alignment Using Boosting and Evolutionary Search. In H. Zha, R-I. Taniguchi, & S. Maybank (Eds.), Ninth Asian Conference on Computer Vision (ACCV 2009). Part II (pp. 110-119). (Lecture Notes in Computer Science; Vol. 5995). Berlin: Springer Verlag. DOI: 10.1007/978-3-642-12304-7_11

Zhang, Hua; Liu, Duanduan; Poel, Mannes; Nijholt, Antinus / Face Alignment Using Boosting and Evolutionary Search.

Ninth Asian Conference on Computer Vision (ACCV 2009). Part II. ed. / H. Zha; R.-I. Taniguchi; S. Maybank. Berlin : Springer Verlag, 2010. p. 110-119 (Lecture Notes in Computer Science; Vol. 5995).

Research output: Scientific - peer-reviewConference contribution

@inbook{a7f9fa59e9e54db793edee1ad5d76522,
title = "Face Alignment Using Boosting and Evolutionary Search",
abstract = "In this paper, we present a face alignment approach using granular features, boosting, and an evolutionary search algorithm. Active Appearance Models (AAM) integrate a shape-texture-combined morphable face model into an efficient fitting strategy, then Boosting Appearance Models (BAM) consider the face alignment problem as a process of maximizing the response from a boosting classifier. Enlightened by AAM and BAM, we present a framework which implements improved boosting classifiers based on more discriminative features and exhaustive search strategies. In this paper, we utilize granular features to replace the conventional rectangular Haar-like features, to improve discriminability, computational efficiency, and a larger search space. At the same time, we adopt the evolutionary search process to solve the deficiency of searching in the large feature space. Finally, we test our approach on a series of challenging data sets, to show the accuracy and efficiency on versatile face images.",
keywords = "METIS-270691, IR-71163, evolutionary search, Face alignment, EWI-16061, granular features, boosting appearance models, HMI-MI: MULTIMODAL INTERACTIONS, EC Grant Agreement nr.: FP6/033812",
author = "Hua Zhang and Duanduan Liu and Mannes Poel and Antinus Nijholt",
note = "10.1007/978-3-642-12304-7_11",
year = "2010",
month = "4",
doi = "10.1007/978-3-642-12304-7_11",
isbn = "978-3-642-12303-0",
series = "Lecture Notes in Computer Science",
publisher = "Springer Verlag",
pages = "110--119",
editor = "H. Zha and R.-I. Taniguchi and S. Maybank",
booktitle = "Ninth Asian Conference on Computer Vision (ACCV 2009). Part II",

}

Zhang, H, Liu, D, Poel, M & Nijholt, A 2010, Face Alignment Using Boosting and Evolutionary Search. in H Zha, R-I Taniguchi & S Maybank (eds), Ninth Asian Conference on Computer Vision (ACCV 2009). Part II. Lecture Notes in Computer Science, vol. 5995, Springer Verlag, Berlin, pp. 110-119, 9th Asian Conference on Computer Vision, ACCV 2009, Xi'an, China, 23-27 September. DOI: 10.1007/978-3-642-12304-7_11

Face Alignment Using Boosting and Evolutionary Search. / Zhang, Hua; Liu, Duanduan; Poel, Mannes; Nijholt, Antinus.

Ninth Asian Conference on Computer Vision (ACCV 2009). Part II. ed. / H. Zha; R.-I. Taniguchi; S. Maybank. Berlin : Springer Verlag, 2010. p. 110-119 (Lecture Notes in Computer Science; Vol. 5995).

Research output: Scientific - peer-reviewConference contribution

TY - CHAP

T1 - Face Alignment Using Boosting and Evolutionary Search

AU - Zhang,Hua

AU - Liu,Duanduan

AU - Poel,Mannes

AU - Nijholt,Antinus

N1 - 10.1007/978-3-642-12304-7_11

PY - 2010/4/25

Y1 - 2010/4/25

N2 - In this paper, we present a face alignment approach using granular features, boosting, and an evolutionary search algorithm. Active Appearance Models (AAM) integrate a shape-texture-combined morphable face model into an efficient fitting strategy, then Boosting Appearance Models (BAM) consider the face alignment problem as a process of maximizing the response from a boosting classifier. Enlightened by AAM and BAM, we present a framework which implements improved boosting classifiers based on more discriminative features and exhaustive search strategies. In this paper, we utilize granular features to replace the conventional rectangular Haar-like features, to improve discriminability, computational efficiency, and a larger search space. At the same time, we adopt the evolutionary search process to solve the deficiency of searching in the large feature space. Finally, we test our approach on a series of challenging data sets, to show the accuracy and efficiency on versatile face images.

AB - In this paper, we present a face alignment approach using granular features, boosting, and an evolutionary search algorithm. Active Appearance Models (AAM) integrate a shape-texture-combined morphable face model into an efficient fitting strategy, then Boosting Appearance Models (BAM) consider the face alignment problem as a process of maximizing the response from a boosting classifier. Enlightened by AAM and BAM, we present a framework which implements improved boosting classifiers based on more discriminative features and exhaustive search strategies. In this paper, we utilize granular features to replace the conventional rectangular Haar-like features, to improve discriminability, computational efficiency, and a larger search space. At the same time, we adopt the evolutionary search process to solve the deficiency of searching in the large feature space. Finally, we test our approach on a series of challenging data sets, to show the accuracy and efficiency on versatile face images.

KW - METIS-270691

KW - IR-71163

KW - evolutionary search

KW - Face alignment

KW - EWI-16061

KW - granular features

KW - boosting appearance models

KW - HMI-MI: MULTIMODAL INTERACTIONS

KW - EC Grant Agreement nr.: FP6/033812

U2 - 10.1007/978-3-642-12304-7_11

DO - 10.1007/978-3-642-12304-7_11

M3 - Conference contribution

SN - 978-3-642-12303-0

T3 - Lecture Notes in Computer Science

SP - 110

EP - 119

BT - Ninth Asian Conference on Computer Vision (ACCV 2009). Part II

PB - Springer Verlag

ER -

Zhang H, Liu D, Poel M, Nijholt A. Face Alignment Using Boosting and Evolutionary Search. In Zha H, Taniguchi R-I, Maybank S, editors, Ninth Asian Conference on Computer Vision (ACCV 2009). Part II. Berlin: Springer Verlag. 2010. p. 110-119. (Lecture Notes in Computer Science). Available from, DOI: 10.1007/978-3-642-12304-7_11