Discriminant feature manifold for facial aging estimation

Hui Fang, Phil Grant, Min Chen

Research output: Contribution to conferencePoster

5 Citations (Scopus)

Abstract

Computerised facial aging estimation, which has the potential for many applications in human-computer interactions, has been investigated by many computer vision researchers in recent years. In this paper, a feature-based discriminant subspace is proposed to extract more discriminating and robust representations for aging estimation. After aligning all the faces by a piece-wise affine transform, orthogonal locality preserving projection (OLPP) is employed to project local binary patterns (LBP) from the faces into an age-discriminant subspace. The feature extracted from this manifold is more distinctive for age estimation compared with the features using in the state-of-the-art methods. Based on the public database FG-NET, the performance of the proposed feature is evaluated by using two different regression techniques, quadratic function and neural-network regression. The proposed feature subspace achieves the best performance based on both types of regression.
Original languageEnglish
Pages593-596
DOIs
Publication statusPublished - 2010
EventInternational Conference on Pattern Recognition - Istanbul, Turkey
Duration: 1 Jan 2010 → …

Conference

ConferenceInternational Conference on Pattern Recognition
CountryTurkey
CityIstanbul
Period1/01/10 → …

Fingerprint

Aging of materials
Affine transforms
Human computer interaction
Computer vision
Neural networks

Cite this

Fang, H., Grant, P., & Chen, M. (2010). Discriminant feature manifold for facial aging estimation. 593-596. Poster session presented at International Conference on Pattern Recognition, Istanbul, Turkey. https://doi.org/10.1109/ICPR.2010.150
Fang, Hui ; Grant, Phil ; Chen, Min. / Discriminant feature manifold for facial aging estimation. Poster session presented at International Conference on Pattern Recognition, Istanbul, Turkey.
@conference{39eda396747a431bbd1fbfa8e24682fc,
title = "Discriminant feature manifold for facial aging estimation",
abstract = "Computerised facial aging estimation, which has the potential for many applications in human-computer interactions, has been investigated by many computer vision researchers in recent years. In this paper, a feature-based discriminant subspace is proposed to extract more discriminating and robust representations for aging estimation. After aligning all the faces by a piece-wise affine transform, orthogonal locality preserving projection (OLPP) is employed to project local binary patterns (LBP) from the faces into an age-discriminant subspace. The feature extracted from this manifold is more distinctive for age estimation compared with the features using in the state-of-the-art methods. Based on the public database FG-NET, the performance of the proposed feature is evaluated by using two different regression techniques, quadratic function and neural-network regression. The proposed feature subspace achieves the best performance based on both types of regression.",
author = "Hui Fang and Phil Grant and Min Chen",
year = "2010",
doi = "10.1109/ICPR.2010.150",
language = "English",
pages = "593--596",
note = "International Conference on Pattern Recognition ; Conference date: 01-01-2010",

}

Fang, H, Grant, P & Chen, M 2010, 'Discriminant feature manifold for facial aging estimation' International Conference on Pattern Recognition, Istanbul, Turkey, 1/01/10, pp. 593-596. https://doi.org/10.1109/ICPR.2010.150

Discriminant feature manifold for facial aging estimation. / Fang, Hui; Grant, Phil; Chen, Min.

2010. 593-596 Poster session presented at International Conference on Pattern Recognition, Istanbul, Turkey.

Research output: Contribution to conferencePoster

TY - CONF

T1 - Discriminant feature manifold for facial aging estimation

AU - Fang, Hui

AU - Grant, Phil

AU - Chen, Min

PY - 2010

Y1 - 2010

N2 - Computerised facial aging estimation, which has the potential for many applications in human-computer interactions, has been investigated by many computer vision researchers in recent years. In this paper, a feature-based discriminant subspace is proposed to extract more discriminating and robust representations for aging estimation. After aligning all the faces by a piece-wise affine transform, orthogonal locality preserving projection (OLPP) is employed to project local binary patterns (LBP) from the faces into an age-discriminant subspace. The feature extracted from this manifold is more distinctive for age estimation compared with the features using in the state-of-the-art methods. Based on the public database FG-NET, the performance of the proposed feature is evaluated by using two different regression techniques, quadratic function and neural-network regression. The proposed feature subspace achieves the best performance based on both types of regression.

AB - Computerised facial aging estimation, which has the potential for many applications in human-computer interactions, has been investigated by many computer vision researchers in recent years. In this paper, a feature-based discriminant subspace is proposed to extract more discriminating and robust representations for aging estimation. After aligning all the faces by a piece-wise affine transform, orthogonal locality preserving projection (OLPP) is employed to project local binary patterns (LBP) from the faces into an age-discriminant subspace. The feature extracted from this manifold is more distinctive for age estimation compared with the features using in the state-of-the-art methods. Based on the public database FG-NET, the performance of the proposed feature is evaluated by using two different regression techniques, quadratic function and neural-network regression. The proposed feature subspace achieves the best performance based on both types of regression.

U2 - 10.1109/ICPR.2010.150

DO - 10.1109/ICPR.2010.150

M3 - Poster

SP - 593

EP - 596

ER -

Fang H, Grant P, Chen M. Discriminant feature manifold for facial aging estimation. 2010. Poster session presented at International Conference on Pattern Recognition, Istanbul, Turkey. https://doi.org/10.1109/ICPR.2010.150