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

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