Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Supervised principal geodesic analysis on facial surface normals for gender classification

Wu, Jing, Smith, W. A. P. and Hancock, E. R. 2008. Supervised principal geodesic analysis on facial surface normals for gender classification. Presented at: Structural, Syntactic, and Statistical Pattern Recognition Joint IAPR International Workshop, SSPR & SPR 2008, Orlando, USA, 4-6 December 2008. Published in: da Vitoria Lobo, N., Kasparis, T., Georgiopoulos, M., Roli, F., Kwok, J., Anagnostopoulos, G. C. and Loog, M. eds. Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshop, SSPR & SPR 2008, Orlando, USA, December 4-6, 2008. Proceedings. Lecture Notes in Computer Science , vol. 5342. Berlin Heidelberg: Springer, pp. 664-673. 10.1007/978-3-540-89689-0_70

Full text not available from this repository.

Abstract

In this paper, we perform gender classification based on facial surface normals (facial needle-maps). We improve our previous work in [6] by using a non-Lambertian Shape-from-Shading (SFS) method to recover the surface normals, and develop a novel supervised principal geodesic analysis (PGA) to parameterize the facial needle-maps. Experimental results demonstrate the feasibility of gender classification based on facial needle-maps, and shows that incorporating pairwise relationships between the labeled data improves the gender discriminating powers in the leading PGA eigenvectors and gender classification accuracy.

Item Type: Conference or Workshop Item (Paper)
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher: Springer
ISBN: 9783540896883
ISSN: 0302-9743
Last Modified: 04 Jun 2017 09:03
URI: http://orca.cf.ac.uk/id/eprint/89866

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item