Facial gender classification using shape from shading and weighted principal geodesic analysis

Wu, Jing ORCID: https://orcid.org/0000-0001-5123-9861, Smith, W. A. P. and Hancock, E. R. 2008. Facial gender classification using shape from shading and weighted principal geodesic analysis. Presented at: 5th International Conference, ICIAR 2008, Póvoa de Varzim, Portugal, 25-27 June 2008. Published in: Campilho, A. and Kamel, M. eds. Image Analysis and Recognition: 5th International Conference, ICIAR 2008, Póvoa de Varzim, Portugal, June 25-27, 2008. Proceedings. Lecture Notes in Computer Science (5112) Berlin Heidelberg: Springer, pp. 925-934. 10.1007/978-3-540-69812-8_92

Full text not available from this repository.

Abstract

In this paper, we investigate gender classification based on 2.5D facial surface normals (facial needle-maps) which can be recovered from 2D intensity images using a non-lambertian Shape-from-shading (SFS) method. We also describe a weighted principal geodesic analysis (WPGA) method to extract features from facial surface normals. By incorporating the weight matrix into principal geodesic analysis (PGA), we control the obtained principal variance axes to be in the direction of the variance on gender information. For classification, an a posteriori probability based method is adopted. Experimental results confirms that using WPGA increases the gender discriminating power in the leading eigenvectors, and also demonstrates the feasibility of gender classification based on facial shape information.

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:	9783540698111
ISSN:	0302-9743
Last Modified:	01 Nov 2022 10:00
URI:	https://orca.cardiff.ac.uk/id/eprint/89869

Citation Data

Cited 9 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item