Automatic features characterization from 3d facial images.

Elyan, Eyad; Ugail, Hassan

Abstract

This paper presents a novel and computationally fast method for automatic identification of symmetry profile from 3D facial images. The algorithm is based on the concepts of computational geometry which yield fast and accurate results. In order to detect the symmetry profile of a human face, the tip of the nose is identified first. Assuming that the symmetry plane passes through the tip of the nose, the symmetry profile is then extracted. This is undertaken by means of computing the intersection between the symmetry plane and the facial mesh, resulting in a planner curve that accurately represents the symmetry profile. Experimentation using two different 3D face databases was carried out, resulting in fast and accurate results.

Citation

ELYAN, E. and UGAIL, H. 2010. Automatic features characterization from 3d facial images. In Arabnia, H.R., Deligiannidis, L. and Solo, A.M.G. (eds.) Proceedings of the 14th International computer graphics and virtual reality conference (CGVR 2010), 12-15 July 2010, Las Vegas, USA. Georgia, USA: CSREA Press, pages 67-73.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 14th International computer graphics and virtual reality conference (CGVR 2010)
• Start Date: Jul 12, 2010
• End Date: Jul 15, 2010
• Acceptance Date: Mar 25, 2010
• Publication Date: Jul 15, 2010
• Deposit Date: Oct 11, 2016
• Publicly Available Date: Oct 11, 2016
• Publisher: CSREA Press Inc
• Peer Reviewed: Peer Reviewed
• Pages: 67-73
• ISBN: 1601321368
• Keywords: 3D images; Features extraction; Facial symmetry; Computational geometry
• Public URL: http://hdl.handle.net/10059/1885
• Contract Date: Oct 11, 2016