Skip to Main content Skip to Navigation
Journal articles

An Intrinsic Framework for Analysis of Facial Surfaces

Abstract : A quantitative analysis of shapes of facial surfaces can play an important role in biometric authentication. The main difficulty in comparing shapes of surfaces is the lack of a canonical system to represent all surfaces. This paper overcomes that problem by proposing a specific coordinate system, on facial surfaces, that enables comparisons of geometries of faces. In this system, a facial surface is represented as a path on the space of closed curves, called facial curves, where each curve is a level curve of distance function from the tip of the nose. Defining H to be the space of paths on the space of closed curves, the paper studies the differential geometry of H and endows it with a Riemannian. Using numerical techniques, it computes geodesic paths between elements of H that represent individual facial surfaces. This Riemannian analysis of faces is then used to: (i) find an optimal deformation from one face to another, (ii) define and compute an average face for a given set of faces, and (iii) compute distances between faces to quantify differences in their shapes. Experimental results are presented to demonstrate and support these ideas.
Document type :
Journal articles
Complete list of metadata

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00665862
Contributor : Mohamed Daoudi Connect in order to contact the contributor
Submitted on : Friday, February 3, 2012 - 11:12:38 AM
Last modification on : Monday, September 20, 2021 - 11:38:10 AM
Long-term archiving on: : Friday, May 4, 2012 - 2:21:27 AM

File

PaperIJCV.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Chafik Samir, Anuj Srivastava, Mohamed Daoudi, Eric Klassen. An Intrinsic Framework for Analysis of Facial Surfaces. International Journal of Computer Vision, Springer Verlag, 2009, 82, pp.80-95. ⟨10.1007/s11263-008-0187-8⟩. ⟨hal-00665862⟩

Share

Metrics

Record views

449

Files downloads

850