Expression-invariant face recognition via spherical embedding

Alexander M. Bronstein, Michael M. Bronstein, Ron Kimmel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recently, it was proven empirically that facial expressions can be modelled as isometries, that is, geodesic distances on the facial surface were shown to be significantly less sensitive to facial expressions compared to Euclidean ones. Based on this assumption, the 3DFACE face recognition system was built. The system efficiently computes expression invariant signatures based on isometry-invariant representation of the facial surface. One of the crucial steps in the recognition system was embedding of the face geometric structure into a Euclidean (flat) space. Here, we propose to replace the flat embedding by a spherical one to construct isometric invariant representations of the facial image. We refer to these new invariants as spherical canonical images. Compared to its Euclidean counterpart, spherical embedding leads to notably smaller metric distortion. We demonstrate experimentally that representations with lower embedding error lead to better recognition. In order to efficiently compute the invariants we introduce a dissimilarity measure between the spherical canonical images based on the spherical harmonic transform.

Original languageEnglish
Title of host publicationIEEE International Conference on Image Processing 2005, ICIP 2005
Pages756-759
Number of pages4
DOIs
StatePublished - 2005
Externally publishedYes
EventIEEE International Conference on Image Processing 2005, ICIP 2005 - Genova, Italy
Duration: 11 Sep 200514 Sep 2005

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume3
ISSN (Print)1522-4880

Conference

ConferenceIEEE International Conference on Image Processing 2005, ICIP 2005
Country/TerritoryItaly
CityGenova
Period11/09/0514/09/05

Fingerprint

Dive into the research topics of 'Expression-invariant face recognition via spherical embedding'. Together they form a unique fingerprint.

Cite this