Expression-invariant representations of faces

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

Research output: Contribution to journalArticlepeer-review

Abstract

Addressed here is the problem of constructing and analyzing expression-invariant representations of human faces. We demonstrate and justify experimentally a simple geometric model that allows to describe facial expressions as isometric deformations of the facial surface. The main step in the construction of expression-invariant representation of a face involves embedding of the facial intrinsic geometric structure into some low-dimensional space. We study the influence of the embedding space geometry and dimensionality choice on the representation accuracy and argue that compared to its Euclidean counterpart, spherical embedding leads to notably smaller metric distortions. We experimentally support our claim showing that a smaller embedding error leads to better recognition.

Original languageEnglish
Pages (from-to)188-197
Number of pages10
JournalIEEE Transactions on Image Processing
Volume16
Issue number1
DOIs
StatePublished - Feb 2007
Externally publishedYes

Keywords

  • Face recognition
  • Isometric embedding
  • Isometry-invariant representation
  • Multidimensional scaling
  • Spherical harmonics

Fingerprint

Dive into the research topics of 'Expression-invariant representations of faces'. Together they form a unique fingerprint.

Cite this