Skip to main navigation Skip to search Skip to main content

Facial expression recognition with 3D deformable models

  • Christoph Mayer
  • , Matthias Wimmer
  • , Martin Eggers
  • , Bernd Radig

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

7 Scopus citations

Abstract

We present a fully automated three-dimensional modelbased, real-time capable approach to distinguish six universal facial expressions from visual images of human faces. The face model is fitted to the images of a publicly available data base. From the model parameters two sets of features are computed, person-specific and non-person-specific to estimate the facial expression visible in the current image sequence. We integrate the complex, state-of-the-art Candide-3 face model, which is specifically appropriate for facial expression recognition [13] and is also publicly available, which further increases the comparability of our approach. Our experimental evaluation presents recognition rates of the six basic facial expressions defined by Ek-man et al [6].

Original languageEnglish
Title of host publicationProceedings of the 2nd International Conferences on Advances in Computer-Human Interactions, ACHI 2009
Pages26-31
Number of pages6
DOIs
StatePublished - 2009
Event2nd International Conferences on Advances in Computer-Human Interactions, ACHI 2009 - Cancun, Mexico
Duration: 1 Feb 20097 Feb 2009

Publication series

NameProceedings of the 2nd International Conferences on Advances in Computer-Human Interactions, ACHI 2009

Conference

Conference2nd International Conferences on Advances in Computer-Human Interactions, ACHI 2009
Country/TerritoryMexico
CityCancun
Period1/02/097/02/09

Fingerprint

Dive into the research topics of 'Facial expression recognition with 3D deformable models'. Together they form a unique fingerprint.

Cite this