Fusion of geometrical and texture information for facial expression recognition

Conference paper


Kotsia, I., Nikolaidis, N. and Pitas, I. 2006. Fusion of geometrical and texture information for facial expression recognition. IEEE International Conference on Image Processing (ICIP 2006). Atlanta, USA 08 - 11 Oct 2006
TypeConference paper
TitleFusion of geometrical and texture information for facial expression recognition
AuthorsKotsia, I., Nikolaidis, N. and Pitas, I.
Abstract

A novel method based on geometrical and texture information is proposed for facial expression recognition from video sequences. The discriminant non-negative matrix factorization (DNMF) algorithm is applied at the image of the last frame of the video sequence, corresponding to the greatest intensity of the facial expression, thus extracting the texture information. A support vector machines (SVMs) system is used for the classification of the geometrical information derived from tracking the Candide grid over the video sequence. The geometrical information consists of the differences of the node coordinates between the neutral (first) and the fully expressed facial expression (last) video frame. The fusion of texture and geometrical information obtained is performed using SVMs. The accuracy achieved is 98.7% when recognizing the six basic facial expressions.

Research GroupResearch Group on Development of Intelligent Environments
ConferenceIEEE International Conference on Image Processing (ICIP 2006)
Publication process dates
Deposited28 Dec 2012
Output statusPublished
Web address (URL)http://www.icip2006.org/
LanguageEnglish
Permalink -

https://repository.mdx.ac.uk/item/83x1x

  • 13
    total views
  • 0
    total downloads
  • 1
    views this month
  • 0
    downloads this month

Export as