Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos

Munawar Hayat, Mohammed Bennamoun, Amar A. El-Sallam

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

10 Citations (Scopus)

Abstract

This paper presents a fully automatic system which exploits the dynamics of 3D videos and is capable of recognizing six basic facial expressions. Local video-patches of variable lengths are extracted from different locations of the training videos and represented as points on the Grass-mannian manifold. An efficient spectral clustering based algorithm is used to separately cluster points for each of the six expression classes. The resulting cluster centers are matched with the points of a test video and a voting based strategy is used to decide about the expression class of the test video. The proposed system is tested on the largest publicly available 3D video database, BU4DFE. The experimental results show that the system achieves a very high classification accuracy and outperforms the current state of the art algorithms for facial expression recognition from 3D videos.

Original languageEnglish
Title of host publication2013 IEEE Workshop on Applications of Computer Vision, WACV 2013
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages83-88
Number of pages6
ISBN (Print)9781467350532
DOIs
Publication statusPublished - 2013
Externally publishedYes
EventIEEE Workshop on Applications of Computer Vision 2013 - Tampa, United States of America
Duration: 15 Jan 201317 Jan 2013
https://cvl.cse.sc.edu/wvm2013/
https://ieeexplore.ieee.org/xpl/conhome/6471303/proceeding (Proceedings)

Publication series

NameProceedings of IEEE Workshop on Applications of Computer Vision
ISSN (Print)2158-3978
ISSN (Electronic)2158-3986

Conference

ConferenceIEEE Workshop on Applications of Computer Vision 2013
Abbreviated titleWACV 2013
CountryUnited States of America
CityTampa
Period15/01/1317/01/13
Internet address

Cite this