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

Munawar Hayat, Mohammed Bennamoun, Amar El-Sallam

Research output: A Conference proceeding or a Chapter in BookConference contribution

8 Citations (Scopus)
1 Downloads (Pure)

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 publicationApplications of Computer Vision, 2013 IEEE Workshop on
EditorsSudeep Sarkar, Michael Brown
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages83-88
Number of pages6
Volume1
ISBN (Electronic)9781467350549
ISBN (Print)9781467350532
DOIs
Publication statusPublished - 2013
Externally publishedYes
EventApplications on Computer Vision (WACV) 2013 IEEE Workshop on - Tampa, Tampa, United States
Duration: 15 Jan 201317 Jan 2013

Conference

ConferenceApplications on Computer Vision (WACV) 2013 IEEE Workshop on
CountryUnited States
CityTampa
Period15/01/1317/01/13

Cite this

Hayat, M., Bennamoun, M., & El-Sallam, A. (2013). Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos. In S. Sarkar, & M. Brown (Eds.), Applications of Computer Vision, 2013 IEEE Workshop on (Vol. 1, pp. 83-88). USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/wacv.2013.6475003
Hayat, Munawar ; Bennamoun, Mohammed ; El-Sallam, Amar. / Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos. Applications of Computer Vision, 2013 IEEE Workshop on. editor / Sudeep Sarkar ; Michael Brown. Vol. 1 USA : IEEE, Institute of Electrical and Electronics Engineers, 2013. pp. 83-88
@inproceedings{c69ba92ccd264082970d5aa6a88b9e81,
title = "Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos",
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",
keywords = "Face-recognition, Pattern-recognition, Computer-vision",
author = "Munawar Hayat and Mohammed Bennamoun and Amar El-Sallam",
year = "2013",
doi = "10.1109/wacv.2013.6475003",
language = "English",
isbn = "9781467350532",
volume = "1",
pages = "83--88",
editor = "Sudeep Sarkar and Michael Brown",
booktitle = "Applications of Computer Vision, 2013 IEEE Workshop on",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

Hayat, M, Bennamoun, M & El-Sallam, A 2013, Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos. in S Sarkar & M Brown (eds), Applications of Computer Vision, 2013 IEEE Workshop on. vol. 1, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 83-88, Applications on Computer Vision (WACV) 2013 IEEE Workshop on, Tampa, United States, 15/01/13. https://doi.org/10.1109/wacv.2013.6475003

Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos. / Hayat, Munawar; Bennamoun, Mohammed; El-Sallam, Amar.

Applications of Computer Vision, 2013 IEEE Workshop on. ed. / Sudeep Sarkar; Michael Brown. Vol. 1 USA : IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 83-88.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos

AU - Hayat, Munawar

AU - Bennamoun, Mohammed

AU - El-Sallam, Amar

PY - 2013

Y1 - 2013

N2 - 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

AB - 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

KW - Face-recognition

KW - Pattern-recognition

KW - Computer-vision

U2 - 10.1109/wacv.2013.6475003

DO - 10.1109/wacv.2013.6475003

M3 - Conference contribution

SN - 9781467350532

VL - 1

SP - 83

EP - 88

BT - Applications of Computer Vision, 2013 IEEE Workshop on

A2 - Sarkar, Sudeep

A2 - Brown, Michael

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

ER -

Hayat M, Bennamoun M, El-Sallam A. Clustering of video-patches on Grassmannian manifold for facial expression recognition from 3D videos. In Sarkar S, Brown M, editors, Applications of Computer Vision, 2013 IEEE Workshop on. Vol. 1. USA: IEEE, Institute of Electrical and Electronics Engineers. 2013. p. 83-88 https://doi.org/10.1109/wacv.2013.6475003