Facial Expression Recognition Based on Fused Spatio-temporal Features

DOI

10.2991/iccsee.2013.532How to use a DOI?

Keywords

facial expression recognition, spatio-temporal (ST), fused spatio-temporal features (FST)

Abstract

Although spatio-temporal features (ST) have recently been developed and shown to be available for facial expression recognition and behavior recognition in videos, it utilizes the method of directly flattening the cuboid into a vector as a feature vector for recognition which causes the obtained vector is likely to potentially sensitive to small cuboid perturbations or noises. To overcome the drawback of spatio-temporal features, we propose a novel method called fused spatio-temporal features (FST) method utilizing the separable linear filters to detect interesting points and fusing two cuboids representation methods including local histogrammed gradient descriptor and flattening the cuboid into a vector for cuboids descriptor. The proposed FST method may robustness to small cuboid perturbations or noises and also preserve both spatial and temporal positional information. The experimental results on two video-based facial expression databases demonstrate the effectiveness of the proposed method.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jingjie Yan
AU  - Minghan Xin
PY  - 2013/03
DA  - 2013/03
TI  - Facial Expression Recognition Based on Fused Spatio-temporal Features
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 2113
EP  - 2116
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.532
DO  - 10.2991/iccsee.2013.532
ID  - Yan2013/03
ER  -