Smile recognition based on the fusion of the face texture feature and the mouth shape feature

DOI

10.2991/icmmct-16.2016.256How to use a DOI?

Keywords

Smile recognition, Discriminative CCA, Feature fusion, LBP, HOG.

Abstract

Smile recognition has recently attracted significant attention due to the increasing accessibility in some digital products. Traditionally, the mouth feature has been extracted for smile recognition. However, it only extracts the features in the mouth region, ignoring the fact that face feature contribute to characterize expressions. In this paper, in order to overcome the drawbacks and make full use of the merits of both features, we propose a novel feature fusion approach for the smile recognition. In our approach, the mouth features are described by HOG descriptor and the face features are represented by Local Binary Pattern (LBP) histograms. Then, the two features are fused by discriminative canonical correlation analysis (DCCA). Robust Support Vector Machine (SVM) classifier is used for classification in our experiment and satisfactory results of experiments based on two databases are obtained finally.

Copyright

© 2016, 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  - Yuanzheng Li
PY  - 2016/03
DA  - 2016/03
TI  - Smile recognition based on the fusion of the face texture feature and the mouth shape feature
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Computing Technology
PB  - Atlantis Press
SP  - 1307
EP  - 1311
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmct-16.2016.256
DO  - 10.2991/icmmct-16.2016.256
ID  - Li2016/03
ER  -