Proceedings of the 2018 2nd International Conference on Applied Mathematics, Modelling and Statistics Application (AMMSA 2018)

A Face Recognition Method Based on LBP and GMM

Authors
Yuwen Song, Qingling Zhang, Xiuquan Xia
Corresponding Author
Yuwen Song
Available Online May 2018.
DOI
10.2991/ammsa-18.2018.54How to use a DOI?
Keywords
face recognition; LBP; GMM; EM algorithm
Abstract

This paper proposes a face recognition method based on local binary pattern(LBP) and Gaussian mixture model(GMM). Firstly, combine Uniform Pattern and Rotation Invariant LBP with traditional LBP operator to obtain initial classification data. Then, adopt GMM to classify face textures, and use EM algorithm to estimate the model parameters where K-means method is applied for initialization. Finally, the experiment is carried out on Yale and ORL face database. The results show that the recognition accuracy of this method has been greatly improved comparing with LBP, PCA or PCA+FLDA alone, especially for small samples.

Copyright
© 2018, 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)

Volume Title
Proceedings of the 2018 2nd International Conference on Applied Mathematics, Modelling and Statistics Application (AMMSA 2018)
Series
Advances in Intelligent Systems Research
Publication Date
May 2018
ISBN
978-94-6252-529-0
ISSN
1951-6851
DOI
10.2991/ammsa-18.2018.54How to use a DOI?
Copyright
© 2018, 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/).

Cite this article

TY  - CONF
AU  - Yuwen Song
AU  - Qingling Zhang
AU  - Xiuquan Xia
PY  - 2018/05
DA  - 2018/05
TI  - A Face Recognition Method Based on LBP and GMM
BT  - Proceedings of the 2018 2nd International Conference on Applied Mathematics, Modelling and Statistics Application (AMMSA 2018)
PB  - Atlantis Press
SP  - 261
EP  - 264
SN  - 1951-6851
UR  - https://doi.org/10.2991/ammsa-18.2018.54
DO  - 10.2991/ammsa-18.2018.54
ID  - Song2018/05
ER  -