Face Recognition Based on LBP(2D)2PCA+SVM

DOI

10.2991/csece-18.2018.37How to use a DOI?

Keywords

face recognition; (2D)2PCA; LBP; SVM

Abstract

In this work, we present a novel approach of face recognition which considers local binary pattern (LBP), principal component analysis (PCA) and support vector machine (SVM) algorithms, which is named as LBP(2D)2PCA+SVM. This method firstly extracts facial texture features, then uses (2D)2PCA algorithm to reduce its dimensions, and finally employs SVM algorithm to classify and recognize the images. Our consideration is that LBP algorithm has a characteristic of rotation invariance, which is robust to illumination change and pose variation; (2D)2PCA is an improvement of PCA, using this method the image can reach the maximum degree of dimension reduction; SVM has the advantages of global optimization, simple structure, strong generalization ability and so on. By synthesizing the advantages of the algorithms, our proposed LBP(2D)2PCA +SVM algorithm performs higher recognition rate than other algorithms, and the effective combination of different strategies can greatly help us to improve the recognition rate.

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)

TY  - CONF
AU  - Yanmei Jiang
AU  - Wei Wei
AU  - Xue Liu
AU  - Ying Shi
PY  - 2018/02
DA  - 2018/02
TI  - Face Recognition Based on LBP(2D)2PCA+SVM
BT  - Proceedings of the 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE 2018)
PB  - Atlantis Press
SP  - 174
EP  - 178
SN  - 2352-538X
UR  - https://doi.org/10.2991/csece-18.2018.37
DO  - 10.2991/csece-18.2018.37
ID  - Jiang2018/02
ER  -