Face recognition based on Gabor wavelet transform and modular 2DPCA

DOI

10.2991/peee-15.2015.67How to use a DOI?

Keywords

Modular two-dimensional principal component analysis(modular 2DPCA), Gabor wavelet, Face recognition, Support vector machine(SVM).

Abstract

Since the dimension of face features which is presented by Gabor wavelet is too high, there has large computation if using the feature by Gabor wavelet transform for recognition directly. A novel idea based on Gabor wavelet transform and modular Two-principal component analysis for face recognition is proposed. Firstly, face image feature is acquired by Gabor Wavelet transforming. Secondly, its dimension is reduced and eigenvectors are extracted by the method of modular 2DPCA. Finally, fusion with nearest neighbor classifier and support vector machine (SVM) is adopted to sort and distinguish. Experimental results on ORL and YALE show that the performance of proposed method is superior to other methods, such as modular 2DPCA and combination of Gabor wavelet transform and 2DPCA.

Copyright

© 2015, 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  - H. Yan
AU  - P. Wang
AU  - W.D. Chen
AU  - J. Liu
PY  - 2015/04
DA  - 2015/04
TI  - Face recognition based on Gabor wavelet transform and modular 2DPCA
BT  - Proceedings of the 2015 International Conference on Power Electronics and Energy Engineering
PB  - Atlantis Press
SP  - 245
EP  - 248
SN  - 2352-5401
UR  - https://doi.org/10.2991/peee-15.2015.67
DO  - 10.2991/peee-15.2015.67
ID  - Yan2015/04
ER  -