Finger Vein Recognition Using 2DGabor Combined With OECA

DOI

10.2991/iccia-17.2017.37How to use a DOI?

Keywords

Optimized KECA, Optimized ECA, Feature Extraction, 2DGabor Feature Fusion, and Independent Component Analysis.

Abstract

An improved Entropy Component Ananysis algorithm is proposed in this paper,which named as Optimized Entropy Component Analysis. The OECA algoptithm which is based on the Optimized Kernel Entropy Component Analysis algorithm develops a different data transformation method. The data transformation reveals structure related to the Renyi entropy of the input space data set. Unlike the Principal Component Analysis (PCA) algorithm, the method does not necessarily use the top eigenvalues and eigenvectors of data correlation matrix. OECA takes the cumulative entropy contribution as the standard of feature extraction, then uses the Independent Component Analysis (ICA) framework to maximize the independence between the components. Applying the OECA algorithm to finger vein recognition. In the meantime, a new finger vein extraction algorithm, GOECA, is proposed in combination with 2DGabor algorithm: when the feature obtained with 2DGabor wavelet transform, five different feature fusion methods are applied then the OECA algorithm is used to reduce dimensions. The results of the experiment show the efficiency of the proposed method.

Copyright

© 2017, 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  - Guangdong Liu
AU  - Xiaohui Qiu
PY  - 2016/07
DA  - 2016/07
TI  - Finger Vein Recognition Using 2DGabor Combined With OECA
BT  - Proceedings of the 2nd International Conference on Computer Engineering, Information Science & Application Technology (ICCIA 2017)
PB  - Atlantis Press
SP  - 222
EP  - 228
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccia-17.2017.37
DO  - 10.2991/iccia-17.2017.37
ID  - Liu2016/07
ER  -