Finger Vein Recognition with Gabor Wavelets and Local Binary Patterns

Jialiang PENG  Qiong LI  Ahmed A. ABD EL-LATIF  Ning WANG  Xiamu NIU  

IEICE TRANSACTIONS on Information and Systems   Vol.E96-D   No.8   pp.1886-1889
Publication Date: 2013/08/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E96.D.1886
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Pattern Recognition
finger vein recognition,  Gabor wavelet,  local binary pattern,  BLDA,  

Full Text: PDF(498.3KB)>>
Buy this Article

In this paper, a new finger vein recognition method based on Gabor wavelet and Local Binary Pattern (GLBP) is proposed. In the new scheme, Gabor wavelet magnitude and Local Binary Pattern operator are combined, so the new feature vector has excellent stability. We introduce Block-based Linear Discriminant Analysis (BLDA) to reduce the dimensionality of the GLBP feature vector and enhance its discriminability at the same time. The results of an experiment show that the proposed approach has excellent performance compared to other competitive approaches in current literatures.