Finger vein verification is a promising biometric pattern for personal identification in terms of security and convenience. The recognition performance of this technology heavily relies on the quality of finger vein images and on the recognition algorithm. To achieve efficient recognition performance, a special finger vein imaging device is developed, and a finger vein recognition method based on sparse representation is proposed. The motivation for the proposed method is that finger vein images exhibit a sparse property. In the proposed system, the regions of interest (ROIs) in the finger vein images are segmented and enhanced. Sparse representation and sparsity preserving projection on ROIs are performed to obtain the features. Finally, the features are measured for recognition. An equal error rate of 0.017% was achieved based on the finger vein image database, which contains images that were captured by using the near-IR imaging device that was developed in this study. The experimental results demonstrate that the proposed method is faster and more robust than previous methods.
© 2012 Optical Society of AmericaFull Article | PDF Article
Miyuki Kono, Hironori Ueki, and Shin-ichiro Umemura
Appl. Opt. 41(35) 7429-7436 (2002)
B. V. K. Vijaya Kumar, Marios Savvides, Chunyan Xie, Krithika Venkataramani, Jason Thornton, and Abhijit Mahalanobis
Appl. Opt. 43(2) 391-402 (2004)
Eriko Watanabe and Kashiko Kodate
Appl. Opt. 44(5) 666-676 (2005)