Abstract

Finger vein recognition deals with the identification of subjects based on its venous pattern within the fingers. The majority of the scanner devices capture a single finger from the palmar side using light transmission. Some of them are equipped with a contact surface or other structures to support in finger placement. However, these means are not able to prevent all possible types of finger misplacements, in particular longitudinal finger rotation can not be averted. It has been shown that this type of deformation causes severe problems to finger vein recognition systems. This paper proposes two new methods in which finger vein images from different perspectives are captured during enrolment and, but only one during authentication. In the first method, the authentication image is compared to all enrolment images, whereas in the second method they are linked together to form a perspective cumulative finger vein template. As the enrolled finger vein images depict the vein structure of a larger range of the finger, the longitudinal positioning of the finger during the acquisition for the biometric recognition is less critical. The experimental results confirm the applicability especially of the first approach.

Reference

[Prommegger19d     ] Rotation Invariant Finger Vein Recognition Bernhard Prommegger, Andreas Uhl In 2019 IEEE 10th International Conference on Biometrics Theory, Applications and Systems (BTAS), pp. 1-9, Tampa, Florida, USA, September 23 - September 26

Data Sets

PLUSVein Finger Rotation Data Set

The PLUSVein Finger Rotation Data Set (PLUSVein-FR) is a partly publically available finger vein data set. It contains finger images captured all around the finger from 63 different subjects, 4 fingers (index and middle finger from both hands) per subject, which sums up to a total of 252 unique fingers. Further information regarding the data set can be found by the following link:

PLUSVein-FR Data Set

Evaluation Framework Information

The experimental evaluations have been conducted using the open source vein recognition framework (PLUS OpenVein Finger- and Hand-Vein Toolkit) provided by the University of Salzburg. This is a feature extraction and matching/evaluation framework for finger- and hand-vein recognition implemented in MATLAB. It was tested on MATLAB 2016 and should work with all version of MATLAB newer or equal to 2016. This software is under the Simplified BSD license.

A more detailed description of the framework as well as its sources can be found here:

The framework contains all the feature extraction, comparison as well as evaluation methods used for the experiments in the paper.

Results

The performance results are provided as .tar files that contains one result file per KPI (EER, FMR100, FMR1000 and ZeroFMR). The content of the tab-delimited files are:

• Perspective used for calculation
• Intra-perspective performance without any rotation correction (IP)
• Intra-perspective performance using circular pattern normalisation as rotation correction (IP_CPN)
• Multi-perspective enrolment with a rotational difference of 15° between two enrolment perspectives (MPE_15)
• Multi-perspective enrolment with a rotational difference of 30° between two enrolment perspectives (MPE_30)
• Multi-perspective enrolment with a rotational difference of 45° between two enrolment perspectives (MPE_45)
• Perspective cumulative finger vein templates with a rotational difference of 15° between two enrolment perspectives (PCT_15)
• Perspective cumulative finger vein templates with a rotational difference of 30° between two enrolment perspectives (PCT_30)
• Perspective cumulative finger vein templates with a rotational difference of 45° between two enrolment perspectives (PCT_45)

Result Files Download