Longitudinal Finger Rotation in Finger-Vein Recognition
This is "The Multimedia Signal Processing and Security Lab", short WaveLab, website. We are a research group at the Computer Sciences Department of the University of Salzburg headed by Andreas Uhl. The short name "WaveLab" already indicates that wavelets are among our favorite tools - we have 15 years of experience in this area. Our research is focused on Multimedia Security including Watermarking, Image and Video Compression, Medical Image Classification, and Biometrics.
Abstract Finger-vein scanners or vein-based biometrics in general are becoming more and more popular. Commercial off-the-shelf finger-vein scanners usually capture only one finger from the palmar side using transillumination. Most scanners have a contact area and a finger-shaped support where the finger has to be placed onto in order to prevent misplacements of the finger including shifts, planar rotation and tilts. However, this is not able to prevent rotation of the finger along its longitudinal axis (also called non-planar finger rotation). This kind of finger rotation poses a severe problem in finger-vein recognition as the resulting vein image may represent entirely different patterns due to the perspective projection. We evaluated the robustness of several finger-vein recognition schemes against longitudinal finger rotation. Therefore, we established a finger-vein data set exhibiting longitudinal finger rotation in steps of 1° covering a range of ±90°. Our experimental results confirm that the performance of most of the simple recognition schemes rapidly decreases for more than 10° of rotation, while more advanced schemes are able to handle up to 30°.
[Prommegger18b ] Longitudinal Finger Rotation - Problems and Effects in Finger-Vein Recognition In Proceedings of the International Conference of the Biometrics Special Interest Group (BIOSIG'18), pp. 1-11, Darmstadt, Germany, September 27 - 28
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:
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:PLUS OpenVein Finger- and Hand-Vein Toolkit
The framework contains all the feature extraction, comparison as well as evaluation methods used for the experiments in the paper.
General Structure of the Files
The scores files are provided as MATLAB .mat files. Each .mat file contains a struct, containing two vectors:
The scores are all similarity scores, i.e. higher scores indicate higher similarity. Thus the genuine scores should be ideally higher than the impostor ones. The scores obtained for the 3 binary features using the Miura matcher as well as for DTFPM are in the range of [0 - 0.5] while the scores obtained for SIFT are in the range of [0 - 1].
File Naming Conventions and Directory Structure
According to the experiments, every evaluated perspective has been treated as its own data set. As a result of this, also the score files are seperated per perspective.
So the directory structure is as follows:
Each of the subdirectories contains one scores file or one settings file per feature type, respectively:
available upon request.