home  |   research   |  members   |  projects  |  publications   |  conferences of interest   |  downloads   |  contact  |  intern
 
 

Finger Vein Template Protection based on Alignment-Robust Feature Description and Index-of-Maximum Hashing

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.

Finger Vein Template Protection based on Alignment-Robust Feature Description and Index-of-Maximum Hashing

Several algorithms have been used for protecting the used finger vein images that have been investigated in the scope of the IEEE Transactions on Biometrics, Behavior, and Identity Science paper "Finger Vein Template Protection based on Alignment-Robust Feature Description and Index-of-Maximum Hashing". The corresponding information to these implementations, necessary setting-files and recognition result files can be downloaded from this site to comply with the principles of reproducible research.

Abstract

Privacy preserving storage and secure processing of biometric data is a key issue that has to be addressed in finger vein recognition systems as well. Various template protection approaches originally proposed for well established biometric modalities have been adopted to the domain of finger vein authentication. However, these adopted methods have the disadvantage that they are not designed for finger vein patterns in particular and are thus, sub-optimal in several ways. In this study we propose an alignment-robust template protection scheme that is based on an efficient binary representation of finger vein patterns on the one hand and is further using the advantages of Index-of-Maximum (IoM) hashing to fulfill mandatory privacy and security based characteristics on the other hand. The proposed method is compared to block re-mapping and warping regarding recognition performance and is analyzed with respect to security and privacy aspects. The analysis is further extended to robustness against misalignment of the finger vein data and a combination of block re-mapping/warping and the proposed method is investigated as well.

Reference

TODO after publication acceptance

Data Sets

PLUSVein-FV3 Finger Vein Data Set

The PLUSVein-FV3 Finger Vein Data Set (PLUSVein-FV3) is a publically available fingr vein data set. It contains palmar and dorsal images of 360 fingers from 60 different subjects (ring, middle and index finger from both hands) captured in one session with five samples per finger using two different variants of the same sensor: One utilizing NIR laser modules for illumination, the other one using NIR LEDs. Further information regarding the data set can be found by the following link:

PLUSVein-FV3 Data Set

University of Twente Finger Vascular Pattern Database

The University of Twente Finger Vascular Pattern (UTFVP) Database is a publically available finger vein data set. It contains six fingers (ring, middle and index finger from both hands) from 60 volunteers acquired in two sessions. Further information regarding the data set can be found by the following link:

UTFVP Download Page (external link)

Template Protection Framework Information

Two resources can be downloaded to obtain the entire code used to perform the experiments:

  • The code used to protect the templates by the proposed Alignment-Robust-Hashing method.
  • The code used to protect the templates by the reference protection schemes utilising block re-mapping and warping.

For both resources a separate directory can be found in the downloadable .tar.gz file inlcuding not only the corresponding MatLab-code but also example startFiles for running the experiments.

Please fill out this form to request a download link for the used code, settings and result files:

Name:
Affiliation:
Email address:

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.

Result Files and Settings

Two resources can be downloaded to obtain the entire code used to perform the experiments:

  • All settings files utilised by the PLUS OpenVein-Toolkit from which an implementation can be downloaded from: OpenVein-Toolkit
  • The obtained score files and the corresponding evaluation software for the extended experiments. These experiments have been additionally performed and thus are new as compared to the results presented in the original paper Kirchgasser19c.

For all resources a separate directory can be found in the downloadable .tar.gz file. The directory containing the score files includes three sub-directories. One contains the evaluation software, while the other two directories are dedicated to the resulting score files.

Please fill out this form to request a download link for the used code, settings and result files:

Name:
Affiliation:
Email address: