home   |  research   |  members   |  projects   |  publications   |  conferences of interest   |  downloads   |  contact & impressum   |  privacy information
 
 

Finger-Vein Acquisition Condition Scores

This is "The Multimedia Signal Processing and Security Lab", short WaveLab, website. We are a research group at the Artificial Intelligence and Human Interfaces (AIHI) Department of the University of Salzburg led by Andreas Uhl. Our research is focused on Visual Data Processing and associated security questions. Most of our work is currently concentrated on Biometrics, Media Forensics and Media Security, Medical Image and Video Analysis, and application oriented fundamental research in digital humanities, individualised aquaculture and sustainable wood industry.
LyX Document

Handbook of Vascular Biometrics (Chapter 7) - Finger-Vein Acquisition Condition Scores



The capture subject comparison scores have been computed in the scope of investigations regrading recognition performance influences of various acquisition conditions. To obtain the comparison scores, all possible genuine and impostor comparisons are performed. This is done by comparing each image against all remaining ones which finally results in 120 genuine and 1650 impostor comparisons per subset. We utilised the PLUS OpenVein-Toolkit from which an implementation can be downloaded from: OpenVein-Toolkit. Thus, the provided score results are given in Matlab .mat files.



Database Description:

Filename and Directory Structure

Directory Structure:
Kirchgasser19a_VeinAcquisitionScores/[Illumination Type]/[Considered Comparison]/

Filename:
[Scores]_[Feature Extraction Method]_[Illumination Type].mat

Placeholder:

  • [Illumination Type]: The illumination method (Laser or LED) used during the data acquisition.
  • [Considered Comparison]: The IDs (ID vs ID) of the datasets used during the comparison represented as capital letters.
    • A: base
    • B: humid
    • C1: light
    • C2: dark
    • D1: temp-5
    • D2: temp+5
    • E1: skin10
    • E2: skin25
    • F1: up5
    • F2: up10
    • G: tremb
    • H1: badpl
    • H2: bend
    • I1: tip
    • I2: trunk
    • J1: handlot
    • J2: sunlot
    • K: cycle
  • [Feature Extraction Method]: Describes which feature extraction method was used (SIFT, Principal Curvature or Maximum Curvature).

Examples:

  • Folder AvsA: The original, undistorted images are compared to each other (baseline of the experiments).
  • Folder KvsA: The images which have been acquired after cycling are compared to undistorted images.

Each score file inlcudes a list of positive and negative comparison scores. The positives are genuine image comparisons while the negatives represent the impostor comparisons.

Download:

The obtained capture subject comparison scores using different finger-vein acquisition conditions as investigated in Handbook of Vascular Biometrics (Chapter 7) are available upon request.

Please fill out this form to request a download link for the score files:

Name:
Affiliation:
Email address:
 
Multimedia Signal Processing
and Security Lab
Tuesday, 16-Apr-2024 20:54:43 CEST