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

PLUSVein-FV3 Finger Vein Data Set - Download Page

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.
PLUSVein-FV3 Finger Vein Data Set

Finger Vein Scanner

The PLUSVein-FV3 LED-Laser Dorsal-Palmar Finger Vein Database was acquired with our two custom designed finger vein scanners, an NIR LED and a NIR laser module based version. The scanners are designed to capture 3 fingers (index, middle and ring finger) at once. Both scanners are based on an NIR enhanced industrial camera equipped with a 9 mm lens in combination with an NIR pass-through filter. Its main light source is a transillumination one consisting of 3 stripes (one underneath each finger) of NIR LEDs for the LED version or NIR laser modules for the laser version of the scanner, respectively. Each LED/laser module is brightness controlled individually and automatically based on a preset brightness value to achieve an optimal image contrast. An LED ring consisting of 8 850 nm LEDs, 8 950 nm LEDs and 8 daylight LEDs for capturing reflected light images is situated on top of the device and can be automatically brightness controlled too. To assist in positioning of the finger, the lower part contains a custom 3D printed finger support which also serves as a bracket for the 3 illumination stripes. Further information on the scanners and its design as well as an open-source repository containing all the scanner details can be found at: PLUS OpenVein Open Source Finger-Vein Scanner

PLUSVein-FV3 Finger Vein Database

The finger-vein data set itself consists of 4 subsets: one dorsal and one palmar finger-vein subset captured using transillumination with the LED and the laser module based scanner, respectively. Currently it contains 60 subjects. 6 fingers (left and right index, middle and ring finger) per subject and 5 images per finger in 1 session were captured for each of the four subsets. So each subset consists of the same 360 individual fingers but captured from a different view - palmar for the first two and dorsal for the second two. Each scanner captures 3 fingers at a time. Thus, each subset contains 600 raw finger-vein images. The images are then separated into 3 parts, corresponding to index, middle and ring finger, respectively. Hence, there are effectively 1800 images in each subset and 7200 images in total for the whole data set. The raw images have a resolution of 1280 × 1024 pixels and are stored in 8 bit greyscale png format. The finger separated images have a resolution of 420 × 1024 pixels and the visible area of the finger inside the images is about 200 × 750 pixels per finger. The ROI images are extracted with the help of edge detection mechanisms and by masking out the background in the images (setting the pixels to black). The ROI images have a size of 736 × 192 pixels.

The database is publicly available for research purposes and the raw finger vein images as well as the ROI images can be obtained here.

The database is planned to be extended set by a second session as well as by adding further subjects in the future.

     

Filename and Directory Structure

For the separated raw finger vein images as well as for the extracted ROI images the same directory structure applies:
  • PLUS-FV3-Laser: contains the finger vein images acquired using the laser module based illumination
    • DORSAL: finger vein images captured from the dorsal side of the hand
      • 01: denotes session 1
        • 001 ... 060: a subdirectory for each user contained in the data set
    • PALMAR: finger vein images captured from the palmar (ventral) side of the hand
      • 01: denotes session 1
        • 001 ... 060: a subdirectory for each user contained in the data set
  • PLUS-FV3-LED: contains the finger vein images acquired using the LED based illumination
    • DORSAL: finger vein images captured from the dorsal side of the hand
      • 01: denotes session 1
        • 001 ... 060: a subdirectory for each user contained in the data set
    • PALMAR: finger vein images captured from the palmar (ventral) side of the hand
      • 01: denotes session 1
        • 001 ... 060: a subdirectory for each user contained in the data set
The filename are encoded using the following structure:
[scanner name]_[DORSAL/PALMAR]_[session ID]_[user ID]_[finger ID]_[image ID].png
  • scanner name: the name of the scanner used to capture the image, either PLUS-FV3-Laser or PLUS-FV3-LED
  • DORSAL/PALMAR: denotes if the image is captured from the palmar or the dorsal side
  • session ID: the session ID, two digits, where 01 denotes the first session
  • user ID: the user ID, three digits, where 001 denotes the first user and 060 denotes the 60th user
  • finger ID: the finger ID, two digits, starting from the left thumb (01) till the right pinky finger (10):
    • 02: left index finger
    • 03: left middle finger
    • 04: left ring finger
    • 07: right index finger
    • 08: right middle finger
    • 09: right ring finger
    • The left thumb (01), left pinky finger (05), right thumb (06) and right pinky finger (10) have not been captured.
  • image ID: the image ID, two digits, starting from 01.
An example filename is: PLUS-FV3-Laser_DORSAL_01_001_02_01.png

Obtaining the Database

To obtain the PLUSVein-FV3 Finger Vein Database you have to agree to our license agreement:
PLUSVein-FV3 Consent Form

Please download, fill in and sign the license agreement and send it to A. Uhl or via mail to our department. After checking the license agreement you will be provided with a download link for both, the raw finger vein images as well as the extracted ROI images.