PLUSVein-Contactless Finger and Hand Vein Data Set - Download Page

Combined Fully Contact-Less Finger and Hand Vein Scanner

The PLUSVein-Contactless Finger and Hand Vein Database was acquired with our two custom designed combined fully contact-less finger and hand vein acquisition device. This scanner is designed to capture finger as well as hand vein images from the palmar side and can capture light transmission as well as reflected light images. It is based on an NIR enhanced industrial camera equipped with a 9 mm lens in combination with an NIR pass-through filter. Its light transmission light source consists of 1 stripe of 5 NIR laser modules, situated in the top part of the device. Each laser module is brightness controlled individually and automatically based on a preset brightness value to achieve an optimal image contrast. The reflect light illuminator consists of two rows of 8 LEDs each, one row of 8 850 nm LEDs, and one row of 8 950 nm LEDs which is situated on the bottom of the device next to the camera. This illuminator is automatically brightness controlled as well. To assist in positioning of the finger/hand, the top front part contains an LCD touchscreen display showing the user a live image of the finger/hand. Further information on the scanners and its design, including all technical details are available on request and can be found at: Combined Fully Contact-Less Finger and Hand Vein Acquisition Device

PLUSVein-Contactless Finger and Hand Vein Database

The data set itself consists of 3 subsets: a palmar finger vein one, acquired using the light transmission illuminator and two hand vein ones, one acquired with the 850 nm reflected light illuminator and the other one with the 950 nm reflected light illuminator. Currently it contains$42$ subjects. $6$ fingers (left and right index, middle and ring finger) and two hands (left and right hand) per subject and $5$ images per finger/hand in $1$ session were captured for each subsets. Hence, the finger vein subset consists of $252$ individual fingers. Each finger is captured 5 times, hence there are effectively $1260$ images in the finger vein subset. The hand vein subset consists of $84$ individual hands. Each hand is captured 5 times, hence there are effectively $420$ images in each of the two hand vein subsets. The dataset consists of a total of $2100$ images. The raw images have a resolution of $1280\times 1024$ pixels and are stored in 8 bit greyscale png format. The visible area of the finger or hand inside the images is about $600\times 180$ and $850\times 850$ pixels per finger/hand, respectively. 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 finger and hand vein ROI images have a size of $\mathrm{TODO}\times \mathrm{TODO}$ pixels and $384\times 384$ pixels, respectively.

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 raw finger and hand vein images as well as for the extracted ROI images the same directory structure applies:

• FingerVein_TI: contains the finger vein images acquired using the laser module based light transmission illumination
• 01: denotes session 1
• 001 ... 042: a subdirectory for each user contained in the data set
• HandVein_850: contains the hand vein images acquired using the LED based reflected light illumination with 850 nm peak wavelength
• 01: denotes session 1
• 001 ... 042: a subdirectory for each user contained in the data set
• HandVein_950: contains the hand vein images acquired using the LED based reflected light illumination with 950 nm peak wavelength
• 01: denotes session 1
• 001 ... 042: a subdirectory for each user contained in the data set

The filename are encoded using the following structure:
[session ID]_[user ID]_[finger ID/hand ID]-[DORSAL/PALMAR]_[image ID]_[illumination type].png

• 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 042 denotes the 42nd 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.
• hand ID: the hand ID, one character, where L denotes the left hand and R denotes the right hand.
• DORSAL/PALMAR: denotes if the image is captured from the palmar or the dorsal side
• image ID: the image ID, two digits, starting from 01.
• illumination ID: the illumination type, where TI indicates the laser module based light transmission for finger vein images, RL850 denotes 850 nm reflected light for hand vein images and RL950 denotes 950 nm reflected light for hand vein images as well.

An example finger vein image filename is: 01_002_02-PALMAR_03_TI.png
An example hand vein image filename is: 01_001_R-PALMAR_01_RL950.png

Obtaining the Database

To obtain the PLUSVein-Contactless Finger and Hand Vein Database you have to agree to our license agreement:
PLUSVein-Contactless 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.