Changelog

• Version 2, 20/Jan/2016:
  • Port to Bob v2
• Version 1, 06/Nov/2014:
  • Initial release

Description

The University of Twente Finger Vascular Pattern (UTFVP) database is a realistic and challenging finger vein database to support and stimulate research efforts in the area of developing, testing and evaluating algorithms for vascular pattern recognition.

The collected dataset contains 1440 finger vascular pattern images in total which have been collected from 60 volunteers at Twente University during the 2011-2012 academic year. Images were captured in two identical sessions with an average time lapse of 15 days. For each volunteer the vascular pattern of the index, ring and middle finger of both hands has been collected twice at each session. This means that each individual finger has been captured four times in total. The captured images have a resolution of 672 x 380 pixels and have a pixel density of 126 pixels per centimetre (ppcm). The images are stored using the lossless 8 bit grey scale Portable Network Graphics(PNG) format.

The percentage of male volunteers was 73% and the percentage of right handed volunteers was 87%. The dataset represents a young population with 82% of the volunteers falling in the age range of 19-30, the remaining volunteers were older than this. The quality of the collected images varies from person to person, but the variation in quality of the images from the same person is small. The width of the visible blood vessels range from 4-20 pixels which corresponds to vessel widths of approximately 0.3-1.6 mm. These vessel widths are approximate numbers because the pixel density was determined assuming a flat surface.

Associated with the database is the UTFVP protocol called 1vsall, which is based on the database reference paper [Ton+13].

The Idiap Research Institue and The Swiss Center for Biometrics Research and Testing define the Normal Operation Mode (NOM) protocols which set of data to use for training, evaluation and testing. Performing experiments according to the protocol allows institutions to easily compare their results to others.

Description: The nom protocols divide the database on three subsets: world (subjects 1-10), development (subjects 11-28) and test (subjects 29-60). Only the images in world set should be used to train system components such as world/background models, PCA/LDA subspaces, etc., or to otherwise use as background data, for example for score normalisation, etc. The development set only should be used to train system hyper-parameters such as the decision threshold, number of dimensions in a subspace, feature extraction and preprocessing hyper-parameters, coefficients for linear fusion, etc., to minimise the chosen error rate metric. Finally, the test set should be used to test finger vein verification accuracy. The decision threshold must be determined by tuning on the development set, and then blindly applied to finger vein verification scores produced on the test set.

In the nom protocol the different fingers of one subject are considered different subjects. Therefore, a total number of 60 x 6 = 360 subjects will be considered for the experiments. The remaining protocols: nomLeftRing, nomLeftMiddle, nomLeftIndex, nomRightIndex, nomRightMiddle, nomRightRing consider just one finger per subject. Therefore, a total number of 60 subjects will be considered for the experiments in these cases. In all these protocols, the two finger vein images from the first session are used for enrolment and the two from the second session as probe samples.

Citation: All documents and papers that report on research that uses the UTFVP database must acknowledge the use of the database by including a citation of the paper [Ton+13].