Finger vein has become an appealing biometric trait due to its intrinsic nature, contactless acquisition and anti-spoofing capability when compared to other dominant biometric traits. There exist many finger vein image-based databases available for research purposes. However, the image-based vein recognition methods also extract artifacts such as noise, breaks and texture along with veins due to the problems such as irregular shading, poor contrast and blurriness in NIR images. Hence a video-based technique can be a better solution to deal with such problems. To the best of our knowledge, there is no finger vein video database available for research so far in the public domain. The researchers at CRICTR have been working on finger vein recognition since 2015. We have developed a prototype device that can capture both videos and images of finger veins. This is a finger vein video database captured using our lab-made device. The final objective is to establish a large-scale finger vein video database for further research and also to make it available to the research community.
The finger vein video database (FV_IIITMK_VideoData) consists of videos of finger veins acquired simultaneously from student volunteers and researchers at our University. This database has been acquired during the period of August - October 2019 using our finger vein prototype device. The vein videos from the index and the middle fingers of both hands of 80 subjects (individuals) were taken. We had taken 6 finger vein videos per subject as session 1 for a duration of 1 second. The videos were stored in MP4 format with a frame rate 25 fps.
NB: Currently only a sample dataset consisting of 5 subjects is provided. Many of the volunteers had shown their privacy concerns and unwillingness to reveal their data publicly while data collection. Hence due to the present pandemic situation, we are not able to get permission from everyone. Considering the legal and privacy aspects, we can provide only a few sample data for the time being. We will be uploading more video samples in the future based on the consent of the subjects.