CandyFV

a dataset for research and development on biometric recognition and presentation attack detection using vascular biometrics

The dataset will be available soon

Description

The CandyFV is dataset has been acquired using sweet -- a contactless platform for research and development on biometric recognition and presentation attack detection using vascular biometrics. The sweet sensor can be used to capture vascular data from fingers, palm and wrist presentation. The CandyFV dataset includes only finger-vein (FV) data. It is a collection of 1200 bona-fide samples acquired from 120 individuals. These biometric-samples have been captured using three cameras: one RGB (visible light) camera, and two NIR cameras. The presented target (fingers) is illuminated in turn by white-light and two NIR wavelengths, namely, 850 nm and 950 nm, during the sample-recording process.

 

Reference

If you publish results using this dataset, please cite the following publication.


@inproceedings{candyfv,
  author = {Bhattacharjee, Sushil and Geissbuhler, David and Clivaz, G. and Kotwal, Ketan and Marcel, S{\'{e}}bastien},
  title = {Vascular Biometrics Experiments on Candy -- A New Contactless Finger-Vein Dataset},
  booktitle = {Proceedings of the International Conference on Pattern Recognition (ICPR)},
  year = {2025},
  month = {Dec},
  }