Palm Vein Verification System based on Nonsubsampled Contourlet Transform

This document presents a new approach in verification system to verify the identity of person by his intrinsic characteristics “Palm vein” which is unique, universal and easy to captured. The first step in this system is to extract the region of interest (ROI) which represent the most informative region of palm, then coding step based on nonsubsampled contourlet transform (NSCT) is presented to produce a binary vector for each ROI, next a matching step of different representative vectors is given and finally a decision is made for both identification and verification mode. This approach is tested on CASIA multispectral database; the experimentations have proved the effectiveness of this coding system in verification modes to gives 0.19% of Equal Error Rate (EER).

@article{Oueslati2019,
  title     = {Palm Vein Verification System based on Nonsubsampled Contourlet Transform},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {10},
  number    = {10},
  year      = {2019},
  publisher = {The Science and Information Organization},
  author    = {Amira Oueslati and Kamel Hamrouni and Nadia Feddaoui and Safya Belghith},
  doi       = {10.14569/IJACSA.2019.0101040},
  url       = {https://doi.org/10.14569/IJACSA.2019.0101040}
}