Abstract

Biometric techniques are currently among the most widely used methods all over the world for determining a person identity. This trend is expected to continue in the near future. In this study, we focused on palm vein is used as a strategy to improve biometric authentication systems by combining a method that is based on texture with a method that is based on a convolutional neural network (CNN). The simulation is used to test the performance of the model on several different datasets. In simulations, the suggested method routinely achieves better results than the current best practice on each and every dataset.