Finger-vein template recognition system using cnnresnet 18

Abstract

Biometric Authentication Technology has been broadly utilized in area of retrieving information of peoples. As one of the most significant innovation of verification, finger vein recognition system is considered best because of its high security, solid precision and better accuracy. However, the system of finger vein recognition cannot be used widely because systems are based on complex image processing concept and they are not representative of feature vector. So here to solve this problem we have implemented CNN in developing Finger vein recognition system, Images are directly provided to the input of CNN for extracting its feature out with the goal that we can make validation by looking at the Euclidean distance between these vectors. We have developed a system with implementation of convolution neural network specifically resnet18 for the training image dataset and image retrieving process is done. Purpose of introducing deep learning in developing finger vein identification system is to get accurate more performance and speedy results. Results are computed on the basis Euclidean distance between features obtained from test image and features of trained images, the model designed has good robustness in illumination and rotation.