Personal Authentication Using Finger Vein Biometric Technology with Implementation of Transfer Learning CNN Model
12 Pages Posted: 28 Dec 2021
Date Written: December 25, 2021
Abstract
In this paper, the performance of convolutional neural networks such as Alex net, Squeeze net and Google Net (Inception) are analyzed for the finger vein based personal authentication with respect to control, access to the confidential data. The finger vein images from SDUMLA HMT database are used for this research work. Using wiener filter the noises are removed from the finger vein images. The noise free images are provided for training to Alex net, Squeeze net and Google net network to recognize person for finger vein authentication. The finger vein authentication using the three pre trained network includes loading finger vein images dataset, loading pretrain network, training network through transfer learning, image classification and image validation. The experiment exhibits the outstanding performance of Google net over the Alex net and Squeeze net on various parameter including computation time, accuracy, dropout, and the initial learning.
Keywords: Convolutional Neural Network, Alex net, Squeeze net, Google net, Transfer learning ,accuracy
JEL Classification: C63,C61 ,C68
Suggested Citation: Suggested Citation