Personal Authentication Using Finger Vein Biometric Technology with Implementation of Transfer Learning CNN Model

12 Pages Posted: 28 Dec 2021

See all articles by Sapna Sharma

Sapna Sharma

GD Goenka University - School of Engineering

Shikha Lohchab

GD Goenka University - School of Engineering

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

Sharma, Sapna and Lohchab, Shikha, Personal Authentication Using Finger Vein Biometric Technology with Implementation of Transfer Learning CNN Model (December 25, 2021). Proceedings of the International Conference on Advances in Management Practices (ICAMP 2021), Available at SSRN: https://ssrn.com/abstract=3993601 or http://dx.doi.org/10.2139/ssrn.3993601

Sapna Sharma (Contact Author)

GD Goenka University - School of Engineering ( email )

Sohna Gurgaon Road
Sohna
India

Shikha Lohchab

GD Goenka University - School of Engineering ( email )

Sohna Gurgaon Road
Sohna
India

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
130
Abstract Views
539
Rank
395,220
PlumX Metrics