Convolutional Neural Network-based Finger Vein Recognition using Near Infrared Images
- 1 September 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 453-458
Abstract
Convolutional Neural Network (CNN) is opening new horizons in biometrics-based authentication field and finger vein recognition is the prominent one which can provide the best possible security system depending on this aforementioned technology. In this paper, we used 5 convolutional layers and 4 fully-connected layers where our developed network has shown the capability to produce the result with almost 100% accuracy rate which became possible due to the fact that deep learning, an end-to-end system is used which performs better in a lot of aspects in comparison to conventional techniques.Keywords
This publication has 12 references indexed in Scilit:
- Glomerulus Classification with Convolutional Neural Networks2017
- A Finger Vein Image-Based Personal Identification System With Self-Adaptive Illuminance ControlIEEE Transactions on Instrumentation and Measurement, 2016
- Vein detection system using infrared camera2016
- Finger-vein biometric identification using convolutional neural networkTurkish Journal of Electrical Engineering and Computer Sciences, 2016
- Finger Vein Segmentation from Infrared Images Based on a Modified Separable Mumford Shah Model and Local Entropy ThresholdingComputational and Mathematical Methods in Medicine, 2015
- A review on vein biometric recognition using geometric pattern matching techniques2014
- A real time embedded novel finger-vein recognition system for authenticated on teller machine2012
- Bi-directional weighted modular B2DPCA for finger vein recognition2010
- Finger vein recognition with manifold learningJournal of Network and Computer Applications, 2010
- Extraction of Finger-Vein Patterns Using Maximum Curvature Points in Image ProfilesIEICE Transactions on Information and Systems, 2007