Universiti Teknologi Malaysia Institutional Repository

Finger-vein biometric identification using convolutional neural network

Ahmad Radzi, S. and Khalil Hani, M. and Bakhteri, R. (2016) Finger-vein biometric identification using convolutional neural network. Turkish Journal of Electrical Engineering and Computer Sciences, 24 (3). pp. 1863-1878. ISSN 1300-0632

Full text not available from this repository.

Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....

Abstract

A novel approach using a convolutional neural network (CNN) for finger-vein biometric identification is presented in this paper. Unlike existing biometric techniques such as fingerprint and face, vein patterns are inside the body, making them virtually impossible to replicate. This also makes finger-vein biometrics a more secure alternative without being susceptible to forgery, damage, or change with time. In conventional finger-vein recognition methods, complex image processing is required to remove noise and extract and enhance the features before the image classification can be performed in order to achieve high performance accuracy. In this regard, a significant advantage of the CNN over conventional approaches is its ability to simultaneously extract features, reduce data dimensionality, and classify in one network structure. In addition, the method requires only minimal image preprocessing since the CNN is robust to noise and small misalignments of the acquired images. In this paper, a reduced-complexity four-layer CNN with fused convolutional-subsampling architecture is proposed for finger-vein recognition. For network training, we have modified and applied the stochastic diagonal Levenberg{Marquardt algorithm, which results in a faster convergence time. The proposed CNN is tested on a finger-vein database developed in-house that contains 50 subjects with 10 samples from each finger. An identification rate of 100.00% is achieved, with an 80/20 percent ratio for separation of training and test samples, respectively. An additional number of subjects have also been tested, in which for 81 subjects an accuracy of 99.38% is achieved.

Item Type:Article
Uncontrolled Keywords:Anthropometry, Biometrics, Classification (of information), Complex networks, Convolution, Image classification, Image processing, Neural networks, Stochastic systems, Biometric identifications, Biometric techniques, Conventional approach, Convolutional neural network, Finger vein, Finger-vein recognition, Identification rates, Image preprocessing, Palmprint recognition
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:Electrical Engineering
ID Code:74291
Deposited By: Widya Wahid
Deposited On:29 Nov 2017 23:58
Last Modified:29 Nov 2017 23:58

Repository Staff Only: item control page