FMnet: Iris segmentation and recognition by using fully and multi-scale CNN for biometric security

Rachida Tobji*, Wu Di, Naeem Ayoub

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

55 Downloads (Pure)

Abstract

In Deep Learning, recent works show that neural networks have a high potential in the field of biometric security. The advantage of using this type of architecture, in addition to being robust, is that the network learns the characteristic vectors by creating intelligent filters in an automatic way, grace to the layers of convolution. In this paper, we propose an algorithm "FMnet" for iris recognition by using Fully Convolutional Network (FCN) and Multi-scale Convolutional Neural Network (MCNN). By taking into considerations the property of Convolutional Neural Networks to learn and work at different resolutions, our proposed iris recognition method overcomes the existing issues in the classical methods which only use handcrafted features extraction, by performing features extraction and classification together. Our proposed algorithm shows better classification results as compared to the other state-of-the-art iris recognition approaches.

Original languageEnglish
Article number2042
JournalApplied Sciences (Switzerland)
Volume9
Issue number10
Number of pages17
ISSN2076-3417
DOIs
Publication statusPublished - 1. May 2019

Fingerprint

biometrics
Biometrics
Neural networks
Feature extraction
pattern recognition
Convolution
convolution integrals
learning
filters

Keywords

  • Convolutional neural networks (CNN)
  • Fully Convolutional Network (FCN)
  • Iris recognition
  • Iris segmentation
  • Multi-scale Convolutional Neural Network (MCNN)

Cite this

@article{7524c221edb849ed96e79ddc376a573e,
title = "FMnet: Iris segmentation and recognition by using fully and multi-scale CNN for biometric security",
abstract = "In Deep Learning, recent works show that neural networks have a high potential in the field of biometric security. The advantage of using this type of architecture, in addition to being robust, is that the network learns the characteristic vectors by creating intelligent filters in an automatic way, grace to the layers of convolution. In this paper, we propose an algorithm {"}FMnet{"} for iris recognition by using Fully Convolutional Network (FCN) and Multi-scale Convolutional Neural Network (MCNN). By taking into considerations the property of Convolutional Neural Networks to learn and work at different resolutions, our proposed iris recognition method overcomes the existing issues in the classical methods which only use handcrafted features extraction, by performing features extraction and classification together. Our proposed algorithm shows better classification results as compared to the other state-of-the-art iris recognition approaches.",
keywords = "Convolutional neural networks (CNN), Fully Convolutional Network (FCN), Iris recognition, Iris segmentation, Multi-scale Convolutional Neural Network (MCNN)",
author = "Rachida Tobji and Wu Di and Naeem Ayoub",
year = "2019",
month = "5",
day = "1",
doi = "10.3390/app9102042",
language = "English",
volume = "9",
journal = "Applied Sciences",
issn = "2076-3417",
publisher = "MDPI",
number = "10",

}

FMnet : Iris segmentation and recognition by using fully and multi-scale CNN for biometric security. / Tobji, Rachida; Di, Wu; Ayoub, Naeem.

In: Applied Sciences (Switzerland), Vol. 9, No. 10, 2042, 01.05.2019.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - FMnet

T2 - Iris segmentation and recognition by using fully and multi-scale CNN for biometric security

AU - Tobji, Rachida

AU - Di, Wu

AU - Ayoub, Naeem

PY - 2019/5/1

Y1 - 2019/5/1

N2 - In Deep Learning, recent works show that neural networks have a high potential in the field of biometric security. The advantage of using this type of architecture, in addition to being robust, is that the network learns the characteristic vectors by creating intelligent filters in an automatic way, grace to the layers of convolution. In this paper, we propose an algorithm "FMnet" for iris recognition by using Fully Convolutional Network (FCN) and Multi-scale Convolutional Neural Network (MCNN). By taking into considerations the property of Convolutional Neural Networks to learn and work at different resolutions, our proposed iris recognition method overcomes the existing issues in the classical methods which only use handcrafted features extraction, by performing features extraction and classification together. Our proposed algorithm shows better classification results as compared to the other state-of-the-art iris recognition approaches.

AB - In Deep Learning, recent works show that neural networks have a high potential in the field of biometric security. The advantage of using this type of architecture, in addition to being robust, is that the network learns the characteristic vectors by creating intelligent filters in an automatic way, grace to the layers of convolution. In this paper, we propose an algorithm "FMnet" for iris recognition by using Fully Convolutional Network (FCN) and Multi-scale Convolutional Neural Network (MCNN). By taking into considerations the property of Convolutional Neural Networks to learn and work at different resolutions, our proposed iris recognition method overcomes the existing issues in the classical methods which only use handcrafted features extraction, by performing features extraction and classification together. Our proposed algorithm shows better classification results as compared to the other state-of-the-art iris recognition approaches.

KW - Convolutional neural networks (CNN)

KW - Fully Convolutional Network (FCN)

KW - Iris recognition

KW - Iris segmentation

KW - Multi-scale Convolutional Neural Network (MCNN)

U2 - 10.3390/app9102042

DO - 10.3390/app9102042

M3 - Journal article

AN - SCOPUS:85066496514

VL - 9

JO - Applied Sciences

JF - Applied Sciences

SN - 2076-3417

IS - 10

M1 - 2042

ER -