Hardware approach of ANN based iris recognition for real-time biometric identification

Md. Mamun Ibne Reaz, Md Syedul Amin, Fazida Hanim Hashim, Khandaker Asaduzzaman

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Artificial Neural Networks (ANN) are increasingly applied to biometric identification because neural nets have been shown to be technologically powerful and flexible, ideally suited to perform identification analysis. Therefore, it demands the development of a new processing structure that allows efficient hardware implementation of the neural networks mechanism. This research presents the ANN based iris recognition for biometric identification modeled by the very high speed integrated circuit Hardware Description Language (VHDL) to ease the description, verification, simulation and hardware realization of this kind of systems. The project is divided into two processes which are image processing and recognition. Image processing was performed by using Matlab where back propagation was used for recognition. The iris recognition architecture comprises of three layers: Input layer with three neurons, hidden layer with two neurons and output layer with one neuron. Sigmoid transfer function is used for both hidden layer and output layer neurons. Neuron of each layer is modeled individually using VHDL. Functional simulations were commenced to verify the functionality and performance of the individual modules and the system. Iris vector from captured human iris has been used to validate the effectiveness of the model. An accuracy of 88.6% is achieved in recognizing the sample of 100 data of irises.

Original languageEnglish
Pages (from-to)2984-2992
Number of pages9
JournalJournal of Applied Sciences
Volume11
Issue number16
DOIs
Publication statusPublished - 2011

Fingerprint

Biometrics
Neurons
Computer hardware description languages
Neural networks
Hardware
Image processing
Image recognition
Backpropagation
Transfer functions
Integrated circuits
Processing

Keywords

  • Artificial intelligence
  • Image processing
  • Iris recognition
  • Neural network
  • VHDL

ASJC Scopus subject areas

  • General

Cite this

Hardware approach of ANN based iris recognition for real-time biometric identification. / Ibne Reaz, Md. Mamun; Amin, Md Syedul; Hashim, Fazida Hanim; Asaduzzaman, Khandaker.

In: Journal of Applied Sciences, Vol. 11, No. 16, 2011, p. 2984-2992.

Research output: Contribution to journalArticle

@article{8f73a0f966e34d219337142e3577c80b,
title = "Hardware approach of ANN based iris recognition for real-time biometric identification",
abstract = "Artificial Neural Networks (ANN) are increasingly applied to biometric identification because neural nets have been shown to be technologically powerful and flexible, ideally suited to perform identification analysis. Therefore, it demands the development of a new processing structure that allows efficient hardware implementation of the neural networks mechanism. This research presents the ANN based iris recognition for biometric identification modeled by the very high speed integrated circuit Hardware Description Language (VHDL) to ease the description, verification, simulation and hardware realization of this kind of systems. The project is divided into two processes which are image processing and recognition. Image processing was performed by using Matlab where back propagation was used for recognition. The iris recognition architecture comprises of three layers: Input layer with three neurons, hidden layer with two neurons and output layer with one neuron. Sigmoid transfer function is used for both hidden layer and output layer neurons. Neuron of each layer is modeled individually using VHDL. Functional simulations were commenced to verify the functionality and performance of the individual modules and the system. Iris vector from captured human iris has been used to validate the effectiveness of the model. An accuracy of 88.6{\%} is achieved in recognizing the sample of 100 data of irises.",
keywords = "Artificial intelligence, Image processing, Iris recognition, Neural network, VHDL",
author = "{Ibne Reaz}, {Md. Mamun} and Amin, {Md Syedul} and Hashim, {Fazida Hanim} and Khandaker Asaduzzaman",
year = "2011",
doi = "10.3923/jas.2011.2984.2992",
language = "English",
volume = "11",
pages = "2984--2992",
journal = "Journal of Applied Sciences",
issn = "1812-5654",
publisher = "Asian Network for Scientific Information",
number = "16",

}

TY - JOUR

T1 - Hardware approach of ANN based iris recognition for real-time biometric identification

AU - Ibne Reaz, Md. Mamun

AU - Amin, Md Syedul

AU - Hashim, Fazida Hanim

AU - Asaduzzaman, Khandaker

PY - 2011

Y1 - 2011

N2 - Artificial Neural Networks (ANN) are increasingly applied to biometric identification because neural nets have been shown to be technologically powerful and flexible, ideally suited to perform identification analysis. Therefore, it demands the development of a new processing structure that allows efficient hardware implementation of the neural networks mechanism. This research presents the ANN based iris recognition for biometric identification modeled by the very high speed integrated circuit Hardware Description Language (VHDL) to ease the description, verification, simulation and hardware realization of this kind of systems. The project is divided into two processes which are image processing and recognition. Image processing was performed by using Matlab where back propagation was used for recognition. The iris recognition architecture comprises of three layers: Input layer with three neurons, hidden layer with two neurons and output layer with one neuron. Sigmoid transfer function is used for both hidden layer and output layer neurons. Neuron of each layer is modeled individually using VHDL. Functional simulations were commenced to verify the functionality and performance of the individual modules and the system. Iris vector from captured human iris has been used to validate the effectiveness of the model. An accuracy of 88.6% is achieved in recognizing the sample of 100 data of irises.

AB - Artificial Neural Networks (ANN) are increasingly applied to biometric identification because neural nets have been shown to be technologically powerful and flexible, ideally suited to perform identification analysis. Therefore, it demands the development of a new processing structure that allows efficient hardware implementation of the neural networks mechanism. This research presents the ANN based iris recognition for biometric identification modeled by the very high speed integrated circuit Hardware Description Language (VHDL) to ease the description, verification, simulation and hardware realization of this kind of systems. The project is divided into two processes which are image processing and recognition. Image processing was performed by using Matlab where back propagation was used for recognition. The iris recognition architecture comprises of three layers: Input layer with three neurons, hidden layer with two neurons and output layer with one neuron. Sigmoid transfer function is used for both hidden layer and output layer neurons. Neuron of each layer is modeled individually using VHDL. Functional simulations were commenced to verify the functionality and performance of the individual modules and the system. Iris vector from captured human iris has been used to validate the effectiveness of the model. An accuracy of 88.6% is achieved in recognizing the sample of 100 data of irises.

KW - Artificial intelligence

KW - Image processing

KW - Iris recognition

KW - Neural network

KW - VHDL

UR - http://www.scopus.com/inward/record.url?scp=84857425391&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857425391&partnerID=8YFLogxK

U2 - 10.3923/jas.2011.2984.2992

DO - 10.3923/jas.2011.2984.2992

M3 - Article

AN - SCOPUS:84857425391

VL - 11

SP - 2984

EP - 2992

JO - Journal of Applied Sciences

JF - Journal of Applied Sciences

SN - 1812-5654

IS - 16

ER -