Biometric Identification System Using Neuro and Fuzzy Computational Approaches

Biometric Identification System Using Neuro and Fuzzy Computational Approaches

Tripti Rani Borah (Gauhati University, India), Kandarpa Kumar Sarma (Gauhati University, India) and Pranhari Talukdar (Gauhati University, India)
DOI: 10.4018/978-1-4666-8654-0.ch016
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

In all authentication systems, biometric samples are regarded to be the most reliable one. Biometric samples like fingerprint, retina etc. is unique. Most commonly available biometric system prefers these samples as reliable inputs. In a biometric authentication system, the design of decision support system is critical and it determines success or failure. Here, we propose such a system based on neuro and fuzzy system. Neuro systems formulated using Artificial Neural Network learn from numeric data while fuzzy based approaches can track finite variations in the environment. Thus NFS systems formed using ANN and fuzzy system demonstrate adaptive, numeric and qualitative processing based learning. These attributes have motivated the formulation of an adaptive neuro fuzzy inference system which is used as a DSS of a biometric authenticable system. The experimental results show that the system is reliable and can be considered to be a part of an actual design.
Chapter Preview
Top

Introduction

Of late biometric attributes have become important components of authentication systems. This is because biometric attributes are based on a physiological or behavioral characteristic which are unique to a person. Biometric aids are accepted as important components of highly secured identification and verification systems as solutions to security breaches, transaction frauds etc. in a diverse range of applications that have direct impact on the lives of the common man. This is more so with cases which are confidential in nature like that seen in financial transactions, restricted access zones, working with personal data and privacy. Biometric authentication systems are also available in real time mode especially with applications including distributed computing resources where application logins, data protection, remote access, transaction security etc are linked to individual personal attributes. The primary benefit derived is security which re-enforces reliability and trust. In most case, biometric identification is found to be the most reliable method of trust-worthy transaction of any type.

Biometric authentication refers to the identification of humans by their characteristics or traits. Biometrics is used in human computer interaction (HCI) systems as a form of identification and access control. Biometric characteristics of a person are unique and remain unchanged over a lifetime. Biometric identifiers are the distinctive, measurable characteristics used to label and describe individuals (Jain, Hong, & Pankanti, 2000).They are often categorized as physiological versus behavioral characteristics. A physiological biometric would identify a person by an iris scan, DNA or fingerprint etc. Behavioral biometrics is related to the behavior of a person, including but not limited to typing rhythm, gait and voice. Though behavioral biometrics is less expensive and less dangerous for the user, physiological characteristics offer highly exact identification of a person.

Fingerprint identification is a matured biometric technique used for criminal investigations. Major representations of the finger are based on the entire image, finger ridges or salient features derived from the ridges (minutiae). These characteristics are used to generate an orientation field of the fingerprint, which subsequently provides the discriminating details for authentication of persons. Fingerprint identification is a popular technique because of their easy access, low price of fingerprint sensors, non-intrusive scanning and relatively good performance. In recent years, significant performance improvements have been achieved in commercial automatic fingerprint recognition systems (FRS). The fingerprint of an individual is unique and remains unchanged over a lifetime (Jain, Hong, Pankanti, & Bolle, 1997).

Retina is another unique biometric pattern that can be used as a part of a verification system. Retina identification is an automatic method that provides true identification of the person by acquiring an internal body image which is difficult to counterfeit (Hill, 1978). Retina identification has found application in high security environments of all types.

Key Terms in this Chapter

Artificial Neural Network (ANN): ANN is a soft-computing tool that can learn patterns and predicts.

Membership Function (MF): The membership function is a graphical representation of the magnitude of participation of each input. It associates weighting with each of the inputs that are processed.

Eigen Vector: A nonzero vector x is an eigen vector of a square matrix A if there exists a scalar ? such that Ax = ? x . Then ? is an eigen value of A .

Retina Recognition System (RRS): It is a high security identification system based on retina. Retina is the vascular pattern (blood vessels) of the eye which is not easy to replicate.

Mean Square Error (MSE): It is used as the primary criterion to ascertain the extent of learning acquired by a learning system like ANN. It is defined as the average squared error between the network’s output and the target value over all the samples.

Ridge: Ridges are like graphical flow patterns present on the surface of the human finger.

Noise: It is the disturbance in a digital image. Noise can be caused in imges by random fluctuations in the image signal.

Blood Vessel: They are present on the thin nerve on the back of the eyeball that processes light entering through the pupil in a retina.

Neuro Fuzzy System (NFS): A neuro fuzzy system is essentially a multilayer neural network and thus it can apply standard learning algorithms developed for neural networks, including the back-propagation algorithm.

Root Mean Square Error (RMSE): It is used as the primary criterion to ascertain the extent of learning acquired by the ANFIS. It is defined by the sum of the square of the difference between the actual and desired output.

Gaussian Noise: It is statistical noise that has a probality density function of the normal distribution. It means, the values that the noise can take on are gaussian distribution.

Fuzzy System (FS): Fuzzy System can solve problems very effectively by adding impreciseness to the systems. It provides an expert leve decision making system by following the variations in the texture of the input data.

Fuzzy Inference System (FIS): A FIS is a way of mapping an input space to an output space using fuzzy logic. FIS uses a collection of fuzzy membership functions and rules, instead of Boolean logic, to reason about data.

Speckle Noise: This type of noise can be seen on medical images because of the signals from elementary scatterers.

Salt and Pepper Noise: It is a form of noise typically seen on images which represents itself as randomly occurring white and black pixels.

Adaptive Neuro Fuzzy Inference System (ANFIS): ANFIS belongs to the class of systems commonly known as neuro fuzzy systems. NFS combines the powers od ANN with those of Fuzzy systems. This procedure leads to long cycles of system modification and evaluation. This process goes on and on until decent levels of accuracy are met.

Fingerprint Recognition System (FRS): It is the process used to determine whether two sets of fingerprint from the same finger or not. Fingerprint consists of ridges and valleys.

Thinning: It is the image enhancement technique in which binary valued image regions are reduced to lines.

Complete Chapter List

Search this Book:
Reset