Biometric Identification Techniques

Biometric Identification Techniques

Hunny Mehrotra (Indian Institute of Technology Kanpur, India), Pratyush Mishra (Indian Institute of Technology Kanpur, India) and Phalguni Gupta (Indian Institute of Technology Kanpur, India)
DOI: 10.4018/978-1-60566-026-4.ch060
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

In today’s high-speed world, millions of transactions occur every minute. For these transactions, data need to be readily available for the genuine people who want to have access, and it must be kept securely from imposters. Some methods of establishing a person’s identity are broadly classified into: 1. Something You Know: These systems are known as knowledge-based systems. Here the person is granted access to the system using a piece of information like a password, PIN, or your mother’s maiden name. 2. Something You Have: These systems are known as token-based systems. Here a person needs a token like a card key, smartcard, or token (like a Secure ID card). 3. Something You Are: These systems are known as inherited systems like biometrics. This refers to the use of behavioral and physiological characteristics to measure the identity of an individual. The third method of authentication is preferred over token-based and knowledge-based methods, as it cannot be misplaced, forgotten, stolen, or hacked, unlike other approaches. Biometrics is considered as one of the most reliable techniques for data security and access control. Among the traits used are fingerprints, hand geometry, handwriting, and face, iris, retinal, vein, and voice recognition. Biometrics features are the information extracted from biometric samples which can be used for comparison. In cases of face recognition, the feature set comprises detected landmark points like eye-to-nose distance, and distance between two eye points. Various feature extraction methods have been proposed, for example, methods using neural networks, Gabor filtering, and genetic algorithms. Among these different methods, a class of methods based on statistical approaches has recently received wide attention. In cases of fingerprint identification, the feature set comprises location and orientation of ridge endings and bifurcations, known as a minutiae matching approach (Hong, Wan, & Jain, 1998). Most iris recognition systems extract iris features using a bank of filters of many scales and orientation in the whole iris region. Palmprint recognition, just like fingerprint identification, is based on aggregate information presented in finger ridge impression. Like fingerprint identification, three main categories of palm matching techniques are minutiae-based matching, correlation-based matching, and ridge-based matching. The feature set for various traits may differ depending upon the extraction mechanism used. The system that uses a single trait for authenticity veri- fication is called unimodal biometric system. A unimodal biometric system (Ross & Jain, 2003) consists of three major modules: sensor module, feature extraction module, and matching module. However, even the best biometric traits face numerous problems like non-universality, susceptibility to biometric spoofing, and noisy input. Multimodal biometrics provides a solution to the above mentioned problems. A multimodal biometric system uses multiple sensors for data acquisition. This allows capturing multiple samples of a single biometric trait (called multi-sample biometrics) and/or samples of multiple biometric traits (called multi-source or multimodal biometrics). This approach also enables a user who does not possess a particular biometric identifier to still enroll and authenticate using other traits, thus eliminating the enrollment problems. Such systems, known as multimodal biometric systems (Tolba & Rezq, 2000), are expected to be more reliable due to the presence of multiple pieces of evidence. A good fusion technique is required to fuse information for such biometric systems.
Chapter Preview
Top

Introduction

In today’s high-speed world, millions of transactions occur every minute. For these transactions, data need to be readily available for the genuine people who want to have access, and it must be kept securely from imposters. Some methods of establishing a person’s identity are broadly classified into:

  • 1.

    Something You Know: These systems are known as knowledge-based systems. Here the person is granted access to the system using a piece of information like a password, PIN, or your mother’s maiden name.

  • 2.

    Something You Have: These systems are known as token-based systems. Here a person needs a token like a card key, smartcard, or token (like a Secure ID card).

  • 3.

    Something You Are: These systems are known as inherited systems like biometrics. This refers to the use of behavioral and physiological characteristics to measure the identity of an individual.

The third method of authentication is preferred over token-based and knowledge-based methods, as it cannot be misplaced, forgotten, stolen, or hacked, unlike other approaches. Biometrics is considered as one of the most reliable techniques for data security and access control. Among the traits used are fingerprints, hand geometry, handwriting, and face, iris, retinal, vein, and voice recognition.

Biometrics features are the information extracted from biometric samples which can be used for comparison. In cases of face recognition, the feature set comprises detected landmark points like eye-to-nose distance, and distance between two eye points. Various feature extraction methods have been proposed, for example, methods using neural networks, Gabor filtering, and genetic algorithms. Among these different methods, a class of methods based on statistical approaches has recently received wide attention. In cases of fingerprint identification, the feature set comprises location and orientation of ridge endings and bifurcations, known as a minutiae matching approach (Hong, Wan, & Jain, 1998). Most iris recognition systems extract iris features using a bank of filters of many scales and orientation in the whole iris region. Palmprint recognition, just like fingerprint identification, is based on aggregate information presented in finger ridge impression. Like fingerprint identification, three main categories of palm matching techniques are minutiae-based matching, correlation-based matching, and ridge-based matching. The feature set for various traits may differ depending upon the extraction mechanism used.

The system that uses a single trait for authenticity verification is called unimodal biometric system. A unimodal biometric system (Ross & Jain, 2003) consists of three major modules: sensor module, feature extraction module, and matching module. However, even the best biometric traits face numerous problems like non-universality, susceptibility to biometric spoofing, and noisy input. Multimodal biometrics provides a solution to the above mentioned problems.

A multimodal biometric system uses multiple sensors for data acquisition. This allows capturing multiple samples of a single biometric trait (called multi-sample biometrics) and/or samples of multiple biometric traits (called multi-source or multimodal biometrics). This approach also enables a user who does not possess a particular biometric identifier to still enroll and authenticate using other traits, thus eliminating the enrollment problems. Such systems, known as multimodal biometric systems (Tolba & Rezq, 2000), are expected to be more reliable due to the presence of multiple pieces of evidence. A good fusion technique is required to fuse information for such biometric systems.

Key Terms in this Chapter

Template: The mathematical representation of biometric data. Any graphical representation is reduced to a numerical representation. The template is then used by the biometric system as an efficient method to make comparisons with other templates stored in the system.

Indexing: Logical partitioning of large database using some known data structures like B-trees, hash functions, and so forth

Hashing: The transformation of a record into a usually shorter fixed-length value or key that represents the original record. Hashing is used to index and retrieve items in a database because it is faster to find the item using the shorter hashed key than to find it using the original value.

Biometrics: The use of physiological or behavioral characteristics to verify the identity of an individual comes under the realm of biometrics. Biometrics is an automated recognition of an individual based on his or her distinctive anatomical characteristics.

Multi-Biometrics: A biometric system that uses more than one biometric identifier (like a combination of face, fingerprint, iris, ear etc.) in making a decision about personal identification. Multimodal biometrics systems are expected to be more reliable due to the presence of multiple traits

Class ification: Supervised grouping of entire dataset at a basic level using some extracted biometric features.

Clustering: Can be considered the most important unsupervised learning problem of organizing objects into groups whose members are similar in some way. A cluster is therefore a collection of objects that are similar between them and are dissimilar to the objects belonging to other clusters.

Fusion: Combines biometric characteristics derived from one or more modalities or technologies (algorithms, sensors), multiple characteristics derived from samples, or multiple or repeated biometric instances to increase performance. Biometrics fusion centers on the capture and comparison of multiple biometric measurements like fingerprint and face

Complete Chapter List

Search this Book:
Reset