Human Ear Recognition System

Human Ear Recognition System

Durgesh Singh (Indian Institute of Technology (BHU), India) and Sanjay Kumar Singh (Indian Institute of Technology (BHU), India)
DOI: 10.4018/978-1-4666-5888-2.ch540
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

A reliable human recognition scheme is required in wide variety of systems to either verify or identify the identity of an individual requesting their services. Using traditional approaches such as possession based and knowledge based systems, it is very difficult to differentiate between an authorized person and an impostor. This is a strong reason for replacing traditional ID-based systems with biometric systems which are based on human traits that cannot be denied, stolen, or faked easily. Biometric recognition refers to the automatic recognition, based on physiological and /or behavioral characteristics of an individual. By using biometrics, it is possible to establish an individual's identity based on “who he or she is” rather than by “what he or she possesses likes smart card” or “what he or she remembers likes password.” Human ear due to its consistent behavior over the age, has gained much popularity in recent years among various physiological biometric traits. The decidability index of the ear has been found that magnitude significant greater than that of face. Ear remarkably consistent and does not change its shape under expressions like face. The shape of the outer ear is recognized as a valuable means for personal identification. Naturally, an ear biometric system consists of ear detection and ear recognition modules. Ear biometric has played an important role for many years in forensic science and its use by law enforcement agencies.
Chapter Preview
Top

Introduction

Biometrics has been an active field of research as there is an ever-growing need to automatically authenticate individuals. In almost all the security aspects, biometric systems play a significant role. Traditional methods of automatic recognition, such as ID cards or passwords, can be stolen, forgotten or faked. On the other hand, biometric characteristics are unique, permanent, universal and measurable. Biometrics method of identification is preferred over traditional methods for various reasons such as: firstly the person to be identified is required to be physically present at the point of identification and secondly the identification based on biometric techniques avoids the need to remember a password or using ID.

In biometrics system universality, distinctiveness, permanence, performance, collectability, acceptability and circumvention mainly these seven parameters are used to decide whether a human trait can be used as biometric or not. Based on these seven parameters, a brief comparison among biometric traits is provided in Table 1 (Jain et al., 2004). In this table high, medium, and low are denoted by H, M, and L, respectively. A biometric system may operate either in verification mode or identification mode that depending on the application. First step of any biometric system is the enrollment process. Enrollment process is used to register a new person with the biometric system. In verification, the user claims an identity and the system verifies whether the claim is genuine or not. So verification is one to one matching process and typically used in applications where the goal is to prevent unauthorised persons from using the services. In the identification mode, the system recognizes an individual by searching template of all the users in the database for a match. So, identification is one to many matching process and typically used to prevent single person from using multiple identities.

Table 1.
A brief comparison among biometric traits based on the seven parameters
Biometric TraitUniversalityDistinctivenesspermanenceCollectabilityPerformanceAcceptabilityCircumvention
EarMMHMMHM
FaceHLMHLHH
FingerprintMHHMHMM
GaitMLLHLHM
IrisHHHMHLL
RetinaHHMLHLL
PalmprintMHHMHMM
KeystrokeLLLMLMM
SignatureLLLHLHH
VoiceMLLMLHH
DNAHHHLHLL

Key Terms in this Chapter

Biometrics: Biometrics also known as biometrics recognition refers to the automatic recognition of individuals based on their physiological and/or behavioral characteristics. Using biometrics system, it is possible to confirm or establish an individual’s identity based on “who she is,” rather than by “what he or she possesses” or “what he or she remembers.”

Identification: In the identification mode, an individual recognizes by searching template of all the users in the database for a match. Hence a system conducts a one -to- many comparisons to establish an individual’s identity.

Verification: In verification also known as authentication mode, the user claims an identity and the system verifies whether the claim is genuine i.e. the system answer the question “Are you who you say you are?.”In this scenario, the query is compared only to the template corresponding to the claimed identity (a one- to -one matching).

Physiological Characteristics: Physiological characteristics derives from the structural information of the human body. Fingerprint, Face, Ear, Iris, Retina, Palmprint, Veins etc. falls under the physiolosical traits.

Multi-Biometrics: Multimodal biometric systems are those that fuse more than one physiological and (or) behavioral characteristic for enrollment, verification, or identification.

Behavioral Characteristics: Behavioral characteristics are based on behaviour of the person. Voice, Signature, Keystroke Dynamics, Gaits etc. traits falls under the behavioural characteristics.

Complete Chapter List

Search this Book:
Reset