Other Free Encyclopedias » Online Encyclopedia » Encyclopedia - Featured Articles » Contributed Topics from A-E

Biometric Technologies - INTRODUCTION, BACKGROUND, Fingerprint, Facial Recognition, Iris Scan, Retinal Scan, Voice Recognition, Signature Verification

system time identification technology

Mayank Vatsa
Indian Institute of Technology Kanpur, India

Richa Singh
Indian Institute of Technology Kanpur, India

P. Gupta
Indian Institute of Technology Kanpur, India

A. K. Kaushik
Electronic Niketan, India


Identity verification in computer systems is done based on measures like keys, cards, passwords, PIN and so forth. Unfortunately, these may often be forgotten, disclosed or changed. A reliable and accurate identification/verification technique may be designed using biometric technologies, which are further based on the special characteristics of the person such as face, iris, fingerprint, signature and so forth. This technique of identification is preferred over traditional passwords and PIN-based techniques for various reasons:

  • The person to be identified is required to be physically present at the time of identification.
  • Identification based on biometric techniques obviates the need to remember a password or carry a token.

A biometric system essentially is a pattern recognition system that makes a personal identification by determining the authenticity of a specific physiological or behavioral characteristic possessed by the user. Biometric technologies are thus defined as the “automated methods of identifying or authenticating the identity of a living person based on a physiological or behavioral characteristic.” A biometric system can be either an identification system or a verification (authentication) system; both are defined below.

  • Identification: One to Many —A comparison of an individual’s submitted biometric sample against the entire database of biometric reference templates to determine whether it matches any of the templates.
  • Verification: One to One —A comparison of two sets of biometrics to determine if they are from the same individual.

Biometric authentication requires comparing a registered or enrolled biometric sample (biometric template or identifier) against a newly captured biometric sample (for example, the one captured during a login). This is a three-step process ( Capture, Process, Enroll ) followed by a Verification or Identification .

During Capture , raw biometric is captured by a sensing device, such as a fingerprint scanner or video camera; then, distinguishing characteristics are extracted from the raw biometric sample and converted into a processed biometric identifier record (biometric template). Next is enrollment, in which the processed sample (a mathematical representation of the template) is stored/registered in a storage medium for comparison during authentication. In many commercial applications, only the processed biometric sample is stored. The original biometric sample cannot be reconstructed from this identifier.


Many biometric characteristics may be captured in the first phase of processing. However, automated capturing and automated comparison with previously stored data requires the following properties of biometric characteristics:

  • Universal: Everyone must have the attribute. The attribute must be one that is seldom lost to accident or disease.
  • Invariance of properties: They should be constant over a long period of time. The attribute should not be subject to significant differences based on age or either episodic or chronic disease.
  • Measurability: The properties should be suitable for capture without waiting time and it must be easy to gather the attribute data passively.
  • Singularity: Each expression of the attribute must be unique to the individual. The characteristics should have sufficient unique properties to distinguish one person from any other. Height, weight, hair and eye color are unique attributes, assuming a particularly precise measure, but do not offer enough points of differentiation to be useful for more than categorizing.
  • Acceptance: The capturing should be possible in a way acceptable to a large percentage of the population. Excluded are particularly invasive technologies; that is, technologies requiring a part of the human body to be taken or (apparently) impairing the human body.
  • Reducibility: The captured data should be capable of being reduced to an easy-to-handle file.
  • Reliability and tamper-resistance: The attribute should be impractical to mask or manipulate. The process should ensure high reliability and reproducibility.
  • Privacy: The process should not violate the privacy of the person.
  • Comparable: The attribute should be able to be reduced to a state that makes it digitally comparable to others. The less probabilistic the matching involved, the more authoritative the identification.
  • Inimitable: The attribute must be irreproducible by other means. The less reproducible the attribute, the more likely it will be authoritative.

Among the various biometric technologies being considered are fingerprint, facial features, hand geometry, voice, iris, retina, vein patterns, palm print, DNA, keystroke dynamics, ear shape, odor, signature and so forth.


Fingerprint biometric is an automated digital version of the old ink-and-paper method used for more than a century for identification, primarily by law enforcement agencies (Maltoni, 2003). The biometric device requires each user to place a finger on a plate for the print to be read. Fingerprint biometrics currently has three main application areas: large-scale Automated Finger Imaging Systems (AFIS), generally used for law enforcement purposes; fraud prevention in entitlement programs; and physical and computer access. A major advantage of finger imaging is the long-time use of fingerprints and its wide acceptance by the public and law enforcement communities as a reliable means of human recognition. Others include the need for physical contact with the optical scanner, possibility of poor-quality images due to residue on the finger such as dirt and body oils (which can build up on the glass plate), as well as eroded fingerprints from scrapes, years of heavy labor or mutilation.

Facial Recognition

Face recognition is a noninvasive process where a portion of the subject’s face is photographed and the resulting image is reduced to a digital code (Zhao, 2000). Facial recognition records the spatial geometry of distinguishing features of the face. Facial recognition technologies can encounter performance problems stemming from such factors as non-cooperative behavior of the user, lighting and other environmental variables. The main disadvantages of face recognition are similar to problems of photographs. People who look alike can fool the scanners. There are many ways in which people can significantly alter their appearance, like slight change in facial hair and style.

Iris Scan

Iris scanning measures the iris pattern in the colored part of the eye, although iris color has nothing to do with the biometric 6 . Iris patterns are formed randomly. As a result, the iris patterns in the left and right eyes are different, and so are the iris patterns of identical twins. Iris templates are typically around 256 bytes. Iris scanning can be used quickly for both identification and verification applications because of its large number of degrees of freedom. Disadvantages of iris recognition include problems of user acceptance, relative expense of the system as compared to other biometric technologies and the relatively memory-intensive storage requirements.

Retinal Scan

Retinal scanning involves an electronic scan of the retina—the innermost layer of wall of the eyeball. By emitting a beam of incandescent light that bounces off the person’s retina and returns to the scanner, a retinal scanning system quickly maps the eye’s blood vessel pattern and records it into an easily retrievable digitized database 3 . The eye’s natural reflective and absorption properties are used to map a specific portion of the retinal vascular structure. The advantages of retinal scanning are its reliance on the unique characteristics of each person’s retina, as well as the fact that the retina generally remains fairly stable throughout life. Disadvantages of retinal scanning include the need for fairly close physical contact with the scanning device. Also, trauma to the eye and certain diseases can change the retinal vascular structure, and there also are concerns about public acceptance.

Voice Recognition

Voice or speaker recognition uses vocal characteristics to identify individuals using a pass-phrase (Campbell, 1997). It involves taking the acoustic signal of a person’s voice and converting it to a unique digital code that can be stored in a template. Voice recognition systems are extremely well-suited for verifying user access over a telephone. Disadvantages of this biometric are that not only is a fairly large byte code required, but also, people’s voices can change (for example, when they are sick or in extreme emotional states). Also, phrases can be misspoken and background noises can interfere with the system.

Signature Verification

It is an automated method of examining an individual’s signature. This technology examines dynamics such as speed, direction and pressure of writing; the time that the stylus is in and out of contact with the “paper”; the total time taken to make the signature; and where the stylus is raised from and lowered onto the “paper”. Signature verification templates are typically 50 to 300 bytes. The key is to differentiate between the parts of the signature that are habitual and those that vary with almost every signing. Disadvantages include problems with long-term reliability, lack of accuracy and cost.

Hand/Finger Geometry

Hand or finger geometry is an automated measurement of many dimensions of the hand and fingers. Neither of these methods takes actual prints of palm or fingers. Only the spatial geometry is examined as the user puts a hand on the sensor’s surface. Hand geometry templates are typically 9 bytes, and finger geometry templates are 20 to 25 bytes. Finger geometry usually measures two or three fingers, and thus requires a small amount of computational and storage resources. The problems with this approach are that it has low discriminative power, the size of the required hardware restricts its use in some applications and hand geometry-based systems can be easily circumvented 9 .

Palm Print

Palm print verification is a slightly modified form of fingerprint technology. Palm print scanning uses an optical reader very similar to that used for fingerprint scanning; however, its size is much bigger, which is a limiting factor for use in workstations or mobile devices.

Keystroke Dynamics

Keystroke dynamics is an automated method of examining an individual’s keystrokes on a keyboard (Monrose, 2000). This technology examines dynamics such as speed and pressure, the total time of typing a particular password and the time that a user takes between hitting keys—dwell time (the length of time one holds down each key) as well as flight time (the time it takes to move between keys). Taken over the course of several login sessions, these two metrics produce a measurement of rhythm unique to each user. Technology is still being developed to improve robustness and distinctiveness.

Vein Patterns

Vein geometry is based on the fact that the vein pattern is distinctive for various individuals. Vein measurement generally focuses on blood vessels on the back of the hand. The veins under the skin absorb infrared light and thus have a darker pattern on the image of the hand. An infrared light combined with a special camera captures an image of the blood vessels in the form of tree patterns. This image is then converted into data and stored in a template. Vein patterns have several advantages: First, they are large, robust internal patterns. Second, the procedure does not implicate the criminal connotations associated with the taking of fingerprints. Third, the patterns are not easily damaged due to gardening or bricklaying. However, the procedure has not yet won full mainstream acceptance. The major disadvantage of vein measurement is the lack of proven reliability 9 .


DNA sampling is rather intrusive at present and requires a form of tissue, blood or other bodily sample 9 . This method of capture still has to be refined. So far, DNA analysis has not been sufficiently automatic to rank it as a biometric technology. The analysis of human DNA is now possible within 10 minutes. If the DNA can be matched automatically in real time, it may become more significant. At present, DNA is very entrenched in crime detection and will remain in the law enforcement area for the time being.

Ear Shape

Identifying individuals by ear shape is used in law enforcement applications where ear markings are found at crime scenes (Burge, 2000). Problems are faced whenever the ear is covered by hair.

Body Odor

The body odor biometrics is based on the fact that virtually every human’s smell is unique. The smell is captured by sensors that are capable of obtaining the odor from non-intrusive parts of the body, such as the back of the hand. The scientific basis is that the chemical composition of odors can be identified using special sensors. Each human smell is made up of chemicals known as volatiles. They are extracted by the system and converted into a template. The use of body odor sensors broaches on the privacy issue, as the body odor carries a significant amount of sensitive personal information. It is possible to diagnose some disease or activities in last hours by analyzing body odor.


Performance Measurements

The overall performance of a system can be evaluated in terms of its storag e, speed and accurac y. The size of a template, especially when using smart cards for storage, can be a decisive issue during the selection of a biometric system. Iris scan is often preferred over fingerprinting for this reason. Also, the time required by the system to make an identification decision is important, especially in real-time applications such as ATM transactions.

Accuracy is critical for determining whether the system meets requirements and, in practice, the way the system responds. It is traditionally characterized by two error statistics: False Accept Rate ( FAR) (sometimes called False Match Rate), the percentage of impostors accepted; and False Reject Rate ( FRR ), the percentage of authorized users rejected. These error rates come in pairs: For each false-reject rate there is a corresponding false alarm. In a perfect biometric system, both rates should be zero. Unfortunately, no biometric system today is flawless, so there must be a trade-off between the two rates. Usually, civilian applications try to keep both rates low. The error rate of the system when FAR equals FRR is called the Equal Error Rate , and is used to describe performance of the overall system. Good biometric systems have error rates of less than 1%. This should be compared to error rates in current methods of authentication, such as passwords, photo IDs, handwritten signatures and so forth. Although this is feasible in theory, practical comparison between different biometric systems when based on different technologies is very hard to achieve. The problem with the system is that people’s physical traits change over time, especially with alterations due to accident or aging. Problems can occur because of accident or aging, humidity in the air, dirt and sweat (especially with finger or hand systems) and inconsistent ways of interfacing with the system.

According to the Biometric Working Group (founded by the Biometric Consortium), the three basic types of evaluation of biometric systems are: technology, scenario and operational evaluation 9 .

The goal of a technology evaluation is to compare competing algorithms from a single technology. The use of test sets allows the same test to be given to all participants. The goal of scenario testing is to determine the overall system performance in a single prototype or simulated application to determine whether a biometric technology is sufficiently mature to meet performance requirements for a class of applications. The goal of operational testing is to determine the performance of a complete biometric system in a specific application environment with a specific target population, to determine if the system meets the requirements of a specific application.

Problems of Using Biometric Identification

Different technologies may be appropriate for different applications, depending on perceived user profiles, the need to interface with other systems or databases, environmental conditions and a host of other application-specific parameters.Biometrics has some drawbacks and loopholes. Some of the problems associated with biometrics systems are as follows:

  • Most of the technologies work well only for a “small” target population: Only two biometric technologies, fingerprinting and iris scanning, have been shown in independent testing to be capable of identifying a person from a group exceeding 1,000 people. Three technologies—face, voice and signature—have been shown in independent testing to be incapable of singling out a person from a group exceeding 1,000. This can be a big problem for large-scale use 2.
  • The level of public concern about privacy and security is still high: Privacy issues are defined as freedom from unauthorized intrusion. It can be divided into three distinct forms:

    • Physical privacy, or the freedom of individual from contact with others.
    • Informational privacy, or the freedom of individuals to limit access to certain personal information about oneself.
    • Decision privacy, or the freedom of individuals to make private choices about personal and intimate matters.
    Public resistances to these issues can be a big deterrent to widespread use of biometric-based identification.
  • Biometric technologies do not fit well in remote systems. If verification takes place across a network (the measurement point and the access control decision point are not colocated), the system might be insecure. In this case, attackers can either steal the person’s scanned characteristic and use it during other transactions or inject their characteristic into the communication channel. This problem can be overcome by the use of a secure channel between the two points.
  • Biometric systems do not handle failure well. If someone steals one’s template, it remains stolen for life. Since it is not a digital certificate or a password, you cannot ask the bank or some trusted third party to issue a new one. Once the template is stolen, it is not possible to go back to a secure situation.


The world would be a fantastic place if everything were secure and trusted. But unfortunately, in the real world there is fraud, crime, computer hackers and theft. So there is need of something to ensure users’ safety. Biometrics is one method that can give optimal security to users in the available resource limitations. Some of its ongoing and future applications are:

  • Physical access
  • Virtual access
  • E-commerce applications
  • Corporate IT
  • Aviation
  • Banking and financial
  • Healthcare
  • Government

This article presents an overview of various biometrics technologies’ performance, application and problems. Research is going on to provide a secure, user-friendly and cost-effective biometrics technology.

Biometrics, A Critical Consideration in Information Security Management - INTRODUCTION, BACKGROUND, BIOMETRICS TECHNOLOGIES, Retina and Iris Scanning, Fingerprint Scanning, Facial Recognition, Voice Recognition, PRACTITIONER IMPLICATIONS [next] [back] Biological Photography - Introduction and History, Subject Handling, Aquatic Subjects, Backgrounds, Photography in the Field

User Comments

Your email address will be altered so spam harvesting bots can't read it easily.
Hide my email completely instead?

Cancel or

Vote down Vote up

over 2 years ago

thanks this thigy really halped!!!!!!!!!!!

Vote down Vote up

over 2 years ago

a nice one but how can we create it at home and link to our website

Vote down Vote up

over 2 years ago

Do you happen to have any technology in which you can scan your finger or heart rate to find a persons mood..<3

Vote down Vote up

about 3 years ago

after going through this article, i found it to be very useful t; my research work

Vote down Vote up

almost 4 years ago

A good overview.

As an update, Vein recognition has been successfully tried in rural areas with the user base over 100,000 users. In fact, Vein Recognition is gaining popularity more than IRIS for the Rural Market.

Moreover, different environments and situations decide which technology has a discreet advantage over the other

It would help if a comparision is made on the applicability factor for each technology.