Over the last few years a new area of engineering science has been established whose products are likely to create a large market in the near future. It has been called ''biometrics". The pioneers of this new domain intend to construct devices which would allow identification of a person on the basis of his/her ''biological'' characteristics: voice, dynamics of movements, features of face and other parts of the body, retina or iris pattern. Nature has made human beings with different characteristics which may vary from one person to another. This property is made use of by Biometric technology to distinctly identify each person
Biometric system is essentially a pattern recognition system which recognizes a user by determining the authenticity of a specific physiological or behavioral characteristic possessed by the user. Several important issues must be considered in designing a practical biometric system. First, a user must be enrolled in the system so that his biometric template can be captured. This template is securely stored in a central database or a smart card issued to the user. The template is retrieved when an individual needs to be identified. Depending on the context, a biometric system can operate either in a verification (authentication) or an identification mode.
Biometrics refers to the automatic identification of a person based on his/her physiological or behavioral characteristics. This method of identification offers several advantages over traditional methods involving ID cards (tokens) or PIN numbers (passwords) for various reasons: (i) the person to be identified is required to be physically present at the point-of-identification; (ii) identification based on biometric techniques obviates the need to remember a password or carry a token. With the increased integration of computers and Internet into our everyday lives, it is necessary to protect sensitive and personal data. By replacing PINs (or using biometrics in addition to PINs), biometric techniques can potentially prevent unauthorized access to ATMs, cellular phones, laptops, and computer networks. Unlike biometric traits, PINs or passwords may be forgotten, and tokens like passports and driver's licenses may be forged, stolen, or lost.
This paper gives an overview of key biometric technologies and basic technique involved. The various opportunities for biometrics are mentioned, followed by the uses, benefits, drawbacks, and applications.
The first modern biometric device was introduced on a commercial basis over 25 years ago when a machine that measured finger length was installed for a time keeping application at Shearson Hamil on Wall Street. In the ensuing years, hundreds of these hand geometry devices were installed at high security facilities operated by Western Electric, Naval Intelligence, the Department of Energy, and the like. There are now over 20,000 computer rooms, vaults, research labs, day care centers, blood banks, ATMs and military installations to which access is controlled using devices that scan an individual's unique physiological or behavioral characteristics. Reduced prices have lead to increased awareness of biometric technologies; this coupled with lower overall prices will certainly bode well for this industry as we move through the new millennium.
The term biometrics refers to the emerging field of technology devoted to the identification of individuals using biological traits or behaviors. In practice, this means capturing an image of a unique feature of an individual such as a fingerprint, hand, eye or face, and comparing it with a template captured previously. For ease of explanation this has been over-simplified, but in essence this is how biometric technology works.
The statistical use of the characteristic variations in unique elements of living organisms is known as biometrics.
Why we need biometrics?
In order to avoid the problems of forgetting passwords and ID codes, Biometrics based authentication helps us in verifying your finger prints, iris pattern and voice for your identity at A.T.M’s, Airports etc.., you can unlock your houses, withdrawing money from a bank with just a blink of an eye, a tap of your finger or by just showing your face.
Biometrics-what is it?
Biometrics refers to the automatic identification of a person based on his/her physiological or behavioral characteristics. This method of identification is preferred over traditional methods involving password’s and PIN numbers for various reasons:
(i) The person to be identified is required to be physically present at the point of identification.
(ii) Identification based on biometric techniques obviates the need to remember a password or carry a token. By replacing PIN’s, biometric techniques can potentially prevent unauthorized access to or fraudulent use of A.T.M‘s, Smart cards, computer networks.
(iii) PIN‘s passwords may be forgotten, and token based methods of identification like passwords and driver’s licenses may be forged, stolen or lost. A biometric system is essentially a pattern recognition system which makes a personal identification by determining the authenticity of a specific physiological or behavioral characteristic possessed by the user.
Design issues of biometric systems:
An important issue in designing a practical system is to determine how an individual is identified and are designed by keeping two characteristics in mind, they are: Physical characteristics
- Iris Pattern
- Acoustic Signature
- Depending on the context a biometric system can be either a verification(authentication) system or an identification system
Verification Vs Identification:
There are two different ways to resolve a person’s identity: verification and identification. Verification (Am I whom I claim I am?) involves confirming are denying a person’s claimed identity. In identification, one has to establish a person’s identity (Who am I?). Each one of these approaches has its own complexities and could probably be solved best by a certain biometric system.
Types of biometric devices and their services:
Now let’s see some of the biometric devices being widely used in many areas like computer/network security, government organizations, prisons…. They are:
F Fingerprint identification.
F Face recognition.
F Iris recognition.
F Hand geometry.
F Signature recognition.
F Retinal scanning
F Voice verification….
And now let’s see some of these biometric devices, their services, advantages and disadvantages in detail.
Finger prints are unique to each individual and no two fingerprints are alike. Fingerprint recognition is most widely accepted biometric among the technology being used today. Fingerprints contain patterns of ridges and valleys as well as minutiae points. Minutiae points are local ridge characteristics that occur at either the ridge bifurcation or a ridge ending.
There are three methods for scanning finger prints:
(1) Optical scanners,
(2) Thermal scanners and
(3) Capacitance (solid state) scanners
Currently, there are two accepted methods for extracting the fingerprint data
(I) Minutia-based and
“Minutia-based is the more microscopic of the two. This method locates the ridge characteristics (branches and endings) and assigns them a XY-coordinate that is then stored in a file.
The correlation-based method looks at the entire pattern of ridges and valleys in the fingerprint. The location of the whorls, loops and arches and the direction that they flow in are extracted and stored. Neither method actually keeps the captured image; only the data is kept, therefore making it impossible to recreate the fingerprints.”
Once the scanning is complete, the analysis is done by a comparison of several features of the fingerprint know as minutia. Investigators are systems look at where the ridge lines end or where one ridge splits into two (bifurcation). The scanning system uses complicated algorithms to recognize and analyze the minutia. If two prints have three ridge endings, two bifurcations, and form the same shape with the same dimensions, then it is likely the same person’s fingerprints.
· High accuracy rate.
· Can perform 1-to-many comparisons.
· Inexpensive equipment.
· Easy to use (samples are easy to capture and maintain).
· Most established and oldest of the biometric technology.
· Actual finger scan images cannot be recreated from a template image
· Users relate fingerprint recognition to criminal activity.
Face (or Facial) recognition:
Face recognition is one of the newer biometrics technologies. The technology analyzes facial characteristics and attempts to match it to database of digitized pictures. This technology is relatively new and has only been commercially available since the 1990’s. Face recognition has received a surge of attention since of disaster of 11/9 for its ability to identify known terrorists and criminals.
Face recognition uses distinctive features of the face –including the upper outlines of the eye socket, the areas surrounding the cheekbones, the sides of the mouth, and the location of the nose and ears – to perform verification and identification. The first step in the face recognition is to obtain an image of an individual and store it in a database for later use. Usually, several pictures (or video images) at different angles are taken. Individuals may also be asked to make different facial expressions for the data base. Next, the images are analyzed and extracted to create a template. The last step is to verify the individual’s identity by matching images to those images that been stored in database.
There are four main methods being used for facial recognition:
· Eigenfaces: a tool developed by MIT that extracts characteristics through the use of two-dimensional grayscale imagery.
· Feature Analysis (also known as Local Feature Analysis (LFA)): is the most widely used technique because of its ability to accommodate for facial changes and aspect. LFA uses an algorithm to create a face print (84 bytes in size) for comparison.
· Neural network: a method that extracts features from the face and create a template of contrasting elements that is then matched to a template in database.
· Automated Face Processing (AFP): a technique that looks for distances and ratios between certain facial features, and is more ideal for poorly lit areas.
· High accuracy rate.
· Can be performed from a distance.
· Accepted by most users.
· Cannot not always account for the effects of aging.
· Sensitive to lighting conditions.
· Can perform limited 1-to-many comparisons.
No two irises are alike, not even in one individual or in identical twins. The iris consists of over 400 distinguished characteristics. Compared to the 40 or 50 points of distinct fingerprint characteristics, the iris has more than 250 distinct features. Therefore, iris scanning is much more accurate than fingerprints or even DNA analysis of the distinguishing features.
Iris scanning is executed by scanning the measures of the colored circle that
surrounds the pupil. With video technology, a camera scans the iris pattern, which consists of corona, pits, filaments, crypts, striations, and radial furrows (page). The system software then digitizes the unique information of the iris and stores it for authentication at a later time. Iris scanning is easy, accurate, and convenient. One significant downfall of Iris recognition is the initial startup costs as they are extremely high.
In identifying one’s Iris, there are two types of methods that are used by Iris identification systems, passive and active. The active Iris system method requires that a user be anywhere from six to 14 inches away from the camera. It also requires the user to move back and forth so that the camera can adjust and focus in on the user’s iris. The passive system allows the user to be anywhere from one to three feet away from the camera(s) that locate and focus in on the iris.
This technology’s main uses are for authentication, identification, and verification of an individual.
· High accuracy rate
· Imitation is almost impossible
· perceived to be intrusive and invasive
· Can be done from a short distance
· optical readers are difficult to operate requiring advanced training for employees
Hand geometry is concerned with measuring the physical characteristics of the user’s hand and fingers and it is believed to be sufficiently unique for use as a means of biometric authentication. The technology records various dimensions of the human hand, it is relatively easy to use, and offers a good balance of performance characteristics. Reader configurations vary among a softball-shaped device which the subject grabs in his hand and a flat plate which the subject places his/her hand, a bar which the subject grabs as if opening a door, and a flat plate which the subject places his/her hand on.
Hand geometry readers are developed in a wide range of scenarios, including time and attendance recording where they have proved extremely popular. The methodology may be suitable where there is a large user base or there are users who access the system infrequently. Accuracy can be very high if desired.
Hand geometry readers are relatively large and expensive but the ease of integration into other systems and processes, small template size (only 9 bytes for pure hand geometry template) and ease of use makes it a good choice for many projects.
Hand geometry Vs Fingerprints:
Unlike fingerprints the human hand isn’t unique. One can use finger length, thickness and curvature for the purposes of verification but not for identification. For some kinds of access control like immigration and border control, invasive biometrics (e.g., fingerprints) may not be desirable as they infringe on privacy. In such situations it is desirable to have a biometric system that is sufficient for verification. As hand geometry is not distinctive, it is idle choice. Further more, hand geometry data is easier to collect. With fingerprint collection good frictional skin is required by imaging systems, and with retina-based recognition systems, special lighting is necessary. Additionally, hand geometry can be easily combined with other biometrics, namely fingerprint. One can envision a system where fingerprints are used for (in frequent) identification and hand geometry is used for (frequent) verification.
The uses for biometric security are varied and growing. It was developed in response to a need to associate human action with identity – whether conducting a transaction, accessing a computer or a critical information system, or entering secure physical area. Some of the existing and proposed applications in general we use are described below:
Many stand-alone and network computer systems carry valuable and sensitive information. Controlling access to these systems is another major use of biometric authentication systems.
Due to growing security requirements that results from the boom in e-commerce, many think of on-line transactions as being an obvious area for biometrics. The biometric authentication generates a greater degree of vendor confidence because he knows that person that the person at the terminal is he who he claims to be.
Physical area security:
Military, Government, and Commercial installations have sufficiently strong confidentiality concerns. The biometric identifiers play a major role in controlling physical access to these installations.
Many leading banks have been experimenting with biometrics for ATM use as a means of combating card fraud. Beginning 2002, some companies will being issuing smart credits cards, with customer’s fingerprint information embedded.
A logical use of biometrics is in voting process where eligible politicians are required to verify their identity. This is intended to stop “proxy” voting.
An interesting use of biometrics is in prisons where the visitors to a prisoner are subjected to verification procedures in order that identities may not be swapped during the visit.
Leading products in biometrics: Biometric is a new but promising technology and therefore a number of companies have appeared in the market in a very short period of time. Some of those products are:
The advances in accuracy and usability and decreasing cost have made the biometric technology a secure, affordable and cost effective way of identifying individuals. Biometric parameters such as fingerprint scanning, iris scanning, retinal scanning, hand geometry, signature verification, voice verification and others are all well established with their own particular characteristics. The limiting factors of speed and band width are now a thing of the past and their practical performance might in many instances be better than expected. Today, it is an efficient and effective method of replacing passwords, tokens and smart cards.
It is important to recognize that although biometric authentication has served extensively in high security applications in defense industry, it is still fledgling technology in commercial world, both in terms of its technical sophistication and current extent of deployment. There are no established standards for biometric system architecture, for template formation, or even for biometric reader testing. It is also not clear as which technology or technologies will dominate the customer market. In the absence of standards and direction, the rapid and wide spread deployment of biometric authentication system could easily facilitate the problematic proliferation of authentication and tracking of the people.