BIOMETRICS

BY

Lt Cdr V Pravin

05IT6019

SIT,IIT KGP

GUIDED BY

Prof D Samanta

SIT,IIT KGP

ABSTRACT- BIOMETRICS

Biometrics is a means of using parts of the human body as a kind of permanent password. Just as fingerprints are unlike those of any other person, your eyes, ears, hands, voice, and face are also unique. Technology has advanced to the point where computer systems can record and recognize the patterns, hand shapes, ear lobe contours, and a host of other physical characteristics. Using biometrics, devices can be empowered with the ability to instantly verify your identity and deny access to everybody else. Using biometrics for identifying and authenticating human beings offers unique advantages over traditional methods. Tokens, such as smart cards, magnetic stripe cards, and physical keys can be lost, stolen, or duplicated. Passwords can be forgotten, shared, or unintentionally observed by a third party. Forgotten passwords and lost smart cards are a nuisance for users and waste the expensive time of system administrators. In biometrics the concerned person himself is the password, as biometrics authentication is based on the identification of an intrinsic part of a human being.

CONTENTS

  1. Introduction
  1. General system
  1. Finger Print
  1. Iris
  1. Performance
  1. Application
  1. Conclusion
  1. References

Introduction

Biometrics is a means of using parts of the human body as a kind of permanent password. Just like our fingerprints are unlike those of any other person, your eyes, ears, hands, voice, and face are also unique. Technology has advanced to the point where computer systems can record and recognize the patterns, hand shapes, ear lobe contours, and a host of other physical characteristics. Using biometrics, devices can be enabled with the ability to instantly verify identity and deny access to everybody else.

Using biometrics for identifying and authenticating human beings offers unique advantages over traditional methods. Tokens, such as smart cards, magnetic stripe cards, and physical keys can be lost, stolen, or duplicated. Passwords can be forgotten, shared, or unintentionally observed by someone. Forgotten passwords and lost smart cards are a problem for users. In biometrics the concerned person himself is the password, as biometrics authentication is based on the identification of an intrinsic part of a human being.

The biometrics technique can be integrated into applications that require security, access control, and identification or verification of users. Biometrically secured resources effectively eliminate risks, while at the same time offering a high level of security and convenience to both the users and the administrators.

Biometric systems automatically verify or recognize the identity of a living person based on physiological or behavioral characteristics. Physiological characteristics pertain to visible parts of the human body. These include fingerprint, retina, palm geometry, iris, facial structure, etc. Behavioral characteristics are based on what a person does. These include voice prints, signatures, typing patterns, key-stroke pattern, gait, and so on. A variety of factors, such as mood, stress, fatigue, and how long ago you woke up, can affect behavioral characteristics.

History
Fingerprints were first used to identify individuals in ancient China. The first commercial use of biometrics was in the 1960's and 1970's. In the late 1960's FBI developed a system for automatically checking /comparing and verifying fingerprints. In early 1970's FBI installed automatic fingerprinting scanning systems .During the late 1970's Idnetiymat installed the first biometrics physical access control systems in top secret US Government sites. The system was based on Hand Geometry. During late 1970s development of voice recognition systems began and in the .1980'sBiometrics systems using Iris scan and that with face recognition system developed.

System:

A generic biometric model consists of five subsystems, namely, data collection,transmission, signal processing, decision making and data storage. Data collection involves user of sensors to detect and measure an individual’s physiological or behavioral characteristics.


Biometric model

Finger print recognition

Among all the Biometric techniques, fingerprint based identification is the oldest method which has been successfully used in numerous applications. Every person’s fingerprint is unique and is a feature that stays with the person throughout his/her life. This makes the fingerprint the most reliable kind of personal identification because it cannot be forgotten, misplaced, or stolen. Fingerprint authorization is potentially the most affordable and convenient method of verifying a person's identity. This fact has been utilized for restricting the access to individuals in high security areas.

The Basics of Fingerprint identification

The skin on the inside surfaces of our hands, fingers, feet, and toes is “ridged” or covered with concentric raised patterns. These ridges are called friction ridges and they serve the useful function of making it easier to grasp and hold onto objects and surfaces without slippage. It is the many differences in the way friction ridges are patterned, broken, and forked which make ridged skin areas, including fingerprints, unique.

Global Versus Local Features

We make use of two types of fingerprint characteristics for use in identification of individuals: Global Features and Local Features. Global Features are those characteristics that you can see with the naked eye. Global Features include:

  • Basic Ridge Patterns
  • Pattern Area
  • Core Area
  • Delta
  • Type Lines
  • Ridge Count

The Local Features are also known as Minutia Points. They are the tiny, unique characteristics of fingerprint ridges that are used for positive identification. It is possible for two or more individuals to have identical global features but still have different and unique fingerprints because they have local features - minutia points - that are different from those of others.

Fingerprint Scanning

Fingerprint scanning is the acquisition and recognition of a person’s fingerprint characteristics for identification purposes. This allows the recognition of a person through quantifiable physiological characteristics that verify the identity of an individual.

There are basically two different types of finger-scanning technology that make this possible. One is an optical method, which starts with a visual image of a finger. The other was a semiconductor-generated electric field to image a finger.

There are different ways to identify fingerprints. They include traditional police methods of matching minutiae, straight pattern matching, moiré fringe patterns and ultra sonic.

Fingerprint Matching

Fingerprint matching techniques can be placed into two categories: minutiae-based and correlation based. Minutiae-based techniques first find minutiae points and then map their relative placement on the finger. However, there are some difficulties when using this approach. It is difficult to extract the minutiae points accurately when the fingerprint is of low quality. Also this method does not take into account the global pattern of ridges and furrows. The correlation-based method is able to overcome some of the difficulties of the minutiae-based approach. However, it has some of its own shortcomings. Correlation-based techniques require the precise location of a registration point and are affected by image translation and rotation.

Fingerprint Classification

Large volumes of fingerprints are collected and stored everyday in a wide range of applications including forensics, access control, and driver license registration. An automatic recognition of people based on fingerprints requires that the input fingerprint be matched with a large number of fingerprints in a database To reduce the search time and computational complexity, it is desirable to classify these fingerprints in an accurate and consistent manner so that the input fingerprint is required to be matched only with a subset of the fingerprints in the database.

Fingerprint classification is a technique to assign a fingerprint into one of the several pre-specified types already established in the literature which can provide an indexing mechanism. Fingerprint classification can be viewed as a coarse level matching of the fingerprints. An input fingerprint is first matched at a coarse level to one of the pre-specified types and then, at a finer level, it is compared to the subset of the database containing that type of fingerprints only. We have developed an algorithm to classify fingerprints into five classes, namely, whorl, right loop, left loop, arch, and tented arch.

Image capture

There are two approaches for capturing the fingerprint image for matching: minutia matching and global pattern matching. Minutia matching is a more microscopic approach that analyzes the features of the fingerprint, such as the location and direction of the ridges, for matching. The only problem with this approach is that it is difficult to extract the minutiae points accurately if the fingerprint is in some way distorted. The more macroscopic approach is global pattern matching where the flow of the ridges is compared at all locations between a pair of fingerprint images; however, this can be affected by the direction that the image is rotated.

Types of scanners

  • Optical Scanner - captures a fingerprint image using a light source refracted through a prism
  • Thermal Scanner - very small sensor that produces a larger image of the finger and is contrast-independent
  • Capacitive Scanner - uses light to illuminate a finger placed on a glass surface and records the reflection of this light with a solid-state camera

Each of these devices use light to measure the ridges and non-ridges, take an original fingerprint image, capture the minutia points and create an identifying template from the minutia points.

Image Processing

Following the image capture, image processing is performed to achieve a definitive match on the individual. At this stage, image features are detected and enhanced for verification against the stored minutia file. Image enhancement is used to reduce any distortion of the fingerprint caused by dirt, cuts, scars, sweat and dry skin.

Image Verification

At the verification stage, the image of the fingerprint is compared against the authorized user’s minutia file to determine a match and grant access to the individual.

Potential Issues

Although fingerprint recognition is the cheapest form of biometric security available and is widely accepted by public and law enforcement communities as reliable identification, its disadvantage is that it requires close physical contact with scanning device. Some other issues includes

  • Privacy
  • False Rejection
  • False Acceptance
  • Accuracy

(a) Privacy: Comparison and storage of unique biological traits makes some individuals feel that their privacy is being invaded. Many associate fingerprint scanning with the fingerprinting of alleged criminals and are therefore hesitant to accept this technology.

(b) False Rejection Rate (FRR): False rejection occurs when a registered user does not gain access to the system. This person has then been falsely rejected from access.

(c) False Acceptance Rate (FAR): False acceptance is when an unauthorized user gains access to a biometrically protected system.

(d) Accuracy: Although fingerprints are unique to an individual, there are instances where a fingerprint may become distorted and authorization will not be granted to the user. As discussed above in image processing, dirt, cuts, scars, sweat and dry skin can cause fingerprint distortion.

Iris recognition

Introduction

Iris recognition combines computer vision, pattern recognition, statistics, and the human-machine interface. The purpose is real-time, high confidence recognition of a person's identity by mathematical analysis of the random patterns that are visible within the iris of an eye from some distance. Because the iris is a protected internal organ whose random texture is stable throughout life, it can serve as a kind of living passport or a living password that one need not remember but one always carries along. The iris’s random patterns are unique to each individual — a human “bar code” or living passport. No two irises are alike. Each person has a distinct pattern of filaments, pits and striations in the colored rings surrounding the pupil of each eye. This pattern is stable throughout life. Unlike fingerprints, iris “prints” are not subject to environmental damage. An internal organ, the iris is protected by the cornea. Because these structures are transparent, the iris can be easily identified with a high degree of certainty up to three feet away.
.

Iris Acquisition

The first step is location of the iris by a dedicated camera no more than 3 feet from the eye. The monochrome camera uses both visible and infrared light, the latter of which is located in the 700-900nm range.

Iris

The retina, a thin nerve (1/50th of an inch) on the back of the eye, is the part of the eye which senses light and transmits impulses through the optic nerve to the brain - the equivalent of film in a camera. Blood vessels used for biometric identification are located along the neural retina, the outermost of retina's four cell layers.

Iris scan

These systems take advantage of random variations in the visible features the iris, the colored ring around the pupil. After a iris has been scanned once, a unique file is placed in a database. Iris scanning takes advantage of random variations in the visible features the iris, the colored part of the eye. The iris consists largely of a system of muscle that expands and contract the pupil in response to changing lighting conditions. The details of each iris are unique, that is, no two are exactly alike, not even among twins, not even in your own two eyes. The structure of the iris develops in the embryo, assuming its lifelong character by the seventh or eighth month. Some color changes can occur in the first months of life, which explains why some babies who are born with blue eyes may end up with brown or some other color.

After taking a picture of the eye, the system samples the radial and angular variations of each individual iris to form an Iris Code, a digital file that serves as a reference in database. At 512 bytes, the file is quite small, since it is a hexadecimal code reference rather than an actual iris image. Research confirms an extraordinarily high level of statistical reliability for the system. A person using the system simply looks into a camera. The computer program then locates the iris. Next, the system locates the iris' outer and inner edges. The monochrome camera uses both visible and infrared (700-900nm) light. The program maps segments of the iris into hundreds of vectors. Position, orientation and spatial frequency provide the basis for calculation of the Iris Code. The system also manages to take into account normal changes in the eye. For example, the system compensates for papillary expansion and contraction. It can also detect reflections from the cornea.

Drawbacks

Iris Scanning offers numerous benefits over other biometrics, although there are a few definite issues surrounding this technology. First and foremost, iris scanning is fairly expensive. Iris scanning produces an accurate image with any number of distractions, but it still depends on usercooperation; a user must know he is being scanned and agree to it for the scan to work. This is because a person must sit quite still – even just momentarily – to get an accurate scan.

How Is the Performance of a Biometric Measured

Biometric performance is most commonly measured in two ways: False RejectionRate (FRR), and False Acceptance Rate (FAR). The FRR is the probability that are not authenticated to access your account. A strict definition states that the FRR is the probability that a mated comparison (i.e. 2 biometric samples of the same eye) incorrectly determines that there is no match. The FAR is the chance that someone other than you is granted access to your account, in other words, the probability that a non-mated comparison (i.e. two biometric samples of different eye) match. FAR and FRR numbers are generally expressed in terms of probability. When comparing biometric systems, a low false acceptance rate is most important when security is the priority. Whereas, a low false rejection rate is most important when convenience is the priority. All biometric implementations balance these two criteria. Some systems use very high FAR's such as 1 in 300. This means that the likelihood that the system will accept someone other than the enrolled user is 1 in 300. However, the likelihood that the system will reject the enrolled user (its FRR) is very low, giving them ease of use, but with low security. Most iris scan systems should be able to run with FAR’s of 1 in 1,000,000or better.

Another factor that must be taken into account when determining the necessary FAR and FRR for the organization is the actual quality of the database in the user population. Experience with several thousand users, and the experience of its customers, indicates that a percentage of the population do not have database of sufficient quality to allow for authentication of the individual. In the general office worker population approximately 2.5% of employees fall into this group. For these users, a smartcard token with password authentication is recommended. Statistical improvements in false rejection rates can also be achieved by requiring the user to use more than one eye to authenticate. Such techniques are referred to as flexible verification. Within the industry, FAR and FRR numbers are often quoted by competing vendors.

However, the environments and testing methodologies, which are used to arrive at these statistics, vary greatly. Therefore, the reported FAR and FRR cannot be relied upon as a definitive measure of performance. Most companies when publishing their FRR only publish the 2 or 3 test attempt statistic. Furthermore, it is continually enhancing the hardware and software to improve the security and usability of the products, which mean the numbers are constantly improving.