Submitted to
Mr.Gaurav Chandiok
Department of IT, ABS
Submitted by
310B14 – Sahil Behl
310B39 – Anuja Sharma
310B41- Abhishek Gupta
1
TABLE OF CONTENTS
1) ……………………………………..3
2) Certificate………………………………………...….4
3) Introduction………………………………………….5
4) Definition of biometrics…………………...………..7
5) Finger recognition………………………..…………10
6) Face recognition…………………………….………14
7) Hand geometry……………………………….……..16
8) Iris recognition…………………………….………..18
9) Voice recognition……………………………..…….21
10) Signature recognition………………..……….……..23
11) Application of biometrics………………..………….26
12) Appendix………………………………………..…..27
2
Table of Pictures
1) General biometric model…………………………………………….9
2) Finger print scanning………………………………………………..10
3) Finger print verification (fig a)……………………………………...11
4) Finger print biometric system (fig b)………………………………..11
5) Iris recognition biometric system……………………………………18
6) Structure of iris……………………………………………...……….18
7) Multi biometric system………………………………………….…..24
3
CERTIFICATE
INTRODUCTION
4
What is Biometrics?
"Biometrics" means "life measurement" but the term is usually associated with
the use of unique physiological characteristics to identify an individual. The
application which most people associate with biometrics is security. However,
biometrics identification has eventually a much broader relevance as computer
interface becomes more natural. Knowing the person with whom you are
conversing is an important part of human interaction and one expects
computers of the future to have the same capabilities.
A number of biometric traits have been developed and are used to authenticate
the person's identity. The idea is to use the special characteristics of a person to
identify him. By using special characteristics we mean the using the features
such as face, iris, fingerprint, signature etc.
Background Concepts
6
6. Reducibility: The captured data should be capable of being reduced to a
file which is easy to handle.
7. Reliability and tamper-resistance: The attribute should be impractical to
mask or manipulate. The process should ensure high reliability and
reproducibility.
8. Privacy: The process should not violate the privacy of the person.
9. Comparable: Should be able to reduce the attribute to a state that makes
it digitally comparable to others. The less probabilistic the matching
involved, the more authoritative the identification.
10. Inimitable: The attribute must be irreproducible by other means. The
less reproducible the attribute, the more likely it will be authoritative.
The term "biometrics" is derived from the Greek words bio (life) and metric (to measure).
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 passwords and PIN numbers for its accuracy and case
sensitiveness. 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. An important issue in designing a
practical system is to determine how an individual is identified. Depending on the
context, a biometric system can be either a verification (authentication) system or an
identification system. Verification involves confirming or denying a person's claimed
identity while in identification, one has to establish a person's identity. Biometric systems
are divided on the basis of the authentication medium used. They are broadly divided as
identifications of Hand Geometry, Vein Pattern, Voice Pattern, DNA, Signature
Dynamics, Finger Prints, Iris Pattern and Face Detection. These methods are used on the
7
basis of the scope of the testing medium, the accuracy required and speed required. Every
medium of authentication has its own advantages and shortcomings.
The biometrics system requires scanners, digital image processor and complex
matching circuitry. The other thing is that in password security we have to remember the
password and it may leak out. But here in biometrics security the password is always
present as an indent which can neither be stolen nor is to be remembered.
History of Biometrics-
Biometric history indicates that the science did not originate at a single place. People all
over the world were using the basics for mainly identifying individuals from each other.
We'll explain about biometric history in brief over the next few paragraphs.
The history of biometrics dates back to a long time. Possibly the most primary known
instance of biometrics in practice was a form of finger printing being used in China in the
14th century, as reported by explorer Joao de Barros.
Barros wrote that the Chinese merchants were stamping children's palm prints and
footprints on paper with ink so as to differentiate the young children from one another.
This is one of the most primitive known cases of biometrics in use and is still being used
today.
Apart from its Chinese genesis, use of biometrics was also noted elsewhere in the world.
8
Up until the late 1800s, identification largely relied upon "photographic memory". In the
1890s, an anthropologist and police desk clerk in Paris, Alphonse Bertillon, decided to fix
the problem of identifying convicted criminals and turned biometrics into a distinct field
of study.
Bertillon developed a technique of multiple body measurements which later got named
after him - Bertillon age. His method was then used by police authorities throughout the
world, until it quickly faded when it was discovered that some people shared the same
measurements and based on the measurements alone, two people could get treated as one.
After the failure of Bertillon age, the police started using finger printing, which was
developed by Richard Edward Henry of Scotland Yard, essentially reverting to the same
methods used by the Chinese for years. (Which still is going strong?)
Biometric history in the recent past (three decades) has seen drastic advancements and
the technology have moved from a single method (fingerprinting) to more than ten
prudent methods. Companies involved with new methods have grown into the hundreds
and continue to improve their methods as the technology available to them also advances.
Prices for the hardware required continue to fall making systems more feasible for low
and mid-level budgets and thus making this more adaptable in small businesses and even
households.
As the industry grows however, so does the public concern over privacy issues. Laws and
regulations continue to be drafted and standards are beginning to be developed. While no
other biometric has yet reached the breadth of use of fingerprinting, some are beginning
to be used in both legal and business areas.
Types of Biometrics:
2. Physical biometrics
Matching Score
Decision
Making 95%
Data Collection
Verification
Making
Signal
Processin
g Enrollment
10
Storage
Biometrics security can be mainly classified as follows:
1) Finger recognition.
2) Hand geometry.
3) Face recognition.
4) Voice recognition.
5) Iris recognition
11
1. One is an optical method, which starts with a visual image of a finger.
2. The other uses a semiconductor-generated electric field to image a finger. There is a
range of ways to identify fingerprints. They include traditional police methods of
matching minutiae, straight pattern matching, moiré fringe patterns and ultrasonic.
Fig-a
101
0
110
IMAGE LIVE 1
UPDATE
101
0
12
Fig-b
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 matching based on minutiae has problems in
matching different sized (unregistered) minutiae patterns. Local ridge structures cannot
be completely characterized by minutiae. A commercial fingerprint-based authentication
system requires a very low False Reject Rate (FAR) for a given False Accept Rate
(FAR). This is very difficult to achieve with any one technique.
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 (FBI database contains
approximately 70 million fingerprints!). 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
13
fingerprints in the database. The algorithms are developed to classify fingerprints into
five classes, namely, whorl, right loop, left loop, arch, and tented arch. The algorithm
separates the number of ridges present in four directions (0degree, 45 degree, 90 degree,
and 135 degree) by filtering the central part of a fingerprint. The classifier is tested on
4,000 images in the database. . For the four-class problem (arch and tented arch
combined into one class), we are able to achieve a classification accuracy of 94.8%.
Someone may attempt to use latent print residue on the sensor just after a legitimate user
accesses the system. At the other end of the scale, there is the gruesome possibility of
presenting a finger to the system that is no longer connected to its owner. Therefore,
sensors attempt to determine whether a finger is live, and not made of latex (or worse).
Detectors for temperature, blood-oxygen level, pulse, blood flow, humidity, or skin
conductivity would be integrated.
Advantages:
d. Easy to use.
e. Small storage space required for the biometric template, reducing the size of the
database memory required
f. It is standardized.
Disadvantages:
a. For some people it is very intrusive, because is still related to criminal identification.
14
b. It can make mistakes with the dryness or dirty of the finger’s skin, as well as with the
age (is not appropriate with children, because the size of their fingerprint changes
quickly).
c. Image captured at 500 dots per inch (dpi). Resolution: 8 bits per pixel. A 500 dpi
fingerprint image at 8 bits per pixel demands a large memory space, 240 Kbytes
approximately → Compression required (a factor of 10 approximately).
FACE RECOGNITION:
Facial recognition systems are built on computer programs that analyze images of human
faces for the purpose of identifying them.
Computers can do increasingly amazing things, but they are not magic. If
human beings often can't identify the subject of a photograph, why should computers
15
be able to do it any more reliably? The fact is that faces are highly complex patterns
that often differ in only subtle ways, and that it can be impossible for man or machine
to match images when there are differences in lighting, camera, or camera angle, let
alone changes in the appearance of the face itself. Not surprisingly, government
studies of face-recognition software have found high rates of both "false positives"
(wrongly matching innocent people with photos in the database) and "false negatives"
(not catching people even when their photo is in the database). One problem is that
unlike our fingerprints or irises, our faces do not stay the same over time. These
systems are easily tripped up by changes in hairstyle, facial hair, or body weight, by
simple disguises, and by the effects of aging.
For example by study, it was found false-negative rates for face-recognition verification
of 43 percent using photos of subjects taken just 18 months earlier, for example. The
study also found that a change of 45 degrees in the camera angle rendered the software
useless. The technology works best under tightly controlled conditions, when the subject
is starting directly into the camera under bright lights.
In addition, questions have been raised about how well the software works on dark-
skinned people, whose features may not appear clearly on lenses optimized for light-
skinned-people.
Samir Nanavati of the International Biometric Group, a consulting firm, sums it up: "You
could expect a surveillance system using biometrics to capture a very, very small
percentage of known criminals in a given database."
It would work especially poorly in the frenetic environment of an airport, where fast-
moving crowds and busy background images would further reduce its already limited
effectiveness.
Advantages:
a. Non intrusive
16
b. Cheap technology.
Disadvantages
a. 2D recognition is affected by changes in lighting, the person’s hair, the age, and if the
person wear glasses.
b. Requires camera equipment for user identification; thus, it is not likely to become
popular until most PCs include cameras as standard equipment.
Every hand is unique. Hand geometry scanners such as those made by Recognition
Systems Inc. take over 90 measurements of the length, width, thickness, and surface area
of the hand and four fingers--all in just 1 second. The technology uses a 32,000-pixel
CCD digital camera to record the hand's three-dimensional shape from silhouetted images
projected within the scanner. The scanner disregards surface details, such as fingerprints,
lines, scars, and dirt, as well as fingernails, which may grow or be cut from day to day.
When a person uses the scanner, it compares the shape of the user's hand to a template
recorded during an enrollment session. If the template and the hand match, the scanner
produces an output--it may unlock a door, transmit data to a computer, verify
identification, or log the person's arrival or departure time. To register in a hand-scan
17
system a hand is placed on a reader’s covered flat surface. This placement is positioned
by five guides or pins that correctly situate the hand for the cameras. A succession of
cameras captures 3-D pictures of the sides and back of the hand. The attainment of the
hand-scan is a fast and simple process. The hand-scan device can process the 3-D images
in 5 seconds or less and the hand verification usually takes less than 1 second. The image
capturing and verification software and hardware can easily be integrated within
standalone units. Hand-scan applications that include a large number of access points and
users can be centrally administered, eliminating the need for individuals to register on
each device. The user's template may reside in internal memory or on other media such as
a hard disk or smart card chip.
Advantages:
a. Though it requires special hardware to use, it can be easily integrated into other
devices or systems.
c. The amount of data required to uniquely identify a user in a system is the smallest by
far, allowing it to be used with Smartcards easily.
Disadvantages:
a. Very expensive
b. Considerable size.
c. It is not valid for arthritic person, since they cannot put the hand on the scanner
properly.
APPLICATIONS:
18
Geometry scanners verify identity at the front entrances of over half the nuclear power
plants in the U.S. The U.S. Immigration and Naturalization Service (INS) use Rhand
geometry scanners to allow over 60,000 frequent travelers to bypass immigration lines
(through the INSPASS program). Employers use hand-scan for entry/exit, recording staff
movement and time/attendance procedures. The drastic reductions in cost of
microprocessors in recent years have brought affordable hand geometry technology to the
commercial market. Biometrics is no longer found only in nuclear power plants. Day care
centers, athletic clubs, obstetrics wards, and police departments now use scanners.
IRIS RECOGNITION:
Fig. a
19
Fig. b
Iris scan biometrics employs the unique characteristics and features of the human iris in
order to verify the identity of an individual. The iris is the area of the eye where the
pigmented or colored circle, usually brown or blue, rings the dark pupil of the eye. The
iris-scan process begins with a photograph. A specialized camera, typically very close to
the subject, no more than three feet, uses an infrared imager to illuminate the eye and
capture a very high-resolution photograph. This process takes only one to two seconds
and provides the details of the iris that are mapped, recorded and stored for future
matching/verification. Eyeglasses and contact lenses present no problems to the quality of
the image and the iris-scan systems test for a live eye by checking for the normal
continuous fluctuation in pupil size. The inner edge of the iris is located by an iris-scan
algorithm which maps the iris’ distinct patterns and characteristics. An algorithm is a
series of directives that tell a biometric system how to interpret a specific problem.
Algorithms have a number of steps and are used by the biometric system to determine if a
biometric sample and record is a match. Iris’ are composed before birth and, except in the
event of an injury to the eyeball, remain unchanged throughout an individual’s lifetime.
Iris patterns are extremely complex, carry an astonishing amount of information and have
over 200 unique spots. The fact that an individual’s right and left eyes are different and
that patterns are easy to capture, establishes iris-scan technology as one of the biometrics
that is very resistant to false matching and fraud. The false acceptance rate for iris
recognition systems is 1
20
In 1.2 million, statistically better than the average fingerprint recognition system. The
real benefit is in the false-rejection rate, a measure of authenticated users who are
rejected. Fingerprint scanners have a 3 percent false-rejection rate, whereas iris scanning
systems boast rates at the 0 percent level. Iris-scan technology has been piloted in ATM
environments in England, the US, Japan and Germany since as early as 1997. Airports
have begun to use iris-scanning for such diverse functions as employee
identification/verification for movement through secure areas and allowing registered
frequent airline passengers a system that enables fast and easy identity verification in
order to expedite their path through passport control. Other applications include
monitoring prison transfers and releases, as well as projects designed to authenticate on-
line purchasing, on-line banking, on-line voting and on-line stock trading to name just a
few. Iris-scan offers a high level of user security, privacy and general peace of mind for
the consumer. A highly accurate technology such as iris-scan has vast appeal because the
inherent argument for any biometric is, of course, increased security.
Important points:
Advantages:
21
c. The eye from a dead person would deteriorate too fast to be useful, so no extra
precautions have to been taken with retinal scans to be sure the user is a living human
being.
Disadvantages:
a. Intrusive.
c. Very expensive
VOICE RECONITION:
"Biometric technologies - those use voice - will be the most important IT innovations of
the next several years.” -Bill Gates at Gartner Group Itexpo '97. In comparing voice to
other forms of biometrics, the frequency locations plotted on the voice print table are
proportionate to the physical locations of minutiae used in fingerprint identification. The
minutiae are the endpoints and bifurcations of the swirls of your fingerprint. The
advantage of using speech is that the number of locations is almost endless. The capacity
to extend data collection over multiple words for even better accuracy is a distinct
advantage over image-based techniques such as fingerprints and retina scans where only
22
a finite amount of biometric data is available. Although it is virtually impossible for an
impostor to copy someone's voice, it is also very difficult for someone to repeat exactly
the phrase originally enrolled. This is very similar to the fact it is difficult to reproduce
the exact version of your signature on your credit card.
The voice print is stored as a table of numbers, where the presence of each
dominant frequency in each segment is expressed as a binary entry. Since all table entries
are either 1 or 0, each column can be read bottom to top as a long binary code. When a
person speaks his or her pass phrase, the code word or words are extracted and compared
to the stored model for that person.
User's first, middle and last name .User's date and month of birth Mother's first,
middle and last maiden name .Home telephone number.
Advantages:
23
c. Cheap technology.
Disadvantages:
a. A person’s voice can be easily recorded and used for unauthorised PC or network.
b. Low accuracy.
c. An illness such as a cold can change a person’s voice, making absolute identification
difficult or impossible.
SIGNATURE RECONITION:
Advantages:
a. Non intrusive.
c. Cheap technology.
24
Disadvantages:
IMAGE
a. Signature verification is designed to verify subjects based on the traits of their unique
ACQUISITION
signature. As a result, individuals who do not sign their names in a consistent manner
MODULE
may have difficulty enrolling and verifying in signature verification.
A Multibiometric system
ENROLLMENT MODULE
Face
Databa Extractor
se
Browse
Minutiae
r
Extractor
Central
Analysis
Template
Finger space
Projection
Database
Face Fingerspac
e
Locato
User acceptance is also an important issue to consider when selecting a biometric system
for employees to use on a regular basis. The following is a general user acceptance list in
descending order, from the most accepted to the least accepted:
1. Iris scan
2. Keystroke/patterning
3. Signature/handwriting
4. Speaker/voice recognition
5. Facial recognition/face location
6. Fingerprint
7. Hand geometry
8. Retinal scan
The following is a general CER list in descending order of accuracy, from the most
effective to the least effective:
1. Hand geometry
2. Iris scan
3. Retinal scan
4. Fingerprint
5. Speaker/voice recognition
6. Facial recognition/face location
7. Signature/handwriting
8. Keystroke/patterning
Application of Biometrics-
27
APPENDIX
Research Papers:
1- Emerging Methods of Biometrics Human Identification
Michał Chora´s Image Processing Group, Institute of Telecommunications,
University of Technology & Life Sciences, Kaliskiego 7, 85-796 Bydgoszcz,
Poland
28
29