Veer Narmad South Gujarat University, Surat. M.sc. (Information Technology) Programme

Veer Narmad South Gujarat University,
Surat.
M.Sc. (Information Technology)

Programme
Seminar Report
7th Semester

5 Year Integrated Course
Year 2008 – 2009
BIOMETRIC TECHNOLOGY
Guided By : Parul Madam Submitted By : Freny Singhvi

Exam No. : 74
Semester : 7th
Veer Narmad South Gujarat University,

Surat.

Programme
Certificate
This is to certify that Ms. Freny Singhvi Exam Seat Number 000074 has
satisfactorily given his/her seminar entitled Biometric Technology as a
partial fulfilment of the requirements for 7th Semester - M.Sc.
(Information Technology) [5 Year Integrated course], during the
academic Year 2008-2009.
Date : 7/12/09 Prof. S.V. Patel

I/C Director
Place : Surat M.Sc. (I.T.) Programme.
2
VN South Gujarat University, Surat
INDEX
Sr.no TOPIC PAGE NO.

1. What is biometrics? 3
2. Why are biometric systems used? 4
3. Why are biometric systems secured? 5
4. Advantages of biometrics 6
5. Identification/ verification 7
6. Typology of biometrics 8
7. How biometric systems work? 9
8. Various biometric systems 11
9. Fingerprint recognition 12
10. Iris scanning 21
11. Retinal scanning 25
12. Hand geometry 28
13. Face recognition 33
14. Voice recognition 36
15. Signature recognition 40
16. Multimodal biometrics 41
17. Applications of biometrics 43
18. Attacks and issues 44
19. Conclusion 45
20. References 46
3
What is BIOMETRICS?
 BIOMETRICS refers to the automatic identification of a
person based on his physiological / behavioral
characteristics .
 Biometrics is the study of methods for uniquely recognizing

humans based upon one or more intrinsic physical or
behavioral traits.
BIOS = “LIFE” METRICS = “MEASURE”
 In technical terms, Biometrics is the automated technique of

measuring the physical characteristics or personal trait of an
individual and comparing that characteristic or trait to a
database for purpose of recognizing that individual.
4
Why are biometric systems used?
 Currently, the prevailing techniques of user authentication

are linked to passwords, user IDs, identification cards and
PINs (personal identification numbers).
 These techniques suffer from several limitations: Passwords

and PINs can be guessed, stolen or illicitly acquired by covert
observation.
 In addition, there is no way to positively link the usage of the

system or service to the actual user. A password can be
shared, and there is no way for the system to know who the
actual user is. A credit card transaction can only validate the
credit card number and the PIN, not if the transaction is
conducted by the rightful owner of the credit card.
 This is where biometrics systems provide a more accurate

and reliable user authentication methods.
5
Why are biometric systems secure?
 Unique: The various biometrics systems have been

developed around unique characteristics of individuals. The
probability of 2 people sharing the same biometric data is
virtually nil.
 Cannot be shared: Because a biometric property is an

intrinsic property of an individual, it is extremely difficult to
duplicate or share (you cannot give a copy of your face or
your hand to someone!).
 Cannot be copied: Biometric characteristics are nearly

impossible to forge or spoof, especially with new
technologies ensuring that the biometric being identified is
from a live person.
 Cannot be lost: A biometric property of an individual can be

lost only in case of serious accident.
6
Advantages of biometrics over existing

techniques:
 Uniqueness.
 No need to remember passwords or carry tokens.
 Biometrics cannot be stolen, lost or forgotten.
 More secure than a long password.
 Solves repudiation problem.
7
Biometrics are used for:
 IDENTIFICATION
 VERIFICATION (AUTHENTICATION)
 Identification is determining who a person is. It involves

trying to find a match for a person's biometric data in a
database containing records of people and that characteristic.
This method requires time and a large amount of processing
power, especially if the database is very large.
 Verification is determining if a person is who they say they

are. It involves comparing a user's biometric data to the
previously recorded data for that person to ensure that this is
the same person. This method requires less processing power
and time, and is used for access control (to buildings or data).
8
Typology of Biometrics
There are two types of biometrics :-
 PHYSICAL BIOMETRICS
 BEHAVIORAL BIOMETRICS
Physical biometrics
 A physiological characteristic is a relatively stable physical
feature such as finger print, hand silhouette , iris
pattern or facial features. These factors are basically
unalterable with out trauma to the individual.
 The degree of intrapersonal variation is smaller in

physical characteristics than in a behavioral one.
Behavioral Biometrics
 A behavioral tract, on the other hand, has some
physiological basis, but also reflects person’s physiological
makeup. The most common trait used in identification is a
person’s signature. Other behaviours used include a
person’s keyboard typing and speech patterns.
 The degree of intrapersonal variation is larger in

behavioral characteristics than in a physical one.
 Hence, as most of behavioural characteristics change over

time, many biometrics machines do not rely on behaviour.
9
How biometric systems work?
Biometric devices normally consist of 3 elements:
 a scanner / reader : that captures the user's biometrics

characteristics .
 a piece of software : that converts this data into digital form
and compares it with data previously recorded
 a database : which stores the biometric data .
The Biometric Process

The biometric process comprises 4 main steps:
 sample capture
 feature extraction
 template comparison and
 matching.
 At enrollment, a person’s biometric information is captured

by the scanner.
 The software then translates this information with an

algorithm , into a code that the database stores.
 When the person needs to be identified, the system will take

the information about the person again, translates this new
information with the algorithm , and then compares the new
code with the ones in the database to discover a match and
hence, identification
10
Block diagram of biometric process.
Types of biometric systems:
11
The main physical biometric technologies include:
 Fingerprint Recognition
 Iris Scanning
 Retinal Scanning
 Hand Geometry
 Face Recognition
The main behavioral biometric technologies include:
 Voice Recognition (analyzing a speaker's vocal behavior)

 Signature Recognition (analyzing the way you sign).
 Keystroke Recognition (measuring the time spacing of
typed words).
Other biometric techniques, still in exploratory stages would

include DNA biometrics, ear shape, fingernails, odor.
Fingerprint Recognition
12
Principles of fingerprint biometrics

 Fingerprints are usually considered to be unique, with no two
fingers having the exact same dermal ridge characteristics.
 A fingerprint is made of a number of ridges and valleys on
the surface of the finger.
 Ridges are the upper skin layer segments of the finger and
valleys are the lower segments.
 The ridges form so-called minutia points: ridge endings
(where a ridge end) and ridge bifurcations (where a ridge
splits in two).
 The uniqueness of a fingerprint can be determined by the
pattern of ridges and furrows as well as the minutiae
points.
13
14
There are five basic fingerprint patterns:

 arch
 tented arch,
 left loop
 right loop and
 whorl.
15
How the fingerprint biometrics work?

 The fingerprint recognition system uses a compact
terminal that incorporates light and CCD image sensors
to take high-resolution picture of a fingerprint .
 To enrol a user is assigned a personal identification number

and then puts a single finger on the glass or Plexiglas
plate for scanning by a CCD image sensor.
Step 1:
Finger is scanned and viewed by the System’s
access unit at the point of entry.
16
Step 2:
In applications for children (under the age of 18) the image is

standardized and resized before processing.
17
Step 3:
System develops a grid of intersection points (minutia points) from
the swirls and arcs of the scanned finger.
18
5178954
Step 4:
The image is discarded from the record and is no longer available
to the system or any operator.
Only a “Template remains that indicates the intersection points.
19
207895.3094.92345.128056.1239
87.10294.24360.193245.3495.29
83.07895.3094.92345.128056.12
3987.10294.24360.193245.3495.
2983.7895.3094.92345.128056.1
23987.10294.24360.193245.3495
.2983.207895.3094.92345.12805
6.123987.10294.24360.193245.3
495.2983.07895.3094.92345.128
056.123987.10294.24360.193245
.3495.2983.7895.3094.92345.128
056.123987.10294.24360.193245
.3495.2983.207895.3094.92345.1
28056.123987.10294.24360.1932
45.3495.2983.07895.3094.92345.
128056.123987.10294.24360.193
245.3495.2983.7895.3094.92345.
Step 5:
In fact, all that the system stores and recognizes for each individual
is a set of numbers that can only be interpreted as a template.
The system only remembers and processes numbers for each

individual, just like a social security number.
The advantages with a biometric approach is that the number

cannot be duplicated, lost or stolen, and uniqueness is defined
by the individual.
At the matching stage, the fingerprint image is processed to

extract its minutia points, which are then compared with the
registered template.
20
Advantages:
 The fingerprints do not change over time.

 Easy to use.
 Small size.
 Low power
 Non intrusive
Disadvantages:
 Finger imaging includes the need for physical contact with

the optical scanner.
 The possibility of poor quality images due to residue on the
finger such as dirt and body oils.
 Scars.
21
Iris Scanning
22
Principles of Iris Biometrics
 The iris is the elastic, pigmented, connective tissue that

controls the pupil.
 The iris is formed in early life in a process called

morphogenesis.
 Once fully formed, the texture is stable throughout life.
 It is the only internal human organ visible from the outside

and is protected by the cornea.
 The iris of the eye has a unique pattern, from eye to eye and
person to person.
How iris biometrics works?
23
 At enrollment, using standard video technology, the various

iris features can be quickly recorded from about nine inches
away, thus eliminating the need for invasive physical contact.
 An iris scan will analyze over 200 points of the iris, such as
 rings,
 furrows,
 freckles,
 the corona
 Software captures the identifying information from the iris

and stores it in a 256 byte code called template.
 Thus at matching stage, the iris scanner will analyze the

points of the iris and will compare it to a previously recorded
template.
 Glasses, contact lenses, and even eye surgery does not

change the characteristics of the iris.
24
 To prevent an image / photo of the iris from being used
instead of a real "live" eye, iris scanning systems will vary
the light and check that the pupil dilates or contracts.
Advantages
 Highly accurate: There is no known case of a false
acceptance for iris recognition .
 Not intrusive and hygienic - no physical contact required .
Disadvantages:
 The user must hold still while the scan is taking place .
 Relatively high expense of the system as compared to other
biometric technologies.
25
Retinal Scanning
Principles of retinal biometrics
 The blood vessels on the retina, at the back of the eye have a
unique pattern, from eye to eye and person to person.
26
How retinal biometrics work?

 Retina scans require that the person removes the glasses,
places his eye close to the scanner, stare at a specific point,
and remain still, and focus on a specified location for
approximately 10 to 15 seconds while the scan is completed.
 A retinal scan involves the use of a low-intensity coherent

light source, which is projected onto the retina.
 This light illuminates the blood vessels which are then

photographed and analysed.
Light is projected on retina
 A coupler is used to read the blood vessel patterns and

represents it in less than 35 bytes of information.
27
 This information is stored as small data templates which
provides quick identity confirmations, and handles well the
job of recognizing individuals in a database at the time
of matching.
Advantages
 Low occurrence of false negatives
 Highly reliable because no two people have the same retinal
pattern
 Speedy results: Identity of the subject is verified very
quickly.
Disadvantages
 Measurement accuracy can be affected by diseases such as
cataracts and glaucoma.
 High equipment costs.
 Poor lighting can affect results.
 Enrollment and scanning are intrusive and slow
Hand Geometry
28
29
Principles of hand biometrics
 An individual's hand does not significantly change after a
certain age.
 Unlike fingerprints, the human hand isn't unique. Individual

hand features are not descriptive enough for identification.
 However, hand biometric recognition systems are accurate

for verification purposes when combining various individual
features and measurements of fingers and hands.
How hand biometrics work?
30
 The user places the palm of his or her hand on the reader's
surface and aligns his or her hand with the guidance pegs
which indicate the proper location of the fingers .
 Looking down upon the hand is a charge-coupled device

(CCD) digital camera, which with the help of mirror
captures the side and top view of the hand simultaneously
 The digital image is analysed by software running on a

built in HD 64180 microprocessor to extract identifying
characteristics from the hand image .
 The system then measures and analyzes the overall structure,

shape and proportions of the hand like-
 Length , width and thickness of hand, fingers and joints.
 characteristics of the skin surface such as creases and ridges.
 Thus the system stores the hand geometry template in the

database.
 At the time of matching, the device checks its database for

verification of the user.
 To prevent a mold or a cast of the hand from being used,

some hand biometric systems will require the user to move
their fingers.
 Also, hand thermography can be used to record the heat of

the hand, or skin conductivity can be measured.
Measurements of hand are taken.
31
Hand is alligned on the reader’s surface by guidance pins.
Advantages
32
 Easy to use .
 Non intrusive .
 Small amount of data required to uniquely identify a user, so
a large number of templates can be easily stored in a
standalone device .
Disadvantages
 Lack of accuracy .
 Fairly expensive .
 Injuries to hands are fairly common and would prevent the
hand biometric system from working properly .
Face recognition
33
Face biometrics principles

The dimensions, proportions and physical attributes of a person's
face are unique.
34
How face biometrics work?
 At enrolment, several pictures are taken of the user's face,
with slightly different angles and facial expressions, to allow
for more accurate matching.
 Biometric facial recognition systems will measure and

analyze the overall structure, shape and proportions of the
face:
 Distance between the eyes, nose, mouth, and jaw edges

 upper outlines of the eye sockets
 the sides of the mouth
 the location of the nose and eyes
 the area surrounding the cheekbones.
 The system then stores the template containing the facial

geometry.
35
 For verification and identification, the user stands in front of

the camera for a few seconds, and the scan is compared with
the template previously recorded.
 To prevent an image / photo of the face or a mask from being

used, face biometric systems will require the user to smile,
blink, or nod their head. Also, facial thermography can be
used to record the heat of the face (which won't be affected
by a mask).
The main facial recognition methods are:

 feature analysis
 neural network,
 eigenfaces
 automatic face processing.
Advantages:
 Not intrusive .
 No physical contact with system: can be done from a
distance.
Disadvantages:
 User perceptions / civil liberty: Most people are not
comfortable with having their picture taken.
 It is easy to change the proportion of one's face by wearing a
mask, a nose extension, etc.
36
Voice Recognition
Principles of voice biometrics

 Our voices are unique to each person (including twins), and
cannot be exactly replicated
How voice biometrics work?
37
 Speech includes two components:
 a physiological component (the voice tract)

 and a behavioural component (the accent).
• It is almost impossible to imitate anyone's voice perfectly.
• Voice recognition systems can discriminate between two

very similar voices, including twins.
 A cold does not affect the vocal tract, so there will be no
adverse affect on accuracy levels.
 Only extreme vocal conditions such as laryngitis will prevent

the user from using the system.
 The performance of voice recognition systems may vary

depending on the quality of the audio signal.
 At enrollment , the person is asked to speak a stated upon

phrase.
 Voice recognition can utilize various audio capture device

(microphones, telephones and PC microphones).
 Voice recognition involves taking the acoustic signal of

person’s voice and converting it into a unique digital code
which can be the stored in a template.
 For future recognition, the exact same phrase is spoken and

the signal is analysed by the voice recognition system.
 To prevents the risk of unauthorised access via tape

recordings, the user is asked to repeat random phrases.
38
VOICE PRINT
COMPARISION OF TWO VOICE SIGNALS
Advantages
39
 Ability to use existing telephones .

 Can be automated, and coupled with speech recognition
systems .
Disadvantages
 High false non-matching rates .

 Phrases can be misspoken.
 Background noises can interfere with the system.
 People’s voices can change (for e.g.: when they are sick or in
extreme emotional states).
Signature Recognition
40
How signature biometrics work?

• Biometric signature recognition systems will measure and
analyze the physical activity of signing, such as
 the stroke order

 the pressure applied
 the pen/stylus speed
 direction in signature
 the points at which the pen is lifted from the paper.
 These behavioral patterns are captured through a specially

designed pen and compared with a template of process
patterns.
 Some systems may also compare visual images of signatures.
Advantages
 It is extremely difficult to mimic the behavior of signing .
 Low False Acceptance Rates (FAR).
Disadvantages
 People may not always sign in a consistent manner.
 Problems of long-term reliability.
 Lack of accuracy.
Multimodal Biometrics
41
 Multimodal biometrics use a combination of different

biometric recognition technologies
 In order for the biometrics to be ultra-secure and to provide

more-than-average accuracy, more than one form of
biometric identification is required.
 Hence the need arises for the use of multimodal biometrics

which uses a combination of different biometric recognition
technologies.
 Multimodal biometric technology uses more then one
biometric identifier to compare the identity of the person.
 Therefore in the case of a system using say three

technologies i.e. face mimic and voice. If one of the
technologies is unable to identify, the system can still use the
other two to accurately identify against.
 Multimodal technologies have been in use commercially

since 1998.
 Some of the commonly used multimodal biometric

technologies are:
 Multimodal system Integrating Faces and Fingerprints

for Personal Identification
 A Multimodal Biometric System Using Fingerprint, Face

and Speech.
42
Multimodal system including face recognition, fingerprint

recognition and speech recognition.
43
Applications of biometric technology:

 Banking/Financial services such as ATMs, payment
terminals, cashless payment , automated cheque cashing etc.
 Computer & IT Security such as Internet transactions, PC
login etc.
 Healthcare such as privacy concern, patient information
control, drugcontrol etc.
 Immigration such as border control, frequent travelers,
asylum seekers etc.
 Law and Order such as public ID card, voting, gun control,
prison etc.
 Gatekeeper/Door Access Control such as secure installations,
military, hotel, building management etc.
 Telecommunication such as telephony, mobile phone,
subscription fraud, call center, games etc.
 Time and Attendance such as school and company
attendance
 Welfare, including health care services and benefit payments
 Consumer Products such as automated service machines,
PDA etc.
44
Attacks and issues:

There are seven main areas where attacks may occur in a biometric
system:
 Presenting fake biometrics or a copy at the sensor, for

instance a fake finger or a face mask. It is also possible to try and
resubmitting previously stored digitized biometrics signals such
as a copy of a fingerprint image or a voice recording.
 Producing feature sets preselected by the intruder by

overriding the feature extraction process.
 Tampering with the biometric feature representation: The

features extracted from the input signal are replaced with a
fraudulent feature set.
 Attacking the channel between the stored templates and the

matcher: The stored templates are sent to the matcher through a
communication channel. The data traveling through this channel
could be intercepted and modified - There is a real danger if the
biometric feature set is transmitted over the Internet.
 Corrupting the matcher: The matcher is attacked and

corrupted so that it produces pre-selected match scores.
 Tampering with stored templates, either locally or remotely.
 Overriding the match result.
45
Conclusion
A range of biometric systems are in developments or on

the market because no one system meets all needs. The trade off
in developing these systems involve component cost, reliability,
discomfort in using a device, the amount of data needed and
other factors. But the application of advanced digital techniques
has made the job possible. Further experiments are going all
over the world. In India also there is a great progress in this
field. So we can expect that in the near future itself, the
biometric systems will become the main part in identification
purposes.
46
References
 www.Biometricnewsportal.com
 Google search
 Biometric image description technology - David Zang.
 Biometric consortium examples of biometrics.
47

Veer Narmad South Gujarat University, Surat. M.sc. (Information Technology) Programme

Caricato da

Informazioni sul documento

Descrizione originale:

Copyright

Formati disponibili

Condividi questo documento

Condividi o incorpora il documento

Opzioni di condivisione

Hai trovato utile questo documento?

Questo contenuto è inappropriato?

Copyright:

Formati disponibili

Veer Narmad South Gujarat University, Surat. M.sc. (Information Technology) Programme

Caricato da

Copyright:

Formati disponibili

Veer Narmad South Gujarat University,

M.Sc. (Information Technology)

M.Sc. (Information Technology)

Guided By : Parul Madam Submitted By : Freny Singhvi

Veer Narmad South Gujarat University,

M.Sc. (Information Technology)

satisfactorily given his/her seminar entitled Biometric Technology as a

partial fulfilment of the requirements for 7th Semester - M.Sc.

(Information Technology) [5 Year Integrated course], during the

academic Year 2008-2009.

Date : 7/12/09 Prof. S.V. Patel

Sr.no TOPIC PAGE NO.

 Biometrics is the study of methods for uniquely recognizing

BIOS = “LIFE” METRICS = “MEASURE”

 In technical terms, Biometrics is the automated technique of

Why are biometric systems used?

 Currently, the prevailing techniques of user authentication

 These techniques suffer from several limitations: Passwords

 In addition, there is no way to positively link the usage of the

 This is where biometrics systems provide a more accurate

Why are biometric systems secure?

 Unique: The various biometrics systems have been

 Cannot be shared: Because a biometric property is an

 Cannot be copied: Biometric characteristics are nearly

 Cannot be lost: A biometric property of an individual can be

Advantages of biometrics over existing

 No need to remember passwords or carry tokens.

 Biometrics cannot be stolen, lost or forgotten.

 More secure than a long password.

 Solves repudiation problem.

 Identification is determining who a person is. It involves

 Verification is determining if a person is who they say they

 The degree of intrapersonal variation is smaller in

 The degree of intrapersonal variation is larger in

 Hence, as most of behavioural characteristics change over

How biometric systems work?

Biometric devices normally consist of 3 elements:

 a scanner / reader : that captures the user's biometrics

The Biometric Process

 At enrollment, a person’s biometric information is captured

 The software then translates this information with an

 When the person needs to be identified, the system will take

Block diagram of biometric process.

Types of biometric systems:

The main physical biometric technologies include:

The main behavioral biometric technologies include:

 Voice Recognition (analyzing a speaker's vocal behavior)

Other biometric techniques, still in exploratory stages would

Principles of fingerprint biometrics

There are five basic fingerprint patterns:

How the fingerprint biometrics work?

 To enrol a user is assigned a personal identification number

In applications for children (under the age of 18) the image is

The system only remembers and processes numbers for each

The advantages with a biometric approach is that the number

At the matching stage, the fingerprint image is processed to

 The fingerprints do not change over time.

 Finger imaging includes the need for physical contact with

Principles of Iris Biometrics

 The iris is the elastic, pigmented, connective tissue that

 The iris is formed in early life in a process called

 Once fully formed, the texture is stable throughout life.

 It is the only internal human organ visible from the outside