This document provides an outline for a paper on biometric systems. It begins with an introduction that defines biometrics and discusses identification vs verification systems. It then covers the basic structure of a biometric system including the sensor, feature extraction, matching, and database modules. It discusses various biometric techniques including fingerprint, iris, retina, face, voice, signature, and keystroke recognition. It also covers biometric system errors, vulnerabilities, applications, and the limitations of unimodal systems. Finally, it discusses multimodal biometric systems including different fusion levels and examples of multimodal combinations.

1. BIOMETRIC
BY
VADI HENA

2. 2
Outline
• Part Ⅰ. Introduction
• Part Ⅱ. Biometric System
• Part Ⅲ. Biometrics Techniques
• Part Ⅳ. Biometric System Errors
• Part Ⅴ. Vulnerable Points Of Biometric System
• Part Ⅵ. Application of Biometric Systems
• Part Ⅶ. Limitation of (Unimodal) Biometric Systems
• Part Ⅷ. Multimodal Biometric Systems

3. 3
Ⅰ. Introduction
• The Term Biometric Comes From The Greek
Words Bios (Life) And Metrikos (Measure).
• Definition:
“Automated measurement of Physiological
and/or behavioral characteristics to determine or
authenticate identity”

4. What is Biometric?
“Automated measurement”
 No human involvement.
 Comparison takes place in Real-Time.
“Physiological and/or behavioral characteristics”
4

5. What is Biometric?(Cont..)
“Determine or Authenticate Identity”
 Identification Systems:
– Who am I?
– Determine Identity
 Verification Systems:
– Am I who I claim to be?
– Authenticate Identity
– More accurate.
– Less expensive.
– Faster.
– More limited in function.
– No Requires more effort by user.
5

6. Identification and Authentication
6
Identification Authentication
It determines the identity of the
person.
It determines whether the person is
indeed who he claims to be.
No identity claim
Many-to-one mapping.
Cost of computation  number of
record of users.
Identity claim from the user
One-to-one mapping.
The cost of computation is
independent of the number of
records of users.
Captured biometric signatures come
from a set of known biometric feature
stored in the system.
Captured biometric signatures may
be unknown to the system.

7. Why Biometric?
• User authentication methods can be broadly classified into three
categories as shown in Figure, know, have, and are.
• Because a biometric property is an intrinsic property of an individual,
it is difficult to surreptitiously duplicate and nearly impossible to
share
7
Know
Have
Be

8. Why Biometric?(Cont..)
• Passwords are not reliable.
– Too many
– Can be stolen
– Forgotten
– Shared
– Many passwords easy to guess
– PIN Can be duplicated
– PIN can be Lost or stolen
– PIN a weak link(Writing the PIN on the card)
• Protect Sensitive Information
– Banking
– Medical
– Commercial
– Government
8

9. Why Biometric?(Cont..)
Frauds in industry happens in the following situations:
• Safety deposit boxes and vaults
• Bank transaction like ATM withdrawals
• Access to computers and emails
• Credit Card purchase
• Purchase of house, car, clothes or jewellery
• Getting official documents like birth certificates or passports
• Obtaining court papers
• Drivers licence
• Getting into confidential workplace
• writing Checks
9

10. Ⅱ. Biometric System
10
Basic Structure of Biometric

11. 11
Biometric System
• A Biometric System Is Designed Using The
Following Four Main Modules.
1) Sensor Module
(Encapsulating a Quality Checking Module)
2) Feature Module
3) Matcher Module
(Encapsulating a Decision Making Module)
4) System Database Module

12. 12
Biometric System (Cont..)
A sample flow chart:
Feature
Extractor
Sensor
Qualify
checker
System
Database
True / False
Matcher
Decision
Maker
template
The templates in the system database
may be updated over time.

13. 13
Biometric System (Cont..)
• A biometric system may operate either in verification
mode or identification mode.
A. Verification mode:
“Does this biometric data belong to Bob? ”
B. Identification mode:
“Whose biometric data is this? ”
• “Recognition” is the generic term of verification and
identification.

14. 14
Biometric System (Cont..)
System
Database
Login
Interface
Get Name & Snapshot
Quality
Checker
Check Quality
Feature
Extractor
Enrollment
Template

15. 15
Biometric System (Cont..)
System
Database
True / False
Login
Interface
Get Name & Snapshot
One template
Feature
Extractor
Extract Features
Matcher
One match
Verification
Claimed identity

16. 16
Biometric System (Cont..)
System
Database
User’s identity or
“user unidentified”
Login
Interface
Get Name & Snapshot
N templates
Feature
Extractor
Extract Features
Matcher
N match
Identification

17. 17
Biometric System (Cont..)
Describing the verification problem:
a) An input feature vector: XQ
b) A claimed identity: I
c) The biometric template corresponding to I : XI
d) The similarity between XQ and XI: S(XQ, XI)
e) The predefined threshold of similarity: t
f) True (a genuine user): ω1 ; False (an imposter): ω2
otherwise
)
,
(
S
if
,
2
,
1
)
,
(
t
X
X
ω
ω
X
I I
Q
Q






18. 18
Ⅲ. Biometrics Techniques
• Retina scanning
• Iris scanning
• Fingerprint scanning
• Hand scanning
• Face recognition
• Voice recognition
• Signature recognition
• Keystroke recognition

19. Biometrics Techniques
• DNA
• Ear recognition
• Skin reflection
• Lip motion
• Vein Pattern
• Footprint and Foot Dynamics
• Body color
• Brain Wave Pattern
• Hand Grip
• Thermograph 19

20. Fingerprint scanning
• "Fingerprint authentication" describes the process of obtaining a
digital representation of a fingerprint and comparing it to a stored
digital version of a fingerprint.
• Measures unique characteristics in a fingerprint (minutiae)
– Crossover
– Core
– Bifurcations
– Ridge ending
– Island
– Delta
– Pore
20

21. Fingerprint Scanning(Cont..)
21

22. Iris Scanning
 Measures unique characteristics of the iris
– Ridges (rings)
– Furrows
– Straitions (freckles)
22

23. Retina Scanning
 Measures unique characteristics of the
retina.
– Blood vessel patterns
– Vein patterns
23

24. Facial Scanning
 Uses off-the-shelf camera to measure the following facial
features:
– Distance between the eyes.
– Distance between the eyes and nose ridge.
– Angle of a cheek.
– Slope of the nose.
– Facial Temperatures.
24

25. Face Recognition
25

26. Hand Geometry
 Measures the top and side of
the hand, and the Palm.
• Full hand geometry systems
take an image of the entire hand
for comparison.
• Two Finger readers only image
two fingers of the hand.
• Usually a specialized reader
device to measure aspects such
as length, width, thickness, and
surface area of the hand and
fingers .
26

27. Voice Pattern
• Identification of the person
who is speaking by
characteristics of
their voices (voice
biometrics), also called Voice
Patterns.
• There is a difference
between speaker
recognition (recognizing wh
o is speaking) and speech
recognition (recognizing wha
t is being said).
– Pitch
– Quality
– Strength
– Frequency
– Tone 27

28. Key Stroke
• The rhythms with which one types at a keyboard are sufficiently
distinctive to form the basis of the biometric technology known as
keystroke dynamics
• Measures the time between strokes and duration of key pressed.
Latencies between keystrokes when writing by two persons
28

29. Signature Scan
Two kinds of signatures:
1. off-line(Static)
2. on-line(Dynamic)
Static:
In this mode, users write their signature on paper, digitize it through an optical
scanner or a camera, and the biometric system recognizes the signature
analyzing its shape. This group is also known as “off-line”.
Dynamic:
In this mode, users write their signature in a digitizing tablet, which acquires the
signature in real time. Dynamic recognition is also known as “on-line”.
• Dynamic information usually consists of the following information:
– spatial coordinate x(t)
– spatial coordinate y(t)
– pressure p(t)
– inclination in(t)
– pen up/down
29

30. Signature Scan
30

31. 31
Comparison

32. 32
Ⅳ. Biometric System Errors
• A biometric verification system makes two
types of errors:
1) Mistaking Biometric Measurements From Two
Different Persons to be From The Same
Person (Called False Match)
2) Mistaking Two Biometric Measurements From
The Same Person to be From Two Different
Persons (Called False Non-match)

33. 33
Biometric System Errors (Cont..)
Hypothesis testing:
1) H0: input XQ does not come from the same person as the template XI
2) H1: input XQ comes from the same person as the template XI
Decision:
1) D0: person is not who she claims to be
2) D1: person is who she claims to be.
If S (XQ , XI) ≧ t , then decide D1 , else decide D0 .

34. 34
Biometric System Errors (Cont..)
• Such a hypothesis testing formulation contains two type of error:
• Type Ⅰ(α): false match (D1, when H0)
• Type Ⅱ(β): false non-match (D0, when H1)
Decision
Threshold (t )
Matching Score (s )
Probability
(
p
)
∞
-∞
Imposter
Distribution
p (s|H0)
Genuine
Distribution
p (s|H1)
FNMR = P (D0|H1)
FMR = P (D1|H0)

35. 35
Biometric System Errors (Cont..)
False Non-match Rate (FNMR)
False
Match
Rate
(FMR)
Forensic
Applications
High-security
Applications
Civilian
Applications

36. Ⅴ. VULNERABLE POINTS OF BIOMETRIC SYSTEM
36

37. Ⅴ. VULNERABLE POINTS OF BIOMETRIC SYSTEM
1. Presenting fake biometrics at the sensor.
2. Resubmitting previously stored digitized biometrics
signals.
3. Overriding the feature extraction process.
4. Tampering with the biometric feature representation.
5. Corrupting the matcher.
6. Tampering with stored templates.
7. Attacking the channel between the stored templates and
the matcher.
8. Overriding the final decision.
37

38. 38
Ⅵ. Application of Biometric Systems
• The application of biometric can be divided into five main groups:
forensic, government, commercial, health-care and travelling and
immigration.
1) Commercial
ATM, credit card, cellular phone, distance learning, etc.
2) Government
ID card, driver’s license, social security, passport control, etc.
3) Forensic
terrorist identification, missing children, etc.
4) Heath-Care
Access to medical details, Patient Info, etc.
5) Travelling and Immigration
Air Travel, Boarder Crossing, Passport, etc.

39. 39
Application of Biometric Systems(Cont..)

40. Example - Face Recognition in Airport
40
Image is sent to
computer
for manipulation.
Image is passed to database
for possible match

41. 41
Ⅶ. Limitation of (Unimodal) Biometric Systems
1) Noise in Sensed Data
2) Intra-class Variations
3) Distinctiveness
E.G. Hand Geometry, Face, etc.
4) Non-universality
5) Spoof Attacks

42. 42
Ⅷ. Multimodal Biometric Systems
Fusion Level
a) Fusion at Sensor level
b) Fusion at Feature level
c) Fusion at Opinion level
d) Fusion at Decision level

43. 43
Multimodal Biometric Systems (Cont..)
decision
Feature
Extraction
Biometric
snapshot
Matching
Decision
Making
Feature
Extraction
Biometric
snapshot
Fusion
System
Database
features
features
Fusion at Sensor level

44. 44
Multimodal Biometric Systems (Cont..)
decision
Feature
Extraction
Biometric
snapshot Matching
Decision
Making
Feature
Extraction
Biometric
snapshot
Fusion
System
Database
Matching
rank values
rank values
Fusion at Feature level

45. 45
Multimodal Biometric Systems (Cont..)
Classifier 1 Classifier 2 Classifier 3
Score1 > t1
Score2 > t2
Score3 > t3 False True
Yes
Yes Yes
No
No No
No
Yes
Score2 > t2
False
False True
Fusion at Opinion level

46. 46
Multimodal Biometric Systems (Cont..)
decision
Feature
Extraction
Biometric
snapshot Matching
Fusion
System
Database
Matching
Decision
Making
Decision
Making
Feature
Extraction
Biometric
snapshot
decision
decision
Fusion at Decision level

47. 47
Multimodal Biometric Systems (Cont..)
• An important combination scheme at the decision level is the serial
and parallel combination, also known as “AND” and “OR”
combination.
• The AND combination improves the False Acceptance Ratio.
• The OR combination improves the False Rejection Ratio.
System 1 System 2
System 1
System 2

48. 48
Multimodal Biometric Systems (Cont..)
Multimodal
Biometrics
Multiple
matchers
Multiple
snapshots
Multiple
units
Multiple
biometrics
Multiple
sensors
right index &
middle fingers
optical &
capacitance
sensors
minutiae &
non-minutiae
based matchers
face &
fingerprint
two attempts of
right index finger

49. Multimodal Biometric Systems - Example
49

50. 50
Multimodal Biometric Systems (Cont..)
Other Examples of Multimodal Biometric Systems
“Person Identification Using Multiple Cues” Face, Voice
“Expert Conciliation for Multimodal Person Authentication
Systems using Bayesian Statistics” Face, Speech
“Integrating Faces and Fingerprints and Voice for
Personal Identification” Face, fingerprint, Voice
“Personal Verification using Palm print and Hand
Geometry Biometric” Palm print and Hand Geometry
“Bioid: A Multimodal Biometric Identification System”
voice, lip motion, face

51. Future Biometric
• Future mobile phones
– Facial scanning and Fingerprint authentication is used now a
days, other possibilities to increase security, this could be
through combining two techniques or looking into other
biometrics methods.
– At the moments vein identification, Keystroke scan could easily
be implemented onto mobiles that have a keypad,
• Biometrics Based Key Generation using Diffie Hellman
Key Exchange for Enhanced Security Mechanism
• Securing E-Governance Services through Biometrics
• Remote User Authentication 51

52. Future Biometric
• Improving the Security of MANETs Oriented Military
Intelligence using Biometrics Authentication
Technologies
• Health Care Infrastructure Security using Bimodal
Biometrics System
• Secure e-transaction
• Cloud Computing, Security Issues and Potential Solution
by Using Biometrics Based Encryption
• Biometrics Technology based Mobile Voting Machine 52

53. References
1. Sergey Tulyakov, Faisal Farooq, Praveer Mansukhani, Venu Govindaraju, “Symmetric Hash functions for Secure Finger print
biometric systems”.
2. Y.Donis, L. Reyzin and A.Smith, “Fuzzy Extractors”In security with Noisy Data: Private Biometrics, Secure key Storage and
Anti-Counterfeiting, P.Tuyls, B.Skoric and T.Kevenaar, Eds., chpt5,pp.79-77, Springer-Verlag, 20012.
3. Direct Indirect Human Computer Interaction Based Biometrics International Journal of Emerging Engineering Research and
Technology Volume 3, Issue 3, March 2015.
4. A.A.E. Ahmed, I. Traore, “A new biometric technology based on mouse dynamics, IEEE Transactions on dependable and Secure
Computing” 4 (3) (2007) 165–179.
5. Deshpande, S. Chikkerur, V. Govindaraju, Accent classification in speech, Fourth IEEE Workshop on Automatic Identification
Advanced Technologies, 17–18 October, 2014, pp. 139–143.
6. F. Bannister and R. Connolly, “New Problems for Old? Defining e-Governance”, proceedings of the 44th Hawaii International
Conference on System Sciences, (2012).
7. W.-S. Chen, K.-H. Chih, S.-W. Shih and C.-M. Hsieh, “Personal Identification Technique based on Human Iris Recognition with
Wavelet Transform”, 2005 IEEE, ICASSP, (2012), pp. II -949.
8. R. Germain, A. Califano, and S. Colville, “Fingerprint Matching Using Transformation Parameter Clustering,” IEEE
Computational Science and Engineering 4, No. 4, 42–49 (2014).
9. L. O’Gorman, “Practical Systems for Personal Fingerprint Authentication,” IEEE Computer 33, No. 2, 58–60 (2013).
10 N. K. Ratha and R. M. Bolle, “Smart Card Based Authentication,” in Biometrics: Personal Identification in Networked Society,
A. K. Jain, R. M. Bolle, and S. Pankanti, Editors, Kluwer Academic Press, Boston, MA (2013), pp. 369–384.
11. T. Rowley, “Silicon Fingerprint Readers: A Solid State Approach to Biometrics,” Proceedings of the CardTech/SecureTech
Conference, CardTech/SecureTech, Bethesda, MD (2013), pp. 152–159.
12. B. Miller, “Vital Signs of Identity,” IEEE Spectrum 31, No.2, 22–30 (2013).
13. B. Schneier, “The Uses and Abuses of Biometrics,” Communications of the ACM 42, No. 8, 136 (2012).
14. W. Bender, D. Gruhl, N. Morimoto, and A. Lu, “Techniques for Data Hiding,” IBM Systems Journal 35, Nos. 3&4, 313–336
(2013).
15. Biometric Digest -http://biometrics.cse.msu.edu. 53

54. Questions!!!!!
54