Professional Documents
Culture Documents
An Overview of Biometrics
An Overview of Biometrics
An Overview of
Biometrics
Contents Biometric Systems
1. Introduction
2. Biometric identifiers
3. Classification of biometrics methods
4. Biometric system architecture
5. Performance evaluation
2
SECURITY INNOVATION ©2003
Contents Biometric Systems
6. Signature recognition
7. Voice recognition
8. Retinal scan
9. Iris scan
10. Face-scan and facial thermograph
11. Hand geometry
3
SECURITY INNOVATION ©2003
Personal Identification
4
SECURITY INNOVATION ©2003
Personal Identification Objects
• Token-based:
“something that you have”
• Knowledge-based:
“something that you
know”
• Biometrics-based:
“something that you are”
5
SECURITY INNOVATION ©2003
Biometrics
• Bio + metrics:
– The statistical measurement of biological data.
• Biometric Consortium definition:
– Automatically recognizing a person using
distinguishing traits.
6
SECURITY INNOVATION ©2003
Application Domains (I)
• Access control
– to devices
• cellular phones
• logging into a computer, laptop, or PDA
• cars
• guns
– to local services
• money from a ATM machine
• logging in to computer
• accessing data on smartcard
– to remote services
• e-commerce
• e-business
7
SECURITY INNOVATION ©2003
Application Domains (II)
9
SECURITY INNOVATION ©2003
Biometric Technologies
10
SECURITY INNOVATION ©2003
Other Biometric Methods
11
SECURITY INNOVATION ©2003
Classification of Biometric
Methods
• Static: • Dynamic:
– fingerprint – signature recognition
– retinal scan – speaker recognition
– iris scan
– hand geometry
12
SECURITY INNOVATION ©2003
Biometric System Architecture
13
SECURITY INNOVATION ©2003
Biometric System Model
score
Application decision
Authentication decision
14
SECURITY INNOVATION ©2003
Data Acquisition Module
15
SECURITY INNOVATION ©2003
Feature Extraction Module
16
SECURITY INNOVATION ©2003
Matching Module
17
SECURITY INNOVATION ©2003
Decision Module
18
SECURITY INNOVATION ©2003
Storage Module
19
SECURITY INNOVATION ©2003
Enrolment
20
SECURITY INNOVATION ©2003
Possible Decision Outcomes
21
SECURITY INNOVATION ©2003
Errors
22
SECURITY INNOVATION ©2003
Tolerance Threshold
• Error tolerance threshold is crucial and
application dependent.
• Tolerance too large gives Type II error (admit
impostors).
• Tolerance too small gives Type I errors (reject
legitimate users).
• Equal error rate for comparison: false non-
match equal to false match.
23
SECURITY INNOVATION ©2003
Biometric Technologies
• Signature recognition
• Voice recognition
• Retinal scan
• Iris scan
• Face biometrics
• Hand geometry
24
SECURITY INNOVATION ©2003
Signature Recognition
25
SECURITY INNOVATION ©2003
Dynamic Signature Recognition
26
SECURITY INNOVATION ©2003
Dynamic Signature Verification
(I)
27
SECURITY INNOVATION ©2003
Dynamic Signature Verification
(II)
28
SECURITY INNOVATION ©2003
Signature Recognition:
Advantages / Disadvantages
• Advantages:
– Resistance to forgery
– Widely accepted
– Non-intrusive
– No record of the signature
• Disadvantages:
– Signature inconsistencies
– Difficult to use
– Large templates (1K to 3K)
29
SECURITY INNOVATION ©2003
Fingerprint Recognition
• Ridge patterns on fingers uniquely identify
people.
• Classification scheme devised in 1890s.
• Major features: arch, loop, whorl.
• Each fingerprint has at least one of the major
features and many ‘small’ features.
30
SECURITY INNOVATION ©2003
Features of Fingerprints
31
SECURITY INNOVATION ©2003
Fingerprint Recognition (cont.)
32
SECURITY INNOVATION ©2003
Fingerprint Authentication
• Basic steps for fingerprint authentication:
– Image acquisition,
– Noise reduction,
– Image enhancement,
– Feature extraction,
– Matching.
33
SECURITY INNOVATION ©2003
Fingerprint Processing
a b
a) Original
b) Orientation
c d
c) Binarised
d) Thinned
e f e) Minutiae
f) Minutia graph
34
SECURITY INNOVATION ©2003
Fingerprint Recognition
• Sensors
– optical sensors
– ultrasound sensors
– chip-based sensors
– thermal sensors
• Integrated products
– for identification – AFIS systems
– for verification
35
SECURITY INNOVATION ©2003
Fingerprint Recognition:
Sensors (I)
Electro-optical sensor
[DELSY® CMOS sensor modul]
Optical fingerprint sensor
[Fingerprint Identification Unit
FIU-001/500 by Sony]
Capacitive sensor
[FingerTIP™ by Infineon]
36
SECURITY INNOVATION ©2003
Fingerprint Recognition:
Sensors (II)
Thermal sensor
[FingerChip™ by ATMEL
(was: Thomson CSF)]
E-Field Sensor
[FingerLoc™ by Authentec]
37
SECURITY INNOVATION ©2003
Fingerprint Recognition:
Integrated Systems (I)
Keyboard [G 81-12000
by Cherry]
39
SECURITY INNOVATION ©2003
Fingerprint Recognition:
Advantages / Disadvantages
• Advantages:
– Mature technology
– Easy to use/non-intrusive
– High accuracy
– Long-term stability
– Ability to enrol multiple fingers
• Disadvantages:
– Inability to enrol some users
– Affected by skin condition
– Association with forensic applications
40
SECURITY INNOVATION ©2003
Speech Recognition
41
SECURITY INNOVATION ©2003
Speaker Recognition Systems
42
SECURITY INNOVATION ©2003
Speaker Recognition:
Advantages/ Disadvantages
• Advantages:
– Use of existing telephony infrastructure
– Easy to use/non-intrusive/hands free
– No negative association
• Disadvantages:
– Pre-recorded attack
– Variability of the voice
– Affected by noise
– Large template (5K to 10K)
43
SECURITY INNOVATION ©2003
Eye Biometric
• Retina:
– back inside of the eye ball.
– pattern of blood vessels used for identification
• Iris:
– colored portion of the eye surrounding the pupil.
– complex iris pattern used for identification.
44
SECURITY INNOVATION ©2003
Retinal Pattern
45
SECURITY INNOVATION ©2003
Retinal Recognition
46
SECURITY INNOVATION ©2003
Retinal Scan:
Advantages / Disadvantages
• Advantages:
– High accuracy
– Long-term stability
– Fast verification
• Disadvantages:
– Difficult to use
– Intrusive
– Limited applications
47
SECURITY INNOVATION ©2003
Iris Properties
48
SECURITY INNOVATION ©2003
Iris Recognition
49
SECURITY INNOVATION ©2003
The Iris Code
50
SECURITY INNOVATION ©2003
Iris Recognition
52
SECURITY INNOVATION ©2003
Face-scan and Facial
Thermographs
• Static controlled or dynamic uncontrolled
shots.
• Visible spectrum or infrared (thermographs).
• Non-invasive, hands-free, and widely
accepted.
• Questionable discriminatory capability.
53
SECURITY INNOVATION ©2003
Face Recognition
• Visible spectrum: inexpensive.
• Most popular approaches:
– eigen faces,
– Local feature analysis.
• Affected by pose, expression, hairstyle, make-
up, lighting, eyeglasses.
• Not a reliable biometric measure.
54
SECURITY INNOVATION ©2003
Face Recognition
55
SECURITY INNOVATION ©2003
Face Recognition:
Advantages / Disadvantages
• Advantages:
– Non-intrusive
– Low cost
– Ability to operate covertly
• Disadvantages:
– Affected by appearance/environment
– High false non-match rates
– Identical twins attack
– Potential for privacy abuse
56
SECURITY INNOVATION ©2003
Facial Thermograph
57
SECURITY INNOVATION ©2003
Facial Thermograph:
Advantages / Disadvantages
• Advantages:
– Non-intrusive
– Stable
– Not affected by external changes
– Identical twins resistant
– Ability to operate covertly
• Disadvantages:
– High cost (infrared camera)
– New technology
– Potential for privacy abuse
58
SECURITY INNOVATION ©2003
Hand Geometry
59
SECURITY INNOVATION ©2003
Hand Geometry Reading
60
SECURITY INNOVATION ©2003
Hand Geometry:
Advantages / Disadvantages
• Advantages:
– Not affected by environment
– Mature technology
– Non-intrusive
– Relatively stable
• Disadvantages:
– Low accuracy
– High cost
– Relatively large readers
– Difficult to use for some users (arthritis, missing
fingers or large hands)
61
SECURITY INNOVATION ©2003
Multimodal Biometric Systems
62
SECURITY INNOVATION ©2003
How good are biometric
products?
• How can we find out, how good a biometric
product is?
– Empirical tests of the product
• There have been independent tests on a series
of biometric products
– in Japan
– in Germany
63
SECURITY INNOVATION ©2003
Different Threat Scenarios
1. Regular biometric
sensor using
artificially generated
biometric data
2. Replay attack of
eavesdropped
biometric data
3. Manipulation of
stored biometric
reference data
64
SECURITY INNOVATION ©2003
Japanese Test
• Tsutomu Matsumoto, a Japanese
cryptographer working at Yokohama
National University
• 11 state-of-the-art fingerprint sensors
• 2 different processes to make gummy fingers
– from live finger
– from latent fingerprint
65
SECURITY INNOVATION ©2003
Test in Germany (I)
• 11 biometric sensors
– 9 fingerprint sensors,
– 1 face recognition system, and
– 1 iris scanner
• Fingerprint sensors –
– reactivate latent fingerprints (optical and capacitive sensors)
– apply latex finger (thermal sensor)
• Face recognition system –
– down- (up-) load biometric reference data from (to) hard
disk
– no or only weak life detection
66
SECURITY INNOVATION ©2003
Test in Germany (II)
• Iris recognition –
– picture of iris of enrolled person with cut-out
pupil, where a real pupil is displayed
68
SECURITY INNOVATION ©2003
Choosing the Biometrics (cont.)
69
SECURITY INNOVATION ©2003
Conclusions