View
218
Download
3
Tags:
Embed Size (px)
Citation preview
Outlines
• Introduction• Integration methods• Decision level integration
– Boolean combination– Binning and filtering– Dynamic authentication protocols
• Score level integration– Normal distributions– Degenerate cases– From threshold to boundaries
• Alternative
Introduction
• For many application there are non-biometric sources of information that can be used in person authentication.
• Using a single biometric is not sufficiently secure or does not provide sufficient coverage of the user population.
• Question: How do we integrate multiple biometric sources of information to make the application more accurate and more secure?
Integration methods
• There are many different methods that can be used to expand a biometric system:– Multiple biometrics: Face image and voiceprint
– Multiple location: Left and right iris
– Multiple sensing: Three tries of index finger
– Multiple sensors: Ultrasonic and optical sensing
– Multiple matchers: Minutia and correlation fingerprint matcher
– Multiple token: Adding possession and/or knowledge
• An example using multiple biometrics:
Integration methods
• Regardless of the methods, there are tow basic approaches to combination information from different sources:
– Tightly coupled integration: • A strong interaction among the input measurements and integration schemes.
– Loosely coupled integration: • There is no interaction among inputs and integration occurs at the output.
A tightly coupled system A loosely coupled system
Integration methods
• Loosely coupled integration systems advantages:– Simpler to implement– More feasible in commonly confronted integration
scenario
• One could try to integrate the biometrics at tow levels:– Decision level– Score level
Decision level integration
• Decision level integration (fusion) is typically concerned with multiple matchers method.
• Methods:– Boolean combination– Binning and filtering– Dynamic authentication protocols
• Note that in this context, the matchers are considered as block box and each output is simply a “Yes/No”.
Boolean combination
• The AND rule and the OR rule:– the most prevalent rules for multiple biometrics combination in
practical systems.
– Used in both Identification and Verification protocol.
Binning and Filtering
• The capability of a biometric 1:many search of a database is a prerequisite.
• Performing N biometric 1:1 matches :– Advantage:
• Simple way.
– Disadvantage: (When N, the size of the database, becomes large)
• High computational cost
• High False Positive Rate and large candidate list ( )NFPR
Filtering
• Constraining the search with parametric (non-biometric) data is called “filtering”.– Filtering down the search of N by, say, a subject’s
surname– Filtering is an authentication protocol
(Possession, Biometric)=(P, B)=(name, B)• Search the database N of enrolled subjects by surname• Search the subjects with matching surname P by matching
input sample biometric B
Binning
• Constraining the search with additional biometric data is referred to as “binning”.– The best known instance is first classify the type of
fingerprint and then match the minutia of fingerprint– Authentication protocol:
• Select those subjects in database N whose biometric template matches biometric B’
• Match the input biometric template B with the templates of those remaining subjects to find those subjects in N with both matching B’ and B
BB ,
Binning and Filtering
• Penetration rate or filter rate:
• Binning error rate is the percentage of subjects in the data base that are missed classify
• Possession token can be added to an existing authentication protocol:– Negative identification
• Decrease the chance of False Positive• Increase the probability of False Negative dramatically
– Positive identification• Does not decrease the biometric verification error rates
N
matchedisBtimesofEPpr
)(#
beP
Dynamic authentication protocols
• One dynamic protocol for speaker verification is the idea of conversational biometrics
• Conversational biometrics does a biometric match between the speech sample B and the voiceprint and a knowledge match between the collected responses through speech recognition and the knowledge
mB
mK
Score level integration
• Loosely coupled integration at score level integration• Assumption:
– Scores are normalized – B is the measurements of biometric a and b
1,0, ba ss
Score level integration
• Principle cases:– The scores are monotonically related to the likelihood– The scores are related to the likelihood in more
complex fashion
• Given ground truth marked data, it is possible to determine a function which relates to – Using ground truth data to estimate joint probability density
function – Example: Prabhakar and Jain estimate the conditional densities
using non-parametric estimation method
)( BdP m
),( ba ss )( BdP m
),( ba ss )( BdP m
),( ba ss
),(
),()(
aba
obam HssP
HssPBdP
),(),( abaoba HssPandHssP
Normal distribution
• Approximation of the curve G with a linear function
• This approximation is correct only when both and are normally distributed.– If we assume that and are
independent, the above equation becomes:
TssssG baba )1(),(
22),(
b
b
a
aba
ssssG
as bs
bsas
Normal distribution
• Problems:– The covariance matrix is assumed to be diagonal.
This is good if disparate biometrics are used.– Modeling match scores with Gaussian is not realistic
• Solution: Use of a Gaussian model for the probability distribution of the distance between two biometric templates
– Simple example:
),(1),( mm BBsBBDist 2
2
1
2
1)(
m
mEd
edP
)),(( mm BBDistEE )),(( mm BBDist
Degenerate cases
• If then
• If then
• It means biometric a does not contribute much to class separation.
ab
ba
Ts
sGa
aa
2)0,(
Ts
sGb
bb
2),0(
From thresholds to boundaries
• Question: Is there any way to estimate some decision boundary?
• Answer: Drive estimates of the match and mismatch score cumulative distributions from training data and determine operating point T that satisfy the design criteria.
• Assume that we have the cumulative match score distribution and the cumulative mismatch score distribution
),( ba ssF
),( ba ssG
TssFAR
ssFARssG
ba
baba
1),(1
),(),(
From thresholds to boundaries
• FR estimates are now the value of along the curve
• The FRR are given by
• A multi biometric system should not just be associated with one FAR and one FRR but with one FAR and a sequence of
),( ba ssF
TssG ba ),(
KkssF kb
ka ,...,1,),(
kFRR
Alternative
• The OR and AND rules for combining two decisions are the only way
• When more than two decision are need to be combined the choice of fusion is not merely limited to applying an overall OR and AND rules to all decision
• Another method is voting• Kittler and Alkoot have shown that score combination
strategy are superior when the individual matcher scores follow Gaussian distribution and voting is superior when scores distribution are heavy tailed