fingure print recognition
TRANSCRIPT
-
8/4/2019 Fingure Print Recognition
1/20
Fingerprint Recognition
-
8/4/2019 Fingure Print Recognition
2/20
Features of
FingerprintsFingerprints are imprints formedby friction ridges of the skin in
fingers and thumbs.Their pattern are permanentand unchangeable on each fingerduring all the life;
They are individual (the probabilitythat two fingerprints are alike is about 1 in
1.9x10^15 )They have long been used for
identification
-
8/4/2019 Fingure Print Recognition
3/20
Fingerprint Applications
Commercial Government Forensic
Computer Network Logon,
Electronic Data Security,E-Commerce,
Internet Access,
ATM, Credit Card,
Physical Access Control,
Cellular Phones
Personal Digital Assistant,
Medical Records,
Distance Leaning, etc.
National ID card,
Correctional Facilities,Drivers License,
Social Security,
Welfare Disbursement,
Border Control,
Passport Control, etc.
Corpse Identification
Criminal Investigation,Terrorist Identification,
Parenthood determination,
Missing Children, etc.
-
8/4/2019 Fingure Print Recognition
4/20
Fingerprint Application Functionality
Positive Identification Is this person truly know to the system Commercial applications (network logon)
Desirable: low cost and user-friendly
Large Scale Identification Is this person in the database
Government and Forensic applications (prevent doubledipping; multiple passports)
Desirable: high throughput with little human intervention
Surveillance and Screening
Is this a wanted person
Airport watch list
Fingerprints are not suitable
-
8/4/2019 Fingure Print Recognition
5/20
Challenges
To design a system that would operate on theextremes of all three axis simultaneously
Accuracy
Scale
Usability
101
105
1010
90% 99% 99.9999%
Unusable
Hard to Use
Easy to use
-
8/4/2019 Fingure Print Recognition
6/20
Reasons for Accuracy Challenges
Information Limitation Due to individuality, poor presentation, and inconsistent
acquisition
Representation Limitation
Design and choice of representation (features) and quality offeature extraction algorithms (especially for poor qualityfingerprints)
Invariance Limitation
Incorrect modeling of invariant relationships among features
-
8/4/2019 Fingure Print Recognition
7/20
Fingerprint Individuality EstimationAccuracy; Information Limitation
Assumptions for theoretical individuality estimation consider only minutiae (ending and bifurcation) features
minutiae locations and directions are independent
minutiae locations are uniformly distributed
correspondence of a minutiae pair is an independent event quality is not explicitly taken into account
ridge frequency is assumes to be constant across population and
spatially uniform in the same finger
analysis of matching of different impressions of the same finger
binds the parameters of the probability of matching prints from
different fingers
an alignment between two fingerprints has been established
-
8/4/2019 Fingure Print Recognition
8/20
Information Limitation: ConclusionAccuracy; Information Limitation
There is an incredible amount of information content
in fingerprints
A minutiae-based fingerprint identification system candistinguish between identical twins
The performance of state-of-the-art automatic
fingerprint matchers do not even come close to thetheoretical performance
Performance of fingerprint matcher is depended onthe fingerprint class and thus may depend upon
target population Fingerprint classification may not be very effective in
genetically related population
Fingerprint identification accuracy may suffer in
certain demographics
-
8/4/2019 Fingure Print Recognition
9/20
Fingerprint RepresentationAccuracy; Representation Limitation
Ideal representation would maximize the inter-classvariability and minimize the intra-class variability
Fingerprints from the same finger
Minutiae-based representationmay not be most suitable Fingerprints from two different fingers
Ridge feature-based representation
may not be most suitable
-
8/4/2019 Fingure Print Recognition
10/20
Fingerprint RepresentationAccuracy; Representation Limitation
Quality Index = 0.04False Minutiae=27
Quality Index = 0.53False Minutiae=7
Quality Index = 0.96False Minutiae=0
-
8/4/2019 Fingure Print Recognition
11/20
Conventional RepresentationsAccuracy; Representation Limitation
Minutiae-based
Sequential design based on the following modules:Segmentation, local ridge orientation estimation (singularity andmore detection), local ridge frequency estimation, fingerprintenhancement, minutiae detection, and minutiae filtering andpost-processing.
Ridge Feature-based
Size and shape of fingerprint, number, type, and position ofsingularities (cores and deltas), spatial relationship and
geometrical attributes of the ridge lines, shape features, globaland local texture information, sweat pores, fractal features.
-
8/4/2019 Fingure Print Recognition
12/20
Representations: Future DirectionsAccuracy; Representation Limitation
Improvement of current representations through robustand reliable domain-specific image processingtechniques such as:
Model-based orientation field estimation
Robust image enhancement and masking
New richer representations
Fusion of various representations
-
8/4/2019 Fingure Print Recognition
13/20
Fingerprint InvarianceAccuracy; Invariance Limitation
Ideal matcher would perfectly model the invariant
relationship in different impressions of the samefinger
Two good quality fingerprint images from the same fingerA fingerprint matching algorithm that assumes a rigid transformation will be unable to match
-
8/4/2019 Fingure Print Recognition
14/20
Matching: Future DirectionsAccuracy; Invariance Limitation
Alignment remains a difficult problem develop
alignment techniques that remain robust under thepresence of false features
Understand and model fingerprint deformation
Fusion of various matchers (based on the same ordifferent representations)
-
8/4/2019 Fingure Print Recognition
15/20
Scale
1:N Identification is a much harder problem (N large)
Accuracy Speed
Traditionally: classify fingerprint into one of the few (4 orso) predefined fingerprint types
Problem: too few distinct bins; uneven naturaldistribution into these bins; many ambiguousfingerprints (17% NIST4 has two labels)
a) b) c)
-
8/4/2019 Fingure Print Recognition
16/20
Scale: Future Directions
Continuous classification
Feature-based indexing (search and retrieval) schemes(e.g., minutiae triplets)
Fast matchers
Classifier combination
0
10
20
30
40
50
60
70
0 5 10 15 20 25 30 35 40Error (%)
Penetr
ation
(%)minutiae triplets
orientation image
FingerCode
Combination
-
8/4/2019 Fingure Print Recognition
17/20
Multiple Biometrics; Fusion
A decision (and lower) level fusion of multiple
biometrics can improve performance
In identification systems, fusion can also improvespeed
Independence among modalities is key
Even combination of correlated modalities can be noworse than the best performing modality alone
Best combination scheme would be applicationdependent
-
8/4/2019 Fingure Print Recognition
18/20
Performance Evaluation
Evaluation types: technology, scenario, operational
Dependent on composition of the population(occupation, age, demographics, race), theenvironment, the system operational mode, etc
Ideally, characterize the application-independent
performance in laboratory and predict technology,scenario, and operational performances
Standardization and independent testing
Parametric and non-parametric estimation ofconfidence intervals and database size
Parametric and non-parametric and statisticalmodeling of inter-class and intra-class variations;
-
8/4/2019 Fingure Print Recognition
19/20
Usability, Security, Privacy
Biometrics are not secrets and not revocable
Encryption, secure system design, and livenessdetection solve this problem
Unintended functional scope; unintended application
scope; covert acquisition Legislation; self-regulation; independent regulatory
organizations
Biometric Cryptosystems: fingerprint fuzzy vault
Alignment
Similarity metric in encrypted domain
Variable and unordered representation
Performance loss; ROC remains the bottleneck
-
8/4/2019 Fingure Print Recognition
20/20
THANK YOU