biometric authentication systems

Post on 02-Jan-2016

46 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

DESCRIPTION

Biometric Authentication Systems. 林維暘 中正大學 資訊工程學系 九十五學年度 第二學期. Agenda. 2.1 Introduction 2.2 Design Tradeoffs 2.3 Feature Extraction 2.4 Adaptive Classifiers. Introduction. - PowerPoint PPT Presentation

TRANSCRIPT

Biometric Authentication Systems

林維暘中正大學 資訊工程學系九十五學年度 第二學期

Biometric Authentication 2

Agenda

§ 2.1 Introduction2.1 Introduction

§ 2.2 Design Tradeoffs

§ 2.3 Feature Extraction

§ 2.4 Adaptive Classifiers

Biometric Authentication 3

Introduction

• There is a rapidly increasing interest in the development of commercial systems for biometric authentication applications.

• The objective of a commercial system is to satisfy security requirement while incurring minimal cost.

• This chapter discusses system deployment requirements as well as critical design tradeoffs.

Biometric Authentication 4

Agenda

§ 2.1 Introduction

§ 2.2 Design Tradeoffs2.2 Design Tradeoffs

§ 2.3 Feature Extraction

§ 2.4 Adaptive Classifiers

Biometric Authentication 5

2.2 Design Tradeoffs

§ 2.2.1 Accuracy vs. Intrusiveness

§ 2.2.2 Recognition vs. Verification

§ 2.2.3 Centralized vs. Distributed

§ 2.2.4 Processing Speed

§ 2.2.5 Storage Requirements

§ 2.2.6 Compatibility between Feature Extractor and Classifier

Biometric Authentication 6

2.2 Design Tradeoffs

• To evaluate a biometric system’s accuracy, the most adopted metrics are– False Rejection Rate (FRR)– False Acceptance Rate (FAR).

Biometric Authentication 7

False Rejection Rate

• FRRFRR, or miss probability, is the percentage of authorized individuals rejected by the system.

• Sensitivity, a.k.a. True Positive Rate (TPRTPR), is the percentage that an authorized person is admitted.

FRR = 1 - TPR

Biometric Authentication 8

False Acceptance Rate

• FARFAR, a.k.a. False Positive Rate (FPRFPR), is the percentage that unauthorized individuals are accepted by the system.

• Specificity, a.k.a. True Negative Rate (TNRTNR), is the percentage that an unauthorized person is correctly rejected.

FAR = FPR = 1 - TNR

Biometric Authentication 9

The ROC Curve

• A good authentication system should have both low FRR and low FAR.

• Typically, the tradeoff is illustrated by so-called Receiver Operation Characteristic (ROCROC) curves or by the Detection Error Tradeoff (DETDET) curves.

• Tradeoff between FAR and FRR is adjusted by varying the threshold.

Biometric Authentication 10

The ROC Curve

Biometric Authentication 11

The ROC Curve

Biometric Authentication 12

ROC and DET curves

10-4

10-3

10-2

10-1

100

0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1

False Acceptance Rate (FAR)

Tru

e P

ositi

ve R

ate

(TP

R)

ROC curve

10-4

10-3

10-2

10-1

100

0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

0.9

1

False Acceptance Rate (FAR)

Fal

se R

ejec

tion

Rat

e (F

RR

)

DET curve

Biometric Authentication 13

2.2.1 Accuracy vs. Intrusiveness

• Physiological characteristics (e.g., fingerprint and iris) generally provide higher accuracy than behavioral features (e.g., voice and signature).– Behavioral features can change from daty to d

ay.– Physiological characteristics always remain th

e same.

Biometric Authentication 14

2.2.1 Accuracy vs. Intrusiveness

• If a security system makes users feel uncomfortable, then it is intrusive.

• For low security level environments (e.g. apartments, hotels), an intrusive system is highly undesirable.

• On the other hand, intrusive systems are commonly deployed in high security areas.

Biometric Authentication 15

2.2.1 Accuracy vs. Intrusiveness

Intrusiveness Convenience Error rate

Face No Good 10-1 ~ 10-3

Palm No? Middle < 10-3

Fingerprint Yes Middle 10-2 ~ 10-6

Iris Yes Bad < 10-6

Voice No Middle 10-1 ~ 10-2

Signature No Bad 10-1 ~ 10-3

Biometric Authentication 16

2.2.2 Identification vs. Verification

• Identification– Search a database for an acceptable match– Higher computational cost– Higher error rate

• Verification– Verify the identity of a user– Greatly reduced FAR– Slightly increased FRR

Biometric Authentication 17

2.2.3 Centralized vs. Distributed

• Three major components in a biometric system– Sensor– Pattern matcher– Controller

• These pieces can be configured in various ways.– Centralized– Distributed

Centralized system architecture 18

Central matcher

& controller Central

template database

Central transaction logging

sensor

sensor sensor

sensor

user

Distributed system architecture 19

Central controller

Central template database

Central transaction logging

sensorsensor

sensorsensor

Local DB Local DB

Local DB Local DB

matcher matcher

matcher matcher

user

Biometric Authentication 20

2.2.3 Centralized vs. Distributed

Distributed System Centralized System

Less communication loading More communication loading

Lower risk of system failure Higher risk of system failure

Maintenance is more complex

Less management issues

Biometric Authentication 21

2.2.4 Processing Speed

• If a gateway control system takes on hour to process one entry request, it is useless no mater how accurate it is.

• Fingerprint identification system– 18 types of fingerprint features– Error rate of 10-10 can be achieved– Accuracy is usually sacrificed for speed

[198,295]

Biometric Authentication 22

2.2.5 Data Storage Requirements

• In most scenarios, the size of raw data is too large to store.

• Raw data is compressed into feature vectors with much smaller dimension.– Pentland et al. [272] compress a 256 x 256 im

age to a 20-dimnesional feature vector.

• Application types dictate the system architecture– e.g., Central or local database

Biometric Authentication 23

2.2.6 Compatibility between Feature Extractor and Classifier

• A recognition system involves mapping between the following spaces. – Instantiation space: A symbol is instantiated into an

object. A symbol may have different instantiations.– Feature space: The mapping from instantiation space

to feature space is called feature extractionfeature extraction.– Symbol space: The symbols represent classes of

objects. The mapping from feature space to symbol space is called classificationclassification.

Biometric Authentication 24

Compatibility between Feature Extractor and Classifier

• Feature extraction– The most important stage in a recognition syst

em– Represented by a mapping from instantiation

space x to feature space v.

x → v = f(x)

Biometric Authentication 25

Compatibility between Feature Extractor and Classifier

• Classification– The mapping from feature space to symbol sp

ace– A two-class classifier

• Discriminant function (v)• (v) > 0 if feature vector is extracted from an insta

ntiation belonging to one class.• (v) < 0 if feature vector is extracted from an insta

ntiation belonging to the other class.

Biometric Authentication 26

Compatibility between Feature Extractor and Classifier

• In order to design an effective system, one needs to consider not only feature extraction but also classification.

Feature Extractor

Pattern Classifier

(e.g. neural networks)Raw Data

(e.g. speech waveform, fingerprint images, facial images)

Feature Vectors

Classification Decisions

(e.g. ID of claimants, accept/reject)

Biometric Authentication 27

Agenda

§ 2.1 Introduction

§ 2.2 Design Tradeoffs

§ 2.3 Feature Extraction2.3 Feature Extraction

§ 2.4 Adaptive Classifiers

Biometric Authentication 28

2.3 Feature Extraction

§ 2.3.1 Criteria of feature extraction

§ 2.3.2 Projection methods for dimension reduction

§ 2.3.3 Feature selection

§ 2.3.4 Clustering methods

Biometric Authentication 29

2.3.1 Criteria of Feature Extraction

• Data compression– Only vital representations are extracted.

• Informative ness– The characteristics essential for the intended

applications should be best described.

• Invariance– The dependency on environmental conditions should

be minimized.

• Ease of processing– A cost-effective implementation should be feasible.

Biometric Authentication 30

2.3.1 Criteria of Feature Extraction

• Two approaches are often adopted to obtain compressed representation.– Dimension reduction by projection onto linear

subspace– Data clustering (Chapter 3)

Biometric Authentication 31

2.3.2 Projection Methods for Dimension Reduction

• Principal Component Analysis (PCAPCA)– A mapping from Rn to Rm, n > m– Mathematically, the PCA is to find a matrix W

such that

y = W x, where W is an mxn matrix

– The W is formed by the m eigenvectors corresponding to the largest m eigenvalues

Biometric Authentication 32

2.3.2 Projection Methods for Dimension Reduction

• Independent Component Analysis (ICAICA)– ICA extracts components with higher-order

statistical independence.– Kurtosis of a random variable is defined as

22

4

][

][)(

YE

YEYk

Biometric Authentication 33

Independent Component Analysis

1. Gaussian:

2. Uniform:

3. Binary:

k(y) 3

k(y) 1.8

k(y) 1

Biometric Authentication 34

Independent Component Analysis

• PCA maximizes the second-order covariance.

• ICP maximizes the fourth-order kurtosis.– An advantage of using ICA is that kurtosis

function is scale invariant.– The most discriminative independent

component

22

4

])[(

])[(min

wx

wxw E

E

Biometric Authentication 35

Independent Component Analysis

• Mathematically, the ICA is to find a matrix W such that

y = W x, where W is an mxn matrix

– y contains the m most discriminative independent components.

– The W is formed by the m independent row vectors wi, which can be extracted sequentially.

Biometric Authentication 36

2.3.3 Feature Selection

• Sometimes, only a few selected features would suffice.– In Hong Kong stock market, only 33 stocks ar

e selected to calculate the Hang Seng index.

• Note that unlike dimension reduction, there is no linear combination in the feature selection.

Biometric Authentication 37

2.3.3 Feature Selection

• Fisher Discriminant Analysis– Fisher discriminant J(xi) represents the ration of inter-

class distance to intra-class variance

– 1i and 2i denote the means of xi belonging to class 1 and class 2, respectively.

– 1i and 2i denote the variances of xi belonging to class 1 and class 2, respectively.

22

21

221 )(

)(ii

iiixJ

Biometric Authentication 38

2.3.3 Feature Selection

• Fisher Discriminant Analysis– The value of J(xi) provides a simple mean for f

eature selection.– The selected features will correspond to the in

dices with better discriminating capability.

Biometric Authentication 39

2.3.4 Clustering Methods: GMM

• Most biometric data cannot be adequately modeled by a single–cluster Gaussian model.

• Gaussian Mixture Model (GMM) provides a more flexible model for describing the distribution of biometric data.– K-means or EM algorithms– Optimal number of clusters

Biometric Authentication 40

Project-Then-Cluster

• We can adopt more sophisticated strategies such as cluster-the-projectcluster-the-project or project-then-clusterproject-then-cluster.

• Cluster-then-project– A projection aimed at separating two classes,

each modeled by a GMM [404].

Biometric Authentication 41

PCA

Model Selection

User Interaction + EM + MDL

2-dimensional space (x-space)

EM

(Probabilistic Clustering)

•Cluster initialization

•Clustering in x-space

•Model validation

Gaussian Mixture Model•Clustering in t-space

Page 27

Fig 2.7 An illustration of the project-then-cluster approach. Projection of data from t-space to x-space, then after clustering in the lower-dimension subspace, trace the membership information back to the t-space

Biometric Authentication 42

Agenda

§ 2.1 Introduction

§ 2.2 Design Tradeoffs

§ 2.3 Feature Extraction

§ 2.4 Adaptive Classifiers2.4 Adaptive Classifiers

Biometric Authentication 43

2.4 Adaptive Classifiers

§ 2.4.1 Neural networks

§ 2.4.2 Training strategies

§ 2.4.3 Criteria on classifiers

§ 2.4.4 Availability of training samples

Biometric Authentication 44

2.4 Adaptive Classifiers

• Statistical approach– Each class is modeled by a normal

distribution– Using prior probabilities, one can compute the

posterior probabilities of each person, conditioned on an observation.

Biometric Authentication 45

2.4.1 Neural Networks

• A neural work is a simulation of the nervous system that contains neuron unit communicating with one another via axon connections.

• By combining a vast number of simple neurons, it is possible to achieve a sophisticated task.

• Neural networks for biometric applications are discussed in Chapter 5, 6, and 7.

Biometric Authentication 46

2.4.2 Training Strategies

• Neural networks can learn rules from a collection of examples.

• The ability to learn from examples is a major advantage of neural networks.

• Two types of learning:– Supervised– Unsupervised

Biometric Authentication 47

2.4.2 Training Strategies

• Supervised learning– A neural network is provided with a training

set with labels (the “teacher values”).– The parameters are determined so that the

system can produce answers as close as possible to the teacher values

– e.g., OCR and speaker recognition

Biometric Authentication 48

2.4.2 Training Strategies

• Unsupervised learning– Explore the underlying rules from an

unlabeled training set– Used in the applications where teacher values

are expensive or difficult to obtain

Biometric Authentication 49

2.4.3 Criteria on Classifiers

• The performance metrics of a learning algorithm– training accuracytraining accuracy: obtained from the training data– generalization accuracygeneralization accuracy: obtained from the testing

data

• There is usually a distinction between training and generalization accuracies.

• High training accuracy does not necessarily yield good generalization accuracy.

Biometric Authentication 50

2.4.3 Criteria on Classifiers

• Invariance and noise resilience– Minimize the dependency on environmental

conditions.– Tolerate noise corruption because noise is

inevitable in practical applications.

Biometric Authentication 51

2.4.3 Criteria on Classifiers

• Cost-effective system implementation– A cost-effective platform should be

considered.– Emphasis should also be placed on the

issues of system integration.

Biometric Authentication 52

2.4.4 Availability of Training Samples

• The availability of training data is of critical concern.

• Solutions to the training sample deficiency problem– Conduct an intensive study on the nature of

the selected biometric.– Virtual pattern generation

Biometric Authentication 53

Intensive study

• An example: fingerprint– The relative positions between various

minutiae are the discriminative features.– The resulting feature vectors could be

separated by simple classifiers.– There is no need to use example to tell the

system which features should be extracted.

Biometric Authentication 54

Virtual pattern generation

• Create additional training samples– 200 virtual images are generated from one

facial image– Chimerical data

Biometric Authentication 55

2.5 Visual-Based Biometric Systems

Biometric Authentication 56

2.6 Audio-Based Biometric Systems

top related