Jan. 14, 2004 1

Biometrics: Personal Identification

Instructor: Natalia Schmid

BIOM 426: Biometrics Systems

Jan. 14, 2004 2

Outline Introduction Applications Identification methods Requirements to biometrics Biometrics technology Automatic Identification:

design representation feature extraction matching evaluation

Privacy Issues

Jan. 14, 2004 3

Introduction

Identification: associating identity with an individual.

Two types of identification problems:

verification (confirming or denying person's identity) Am I who I claim I am?

identification or recognition (establishing identity) Who am I?

password

PIN

Jan. 14, 2004 4

Introduction

Master Card: estimated fraud at 450 million per year

1 billion dollars worth of calls are made by cellular bandwidth thieves

ATM related fraud - 3 billion annually

3,000 illegal immigrants crossing the Mexican border each day

Facts:

Jan. 14, 2004 5

Identification methods

Person’s identity is everything what person represents and believes.

Engineering approach: reduce the problem to: (i) some possession ("something what he has") or (ii) some knowledge ("something what he knows")

Another approach: reduce it to a problem of authentication based on physical characteristics (physiological or behavioral).

Definition: Biometrics are person's identification based on his/her physiological or behavioral characteristics. "something that you are"

Jan. 14, 2004 6

New Definition

Biometrics are automated methods of recognizing a person

based on a physiological or behavioral characteristic.

(BCC2003)

Jan. 14, 2004 7

Requirements to biometrics

1. universality: everyone should have it

2. uniqueness: small probability that two persons are the same in terms of this characteristic

3. permanence: invariance with the time

4. collectability: can be measured quantitatively

5. performance: high identification accuracy

6. acceptability: acceptance by people

7. circumvention: how easy to fool the system by fraudulent technique

Jan. 14, 2004 8

Accepted Biometrics

Accepted and studied biometrics: voice, hand geometry, gait, fingerprint, ear, face, iris, retina, fingerprint, infrared facial and hand vein thermograms, key stroke, signature, DNA

DNA, signature, and fingerprint are recognized in court of law

Jan. 14, 2004 9

Biometric Technology: OverviewFingerprints: are graphical flow-like ridges.

Their formation depends on embrionic development. Factors:

(i) genetic, (ii) environmental

Fingerprint acquisition: (i) scanning inked impression, (ii) life-scan

Major representations: image, ridges, minutia (features derived

from ridges), or pores

Basic approaches to identification: (i) correlation based; (ii) global ridge patterns (classes); (iii) ridge patterns; (iv) fingerprint minutiae (ridge endings and bifurcations)

Jan. 14, 2004 10

Biometric Technology: OverviewFace: one of the most acceptable biometrics

Two identification approaches: (i) transform (eigenvalues, analysis of covariance matrix, orthonormal basis vectors)

(ii) attribute-based approach (geometirc features)

Factors that influence recognition: (i) facial disguise (ii) facial expressions (iii) lighting conditions (iv) pose variation

Jan. 14, 2004 11

Biometric Technology: OverviewIris: is one of the most reliable

biometrics.

Frontal images are obtained using near infrared camera (320 x 480 pixels) at distance < 1 meter.

Iris images are (i) segmented and (ii) encoded.

Twins have different iris patterns.

Jan. 14, 2004 12

Biometric Technology: Overview

Voice: is a behavioral characteristic and is not sufficiently unique (large database).

Processing: signal subdivided into a few frequency bands. The most commonly used feature is cepstral feature (log of FT in each band).

Matching strategies: hidden Markoff, vector quantization, etc.

Types of verification: text-dependent; text-independent;

language-independent.

Voice print is highly accepted biometrics.

Used for identification over the telephone.

Easy to fool the system.

Jan. 14, 2004 13

Biometric Technology: Overview

Infrared Facial and Hand Vein Thermogram:

Human bodies radiate heat.

Infrared sensors acquire an image of heat distribution along the body. Images = thermograms.

Imaging methods: similar to visible spectrum photographs.

Processing: raw images are normalized with respect to heat radiating from landmark features.

In uncontrolled environment, other sources of heat could be disturbance.

Jan. 14, 2004 14

Biometric Technology: Overview

Gait: is the specific way one walks. Complex spatio-temporal behavioral characteristic.

Gait is not unique and does not stay invariant over time.

It is influences by: distribution of body weight, injuries involving joints or brain, aging.

Gait features are derived from a video sequence and consists of charactertization of several movements (computer vision problem).

Jan. 14, 2004 15

Biometric Technology: Overview

Retinal Scan: Retinal vasculature is rich in structure.

Unique characteristic of each individual and each eye.

Not easy to change or replicate.

Image capture: requires person to peep into an eye-piece and focus on a specific spot. A predetermined part of retinal vasculature is imaged.

Requires cooperation.

Not accepted by public.

Can reveal some medical conditions as hypertension.

Jan. 14, 2004 16

Biometric Technology: Overview

Signature: the way person signs his/her name.

Highly acceptable behavioral biometrics.

Evolves over time and depends on physical and mental conditions.

Easily forged.

Modeling the invariance and automating signature recognition process is challenging.

Two approaches to signature verification: (i) static (geometric features = strokes) (ii) dynamic (strokes and acceleration, velocity, trajectory)

Jan. 14, 2004 17

Biometric Technology: Overview

Hand and finger geometry: is used for access control (50% of market).

System captures frontal and side views of palm.

Measurements: length and width of fingers, various distances.

The representation requirements are only 9 bytes.

Hand geometry is not unique but highly

acceptable.

Jan. 14, 2004 18

Comparison of Biometrics Technologies

Biometrics Universality Uniqueness Permanence Collectability Performance Acceptability Circumvention Face High Low Medium High Low High Low Fingerprint Medium High High Medium High Medium High Hand Geometry

Medium Medium Medium High Medium Medium Medium

Keystrokes Low Low Low Medium Low Medium Medium Hand Vein Medium Medium Medium Medium Medium Medium High Iris High High High Medium High Low High Retinal Scan High High Medium Low High Low High Signature Low Low Low High Low High Low Voice Print Medium Low Medium Low Low High Low Facial Thermograms

High High Low High Medium High High

Odor High High High Low Low Medium Low DNA High High High Low High Low Low Gait Medium Low Low High Low High Medium Ear Medium Medium High Medium Medium High Medium

From “Biometrics: Personal Identification in Networked Society,” p. 16

Jan. 14, 2004 19

Automatic IdentificationHistory:

• Prehistoric Chinese used thumb-

print for identification;• Alphonse Bertillon’s System ofAnthropometric Identification (1882)is based on bodily measuments,physical description, and photographs.• Henry’s fingeprint classificationsystem (1880) classifies in > 100 classes.

1685

Sets of rules are developed for:(i) matching of biometrics(ii) searching databases

Automatic identification is due to: inexpensive computer resources, advances incomputer vision, pattern recognition, and image understanding.

Jan. 14, 2004 20

Applications

Civil applications:

Banking (electronic funds transfer, ATM security, Internet commerce, credit card transactions)

Physical access control (airport) Information system security (access to databases via login) Customs and immigration (identification based on hand geometry) Voter/driver registration Telecommunications (cellular bandwidth access control)

Jan. 14, 2004 21

Example

Jan. 14, 2004 22

Automatic IdentificationDesign

Identification system operates in two modes: (i) enrollment mode and (ii) identification.

Biometric Reader

Feature Extractor

Feature Extractor

Biometric Reader

Feature Matcher

Enrollment

Identification

Jan. 14, 2004 23

Automatic Identification

Enrollment mode:

- biometric measurement is captured - information from raw data extracted; - (feature, person) information is stored; - ID is issued (for verification).

Identification mode:

- biometric is sensed (live-scan); - features are extracted from the raw data; - match is performed (search of the database).

In verification mode, person presents ID. Then system performs match only against one template in the database.

Jan. 14, 2004 24

Recognition System

Acquisition Feature Extraction

System Knowledge

Object

Training

Testing

Acquisition MatchingFeature Extraction

Object

Outcome

Architecture of a typical pattern recognition system (see A. K. Jain, et al., p. 22).

Jan. 14, 2004 25

Design Issues

Given the speed, accuracy, and cost specifications

1. How to collect the input data? (3D, 2D, multiple views, high or low resolution)

2. Internal representation (features) for automatic feature extraction

3. How to extract features? (Algorithms, etc.)

4. How to select the "matching" metric? (Measurements are made in specific space)

5. How to implement it?

6. Organization of database

7. Effective methods for searching a template in the database (binning, etc.)

Jan. 14, 2004 26

AcquisitionQuality of collected data determines performance of the entire system.

Associated tasks:

(i) quality assessment (ii) segmentation (separation of the data into foreground and background).

Research efforts:

(i) richer data (3D, color, etc.) (ii) metrics for assessment quality of measurements. (iii) realistic models

Solutions: enhancement

Jan. 14, 2004 27

Representation

Which machine-readable representation captures the invariant and discriminatory information in the data?

Determine features s.t.

- invariant for the same individual (intraclass variation) - maximally distinct for different individuals (interclass)

More distincive features offer more reliable identification. Representation has to be storage space efficient (smart card: 2 Kbytes) Representation depends on biometrics

Jan. 14, 2004 28

Feature extraction

• Given raw data, automatically extracting the given representation is difficult problem.

Example: manual fingerprint system uses about a dozen of features. For automatic system, many of them are not easy to reliably detect.

Feature extraction procedures are typically designed in ad hoc manner (inefficient when measurements are noisy).

Determining effective models for features will help to reliably

extract them (esp. in noisy situations).

Jan. 14, 2004 29

Matching

Similarity metric should be robust against:

- noise, - structural and statistical variations, - aging, and artifacts of feature extraction module.

Example: signature (hard to define the ground truth)

Performance is determined by: (i) representation and (ii) similarity metric.

Trade-off: better engineering design vs. more complex matcher.

Example: fingerprint (variations in features and rigid matcher vs. Flexible matcher)

Jan. 14, 2004 30

Matching (Fingerprint)

Sources of distortion and noise:

(i) inconsistent contact (3D-to-2D)

(ii) non-uniform contact (due to dryness of skin, sweat, dirt, humidity in the air, etc.)

(iii) irreproducible contact (injuries to the finger)

(iv) feature extraction artifacts (measurement error)

(v) sensing itself adds noise

Jan. 14, 2004 31

Evaluation

An end-user questions: (i) Does the system makes an accurate identification? (ii) Is the system sufficiently fast? (iii) What is the cost of the system?

Because of noise, distortions, and limited information no metric is adequate for reliable identification.

Decisions: - genuine individual, - imposter.

Jan. 14, 2004 32

Evaluation

Four types of outcomes:

(1) Genuine individual is accepted (true) (2) Genuine individual is rejected (error) (3) Imposter is rejected (true)

(4) Imposter is accepted (error)

FAR - false acceptance rate

FRR - false rejection rate

EER - equal error rate

Given a database, performance is a RV and only can be estimated.

Jan. 14, 2004 33

EvaluationMeasure of performance:

ROC - receiver operating curve

Confidence Intervals

Jan. 14, 2004 34

Useful Links

http://www.biometrics.org/ (publications and periodicals; research and databases; meetings and events)

http://www.itl.nist.gov/div895/biometrics/

http://biometrics.cse.msu.edu/

http://www.tech.purdue.edu/it/resources/biometrics/

http://www.wvu.edu/~bknc/

http://www.citer.wvu.edu/