48
BIOMETRICS BIOMETRICS

BIOMETRICS. CONTENTS Introduction Introduction History History General system General system Finger Print Recognition Finger Print Recognition Hand Geometry

Embed Size (px)

Citation preview

BIOMETRICSBIOMETRICS

CONTENTSCONTENTS

IntroductionIntroduction HistoryHistory General systemGeneral system Finger Print RecognitionFinger Print Recognition Hand GeometryHand Geometry IrisIris Speaker VerificationSpeaker Verification Performance & ApplicationPerformance & Application ConclusionConclusion

AIMS AT…..AIMS AT…..

Forget passwords ...Forget passwords ... Forget pin numbers ...Forget pin numbers ... Forget all your security concerns ...Forget all your security concerns ...

WHY USE IT?WHY USE IT?

Tokens, such as smart cards, magnetic stripe cardsand physical keys Tokens, such as smart cards, magnetic stripe cardsand physical keys can be lost, stolen, or duplicated.can be lost, stolen, or duplicated.

Passwords can be forgotten, shared, or unintentionally observed by a Passwords can be forgotten, shared, or unintentionally observed by a third party.third party.

Forgotten passwords and lost smart cards are a nuisance for users Forgotten passwords and lost smart cards are a nuisance for users and waste the expensive time of system administrators.and waste the expensive time of system administrators.

Can potentially prevent unauthorized access to or fraudulent use of ATMs, cellular phones, smart cards, desktop PCs, workstations, and computer networks

WHAT IS BIOMETRICSWHAT IS BIOMETRICS??

Automated methodAutomated method - -automatic identification of of person using automatic identification of of person using

human body as a password.human body as a password.

Pattern recognition systemPattern recognition system - -computer systems can record and computer systems can record and

recognize the patterns, hand shapes, ear lobe contours, and a host of recognize the patterns, hand shapes, ear lobe contours, and a host of other physical characteristics .other physical characteristics .

Specific physiological or behavioral characteristicsSpecific physiological or behavioral characteristics – – Physiological characteristics -> visible parts of the human body which Physiological characteristics -> visible parts of the human body which

include fingerprint, retina, palm geometry, iris, facial structure, etc. include fingerprint, retina, palm geometry, iris, facial structure, etc.

Behavioral characteristics ->what a person does which include voice Behavioral characteristics ->what a person does which include voice prints, signatures, typing patterns, key-stroke pattern, gait which is prints, signatures, typing patterns, key-stroke pattern, gait which is affected by mood, stress, fatigue, and how long ago you woke upaffected by mood, stress, fatigue, and how long ago you woke up

HISTORYHISTORY Fingerprints were first used to identify individuals in ancient ChinaFingerprints were first used to identify individuals in ancient China The Henry Classification system, named after Edward Henry who The Henry Classification system, named after Edward Henry who

developed and first implemented the system in 1897 in India, was developed and first implemented the system in 1897 in India, was the first method of classification for fingerprint identification based the first method of classification for fingerprint identification based on physiological characteristics on physiological characteristics

First commercial use of biometrics was in the 1960's and 1970's. First commercial use of biometrics was in the 1960's and 1970's. In the late 1960's FBI developed a system for automatically In the late 1960's FBI developed a system for automatically

checking /comparing and verifying fingerprints. checking /comparing and verifying fingerprints. In early 1970's FBI installed automatic fingerprinting scanning In early 1970's FBI installed automatic fingerprinting scanning

system.system. In late 1970's Idnetiymat installed the first biometrics physical In late 1970's Idnetiymat installed the first biometrics physical

access control systems in top secret US Government sites. The access control systems in top secret US Government sites. The system was based on Hand Geometry.system was based on Hand Geometry.

Late 1970s development of voice recognition systems.Late 1970s development of voice recognition systems. 1980's Biometrics systems using Iris scan and that with face 1980's Biometrics systems using Iris scan and that with face

recognition system developed. recognition system developed.

BIOMETRIC FORMSBIOMETRIC FORMS

• Fingerprints Hand veinsFingerprints Hand veins• Voiceprints Retina ScanVoiceprints Retina Scan• Facial features SignatureFacial features Signature• Writing patterns Voice RecognitionWriting patterns Voice Recognition• Iris patterns Facial thermographIris patterns Facial thermograph• Hand geometry OdorHand geometry Odor• Keystrokes GaitKeystrokes Gait• DNA Ear canalDNA Ear canal

CHARACTERISTICSCHARACTERISTICS

UniversalityUniversality: Every person should have the characteristic. People who are : Every person should have the characteristic. People who are mute or without a fingerprint will need to be accommodated in some way. mute or without a fingerprint will need to be accommodated in some way.

UniquenessUniqueness: Generally, no two people have identical characteristics. : Generally, no two people have identical characteristics. However, identical twins are hard to distinguish. However, identical twins are hard to distinguish.

PermanencePermanence: The characteristics should not vary with time. A person's face, : The characteristics should not vary with time. A person's face, for example, may change with age. for example, may change with age.

CollectibilityCollectibility: The characteristics must be easily collectible and measurable. : The characteristics must be easily collectible and measurable. PerformancePerformance: The method must deliver accurate results under varied : The method must deliver accurate results under varied

environmental circumstances. environmental circumstances. AcceptabilityAcceptability: The general public must accept the sample collection routines. : The general public must accept the sample collection routines.

Nonintrusive methods are more acceptable. Nonintrusive methods are more acceptable. CircumventionCircumvention: The technology should be difficult to deceive. : The technology should be difficult to deceive.

BIOMETRIC SYSTEMBIOMETRIC SYSTEM

FINGERPRINTFINGERPRINT Oldest form of BiometricsOldest form of Biometrics Highly ReliableHighly Reliable Uses distinctive features of fingersUses distinctive features of fingers

Finger-scan biometrics is based on the distinctive Finger-scan biometrics is based on the distinctive characteristics of the human fingerprint characteristics of the human fingerprint

A fingerprint image is read from a capture device A fingerprint image is read from a capture device Features are extracted from the image Features are extracted from the image A template is created for comparisonA template is created for comparison

FINGER PRINT RECOGNITIONFINGER PRINT RECOGNITION Global features-Global features- you can see with the naked eye.you can see with the naked eye. o Basic Ridge PatternsBasic Ridge Patternso Pattern Areao Core Pointo Deltao Line typeso Ridge Count

Local features- Local features- Minutia Points are the tiny, unique characteristics of Minutia Points are the tiny, unique characteristics of fingerprint ridges that are used for positive identification. fingerprint ridges that are used for positive identification.

It is possible for two or more individuals to have identical global features but It is possible for two or more individuals to have identical global features but still have different and unique fingerprints because they have local features - still have different and unique fingerprints because they have local features - minutia points - that are different from those of others.minutia points - that are different from those of others.

STAGES

Fingerprint Scanning

Fingerprint Matching

Fingerprint Classification

FINGERPRINT SCANNING It’s the acquisition and recognition of a person’s fingerprint characteristics for identification purposes optical method ->which starts with a visual image of a finger. semiconductor-generated-> electric field to image a finger

FINGERPRINT MATCHINGMinutiae-based ->techniques first find minutiae points and then map their relative placement on the finger. Correlation-based ->techniques require the precise location of a registration point and are affected by image translation and rotation.

Fingerprint ClassificationFingerprint Classification It is a technique to assign a fingerprint into one of the several It is a technique to assign a fingerprint into one of the several

pre-specified types already established in the literature which pre-specified types already established in the literature which can provide an indexing mechanism can provide an indexing mechanism

An input fingerprint is first matched at a coarse level to one of An input fingerprint is first matched at a coarse level to one of the pre-specified types and then, at a finer level, it is compared the pre-specified types and then, at a finer level, it is compared to the subset of the database containing that type of fingerprints to the subset of the database containing that type of fingerprints

An algorithm to classify fingerprints into five classes, namely, An algorithm to classify fingerprints into five classes, namely,

whorl, right loop, left loop, arch, and tented arch.whorl, right loop, left loop, arch, and tented arch. An automatic recognition requires that the input fingerprint be An automatic recognition requires that the input fingerprint be

matched with a large number of fingerprints in a databasematched with a large number of fingerprints in a database . . Input fingerprint is required to be matched only with a subset of Input fingerprint is required to be matched only with a subset of

the fingerprints in the databasethe fingerprints in the database

LOOP, ARCH AND WHORL

IMAGE CAPTUREIMAGE CAPTUREMinutia matching -microscopic approach that Minutia matching -microscopic approach that

analyzes the features of the fingerprint, such as analyzes the features of the fingerprint, such as the location and direction of the ridges, for the location and direction of the ridges, for matchingmatching

Global pattern matching- macroscopic Global pattern matching- macroscopic approach where the flow of the ridges is approach where the flow of the ridges is compared at all locations between a pair of compared at all locations between a pair of fingerprint imagesfingerprint images

MINUTIA MATCHING

IMAGE CAPTUREIMAGE CAPTURE Optical Scanner - captures a fingerprint image using a light source refracted Optical Scanner - captures a fingerprint image using a light source refracted

through a prism through a prism Thermal Scanner - very small sensor that produces a larger image of the Thermal Scanner - very small sensor that produces a larger image of the

finger and is contrast-independent finger and is contrast-independent Capacitive Scanner - uses light to illuminate a finger placed on a glass Capacitive Scanner - uses light to illuminate a finger placed on a glass

surface and records the reflection of this light with a solid-state camera surface and records the reflection of this light with a solid-state camera

Image ProcessingImage Processing image features are detected and enhanced for verification against the image features are detected and enhanced for verification against the

stored minutia file. Image enhancement is used to reduce any stored minutia file. Image enhancement is used to reduce any distortion of the fingerprint caused by dirt, cuts, scars, sweat and dry distortion of the fingerprint caused by dirt, cuts, scars, sweat and dry skin. skin.

Image VerificationImage Verification At the verification stage, the image of the fingerprint is compared against the At the verification stage, the image of the fingerprint is compared against the

authorized user’s minutia file to determine a match and grant access to the authorized user’s minutia file to determine a match and grant access to the individual individual

IMAGE ACQUISITONIMAGE ACQUISITON

PROCESSPROCESS

FINGERPRINT PC LOCK

FINGERPRINT DOOR LOCK

ISSUESISSUESPrivacy - Comparison and storage of unique Privacy - Comparison and storage of unique

biological traits makes some individuals feel biological traits makes some individuals feel that their privacy is being invaded.that their privacy is being invaded.

False Rejection- False rejection occurs when a False Rejection- False rejection occurs when a registered user does not gain access to the registered user does not gain access to the system. system.

False Acceptance-False acceptance is when an False Acceptance-False acceptance is when an unauthorized user gains access to a unauthorized user gains access to a biometrically protected system.biometrically protected system.

Accuracy- instances where a fingerprint may Accuracy- instances where a fingerprint may become distorted and authorization will not be become distorted and authorization will not be granted to the user. granted to the user.

Hand GeometryHand Geometry This approach uses the geometric shape of the hand for authenticating a This approach uses the geometric shape of the hand for authenticating a

user's identity.Individual hand features are not descriptive enough for user's identity.Individual hand features are not descriptive enough for identification. However, it is possible to devise a method by combining various identification. However, it is possible to devise a method by combining various individual features to attain robust verification. individual features to attain robust verification.

Hand geometry systems use an optical camera to capture two orthogonal Hand geometry systems use an optical camera to capture two orthogonal twodimensional images of the palm and sides of the hand, offering a balance twodimensional images of the palm and sides of the hand, offering a balance of reliability and relative ease of use. of reliability and relative ease of use.

They typically collect more than 90 dimensional measurements, including They typically collect more than 90 dimensional measurements, including finger width, height, and length; distances between joints; and knuckle finger width, height, and length; distances between joints; and knuckle shapes. These systems rely on geometry and do not read fingerprints.shapes. These systems rely on geometry and do not read fingerprints.

Hand geometry readers can function in extreme temperatures and are not Hand geometry readers can function in extreme temperatures and are not impacted by dirty hands (as fingerprint sensors can be). impacted by dirty hands (as fingerprint sensors can be).

Hand geometry devices are able to withstand wide changes in temperature and Hand geometry devices are able to withstand wide changes in temperature and function in a dusty environment. function in a dusty environment.

Hand Geometry vs FingerprintsHand Geometry vs Fingerprints Unlike fingerprints, the human hand isn't unique. One can use Unlike fingerprints, the human hand isn't unique. One can use

finger length, thickness, and curvature for the purposes of finger length, thickness, and curvature for the purposes of verification but not for identification. verification but not for identification.

For some kinds of access control like immigration and border For some kinds of access control like immigration and border control, invasive biometrics (e.g., fingerprints) may not be control, invasive biometrics (e.g., fingerprints) may not be desirable as they infringe on privacy. In such situations it is desirable as they infringe on privacy. In such situations it is desirable to have a biometric system that is sufficient for desirable to have a biometric system that is sufficient for verification. As hand geometry is not distinctive, it is verification. As hand geometry is not distinctive, it is

the ideal choice. the ideal choice. Hand geometry data is easier to collect. With fingerprint Hand geometry data is easier to collect. With fingerprint

collection good frictional skin is required by imaging systems, collection good frictional skin is required by imaging systems, and with retina-based recognition systems, special lighting is and with retina-based recognition systems, special lighting is necessary. Additionally, hand geometry can be easily combined necessary. Additionally, hand geometry can be easily combined with other biometrics, namely fingerprint. One can envision a with other biometrics, namely fingerprint. One can envision a system where fingerprints are used for (infrequent) identification system where fingerprints are used for (infrequent) identification and hand geometry is used for (frequent) verificationand hand geometry is used for (frequent) verification. .

IRIS RECOGINITIONIRIS RECOGINITION

IRIS RECOGNITIONIRIS RECOGNITION• Pattern recognition techniquePattern recognition technique - Iris - Iris

recognition combines computer vision, recognition combines computer vision, pattern recognition, statistics, and the pattern recognition, statistics, and the human-machine interface.human-machine interface.

• Identification by mathematical analysis of Identification by mathematical analysis of

the random patterns.the random patterns.

• Based upon the qualities of the Iris.Based upon the qualities of the Iris.

• Each person has a distinct pattern of Each person has a distinct pattern of filaments, pits and striations in the colored filaments, pits and striations in the colored rings surrounding the pupil of each eye.rings surrounding the pupil of each eye.

Iris is a protected internal organ whose Iris is a protected internal organ whose random texture is stable throughout liferandom texture is stable throughout life

IRIS PROPERTIESIRIS PROPERTIES

High degree of RandomnessHigh degree of Randomness No two Iris are alike – No two humans have No two Iris are alike – No two humans have

same iris even one just have different iris in same iris even one just have different iris in both eyes.both eyes.

Stable in a persons lifeStable in a persons life Doesn't vary with changesDoesn't vary with changes

IRIS SCANIRIS SCAN

Camera at close proximityCamera at close proximity

Captures photographCaptures photograph

Uses Infra red light to illuminateUses Infra red light to illuminate

High resolution photographHigh resolution photograph

IRIS SCAN IMAGEIRIS SCAN IMAGE

IRIS CODEIRIS CODE Localization of inner and outer boundaries-Localization of inner and outer boundaries- We detect the inner boundary between the pupil We detect the inner boundary between the pupil

and the iris by means of threshold. The outer and the iris by means of threshold. The outer boundary of the iris is more difficult to detect boundary of the iris is more difficult to detect because of the low contrast between the two because of the low contrast between the two sides of the boundary. We detect the outer sides of the boundary. We detect the outer boundary by maximizing changes of the boundary by maximizing changes of the perimeter- normalized sum of gray level values perimeter- normalized sum of gray level values along the circle. along the circle.

Pattern of 512 bytesPattern of 512 bytes Complete and Compact descriptionComplete and Compact description More complete than features of DNAMore complete than features of DNA

IRIS SYTEMIRIS SYTEM

Pre processing

Feature-extraction

Identification Verification

Stored templates

Uniform distribution

Reject

AcceptIris scan image capture

Iris localization

Iris code comparison

IRIS RECOGNITIONIRIS RECOGNITION

Database of millions of recordsDatabase of millions of records Iris code generated is compared Iris code generated is compared Searching algorithm based on Properties Searching algorithm based on Properties

of Irisof IrisOrder of a few secondsOrder of a few seconds

AVIATION – IRIS DEVICESAVIATION – IRIS DEVICES

Voice & Signature recognitionVoice & Signature recognition

Does not measure the visual featuresDoes not measure the visual features In voice recognition sound vibrations of a In voice recognition sound vibrations of a

person is measured and compared to an person is measured and compared to an existing sample.existing sample.

Dynamic signature verification technology Dynamic signature verification technology used.used.

Analyzing the shape, speed, stroke, and Analyzing the shape, speed, stroke, and pen pressure and timing information pen pressure and timing information during the act of signing.during the act of signing.

Face & Palm recognitionFace & Palm recognition

In order to recognize a person, one In order to recognize a person, one commonly looks at face, which distinguish commonly looks at face, which distinguish one person from another.one person from another.

In palm recognition a 3-dimensional image In palm recognition a 3-dimensional image of the hand is collected. of the hand is collected.

The feature vectors are extracted and The feature vectors are extracted and compared with the database feature compared with the database feature vectors.vectors.

BIOMETRIC PERFORMANCEBIOMETRIC PERFORMANCE

FARFAR

The FAR is the chance that someone The FAR is the chance that someone other than you is granted access to other than you is granted access to your account.your account.

Low false acceptance rate is most Low false acceptance rate is most important when security is the priorityimportant when security is the priority

BIOMETRIC PERFORMANCEBIOMETRIC PERFORMANCE

FRRFRR

The FRR is the probability that are not The FRR is the probability that are not authenticated to access your account.authenticated to access your account.

A low FRR is required when convenience A low FRR is required when convenience is the important factoris the important factor

FINGERPRINT PERFORMANCEFINGERPRINT PERFORMANCE

FAR - As low as 1 in 1,000,00FAR - As low as 1 in 1,000,00

FRR –around 4%FRR –around 4%

IRIS PERFORMANCEIRIS PERFORMANCE

FAR - As low as 1 in 1,000,000FAR - As low as 1 in 1,000,000

FRR –around 2%FRR –around 2%

APPLICATIONSAPPLICATIONS

Criminal identificationCriminal identification Prison securityPrison securityATMATMAviation securityAviation securityBorder crossing controlsBorder crossing controlsDatabase access Database access

SOME BIOMETRICS STILL IN SOME BIOMETRICS STILL IN DEVELOPMENTDEVELOPMENT

Scent Scent

Ear Shape Ear Shape

Finger nail bed Finger nail bed

Facial 3DFacial 3D

REFERENCESREFERENCES

www.biometix.comwww.biometix.com www.biomet.orgwww.biomet.org www.owlinvestigation.comwww.owlinvestigation.com www.ddl.ision.co.ukwww.ddl.ision.co.uk www.zdnetindia.com/techzone/resourceswww.zdnetindia.com/techzone/resources www.biodata.com.auwww.biodata.com.au

THANK THANK YOUYOU