biometria eyes

Upload: superlucido

Post on 07-Jul-2018

222 views

Category:

Documents


0 download

TRANSCRIPT

  • 8/18/2019 Biometria EYES

    1/9

    A collage of iris scans,

    showing the many small details

    that make these unique to each

    individual. Even identical twins

    have different iris scans

     as well as fingertips, of course).

     Photo: University of Cambridge)

    Ravi Das

    I I C S

    An Introduction to Biometrics

    Ever since the tragic events of 11

    September

     2001,

     security is a topic

    that has received much attention.

    We keep hearing in the news about

    security increasing at airports andseaports. There are many solutions

    to security. However, there is one

    solution that utilises a unique tech-

    nological approach: Biometrics.

    Biometrics leverages physiological

    characteristics to identify and  veri-

    fy people. This article reviews in

    some detail the biometric technol-

    ogies that are availabie today, and

    what is being envisioned for the

    future.

    Before examining the various biom etric  tech-

    nologies, it is important to expand upon the de-

    finition of biometrics.

    Biometrics Defined

    While detective novels and cop shows have

    long made us aware that our fingerprints are

    unique, perhaps less known is the fact that our

    bodies are unique in several other measurable

    areas as  well.  Biometrics technology uses

    those points of measurable uniqueness to de-

    termine our identities, and acts as a front end to

    This is how a facial recognition

    a system that requires precise identification

    before it can be accessed or used- That system

    could be a sliding door with electronic locking

    mechanisms, an operating device, or an app li-

    cation where individual users have their own

    rights and permissions.

    Of course, this is partly what passwords

    have done all along. Passwords determine

    identity through user knowledge: If you know

    the password, you can gain access to

    system. The proDlem is that a password

    nothing to do with your actual identity. P

    words can be stolen, and users can give

    passwo rds to others willingly or under

    striction), resulting in a system that is far

    open to far too many p eople. There is simp

    foolproof way to make password-prote

    systems completely safe from unautho

  • 8/18/2019 Biometria EYES

    2/9

    ion system.

    of the

    Individuals have physiological features that

    thought of as unique identifiers . More spe-

    Biometrics are automated methods of recog-

    The need for biometrics can be found in fed-

      state and local governments, in the  mili-

    ready b enefiting from these

     tech-

      data protection, remote access to re-

    ith other

     tech-

    Utilising biometrics for personal authentica-

    tion is becoming convenient and considerably

    more accurate than previous methods such as

    the utilisation of passwords or PINs. This is

    because biometrics links the event to a partic-

    ular individual (as already commented, a pass-

    word or token may be used by someone other

    than the authorised user), is convenient (noth-

    ing to carry or remem ber}, accurate (it provides,

    for positive authentication), can provide an

    audit trail and is becoming socially acceptable

    and inexpensive-

    By early 20 05, there was an impressive list of

    34 countries that already had a national bio-

    metric system in place or were developing it

    Australia, the Bahamas, Belgium, Bosnia and

    Herzegovina, Brazil, Brunei, Bulgaria, China,

    Colombia, Denmark, Estonia, Finland, France,

    Gernnany. Greece, Hong Kong, Ireland, Italy,

    Lebanon, Malaysia, the Netherlands, New

    Zealand,

      Oman, Pakistan, Philippines, Portu-

    gal,  Qatar, Russia, Slovakia, Spain, Sweden,

    Switzerland, the United Kingdom, and the

    United States. The industrial implications are

    self-evident. According to the International

    Biometric Group, totai biometric industry reve-

    nues grew from slightly less than $600 m illion in

    2002 to more than $1.2 billion in 2004, and are

    projected to attain $4-6 billion in 2008.

    How Biometrics Work

    Biometric systems consist of both hardware

    and software; the hardware c aptures the salient

    human characteristic(s), and the software inter-

    prets the resulting data and determines accept-

    ability.

    At the most simple level, biometric systems

    operate on a three-step process . First, a sensor

    takes an observation. The type of sensor and

    its observation will vary by biometric type.

    Second,

      the biometric system develops a way

    to describe the observation mathematically and

    produce a biometric signature. The method will

    again vary by biom etric type , but also from ven-

    dor to vendor. Third, the computer system in-

    puts the biometric signature into a comparison

    algorithm and compares it to one or more bio-

    metric signatures previously stored in its data-

    base. Other system components, or human

    operators, then use these result(s) for other

    actions such as allowing or denying access,

    sounding an afarm, etc.

    The crucial step in building an effective bio-

    metric system is enrollment. During enrollment

    each user, beginning with the administrator

    who controls the system, provides samples of

    from the scan and stores the data as a tem-

    plate. You then interact with the biometric de-

    vice again, and the system verifies that the da ta

    corresponds to the template. It the software

    fails to get a match, more tries may be needed,

    just as dictation software learns tc recognise

    the user's speech patterns over time. Once this

    procedure is complete, the system is opera-

    tional. The next time you try to access the sys-

    tem,  you are scanned by whatever device is

    being used (you might be asked to supply  a

    user name as well), and the hardware passes

    the data to the software, which checks the user

    templates. If there Is a match, you are granted

    access; otherwise, a message

      reports

     that

      the

    system can't identify the user.

    Let's us now examine in detail a real world

    example that utilises biometrics. The technolo-

    gy is fingerprint recognition, and the scenario is

    that of verification for physical access entry.

    Imagine that you are trying to enter a   high-

    Sharbat Gula, first photographed

      In

     1984

    when aged 12 in a refugee camp in

    Pakistan by National Geographic

    photographer Steve Curry, was traced

    18 years later to a remote part of

    Afghanistan vi/here she w as again p hoto-

    graphed by Mr. Curry. Prof. John Daug man,

    of the University of Cambridge Computer

    Laboratory, established that these protraits

    show the same person, by running his

    iris recognition algorithms on m agnified

    images of the eye regions in the two

    photographs.

    (Photo: University of Cambridge)

    security area. Before you can enter this area,

    you m ust first be in the database of people wh o

    are authorised tc enter. To be included into this

    database, you must first register your finger-

    print through the enrollment process. During

    enrollment, a number of pictures are taken of

    your fingerprints. These pictures are called

    samples, and the samples are then combined

    to form one typical sample. A mathematical for-

    mula called an extraction algorithm then

    Ravi Das is the President of HT G Advance Systems.

    Mr. Das

    '

     original article has been expanded by MT edi-

    torial staff with additiona l material from a v ariety of

    other open sources. The illustrations sourced lAEE

    originate from the paper.  An Introduction to Biometnc

    Recognition ba Anil K.Jain Atun  oss and Salil Prab

  • 8/18/2019 Biometria EYES

    3/9

    Schematic diagram of the working

    principle of a generic biometric system.

     Sou rce: internet)

    extracts the unique features from the sample,

    whic h are stored into a file called an enrollment

    template.

    Now that you have completed the enrollment

    process, you are ready for the next step - the

    verification process. With verification, we are

    attempting to answer the question Am I really

    whom I claim to be? Imagine yourself once

    again trying to acc ess the high security area. In

    order to have authorisation to enter, you must

    now verify yourself by placing your finger on

    top of the sefisor of the fingerprint scanner. The

    sensor will take a picture, or a sample, of your

    fingerprint. The extraction algorithm will then

    extract the unique features of your fingerprint

    and store it into a file called a verification tem-

    plate. The verification template is then com-

    pared to the enrollment template to determine

    how close the two templates match with each

    other, via a mathematical formula called a

    matching algorithm. Based o n this closeness, a

    Block  diagrams of enrol lment,

    veri f icat ion  an d  identi f icat ion shown

    using the four main modu les of

    a biometric system, i.e. sensor, feature

    extraction, matcher, and system database.

     Source: IEEE]

    SerEorDats

    Registration or

    Enroinent

    Sensor Data

    •>

    -

    Authentication

    Venficationor

    idertificabon

    Threshold arxJ

    Authenticate

    1

     

    YES NO

    Find and Process

    Biometnc

    Information

    *

    Create Template

    Find and Process

    Siometnc

    Information

    Create Templets

    Match and

    Generate Score

    number called a score is then co mpu ted. If this

    score is greater than a value called a threshold

    (this value is determined a nd set by the biom et-

    ric system's administrator), you are then

    authorised to enter the high security area. If the

    score is less than the thres hold, you are denied

    authorisation to enter, and the verification pro-

    cess will repeat again. Although a lot does hap-

    pen in the enrollment and verification process-

    template

    Quality

    checker

    Feature

    Extractor

    User interface

    Enrollment

    System DB

    claimed identity

    Feature

    Extractor

    Matcher

    (1 match)

    User interface

      erification

    one

    template

    True/False

    System DB

    Feature

    Extractor

    Matcher

     N matches)

    User interface

     

    System DB

    es,

      they only take a m

    of seconds to comple

    It is important to ap

    ciate the differ

    between  verification 

    identification With v

    cation, the system

    attempting to answer

    question His this pe

    really who they claim

    be?

    The previous ex

    ple demonstrates veri

    t ion.

      With identifica

    the system is rather tr

    to found a person, th

    supposed to be on

    database. To asce

    identity, the entire d

    base of biometric

    plates is searched

    determine if there

    match between your

    plate and all of the o

    templates in the datab

    In other words, the

    metric system is tryin

    recognise you. A perfect example of identi

    tion is AFIS (Automated Fingerprint Ide

    cation Services) that is used by many law

    forcement agencies to track known crimin

    A specific application of the identific

    process is the watchtist. In the watchlist ta

    the biometric system determines If

    individual's biometric signature matches

    corresponding signature of someone o

    watchlist. The individual does not make

    Identity claim, and is some cases does not

    sonally interact with the system in any

    Examples of the watchlist task could be c

    paring visitors to a public building against a

    rorist database, or comparing John Doe

    hospital to a missing persons list. The main

    ference between standard identification pr

    dures and the watchltst task is that while in

    former case the person is supposed to be i

    database and the system is trying to ide

    him/her, in the latter the question is, Is

    person in the database? If so, who are the

    Biometric Technologies

    The main biometric technologies avail

    today include fingertip recognition, hand ge

    etry recognition, facial recognition, voice

    ognition, and iris/retinal recognition. The

    geometry and the fingerprint recognition d

    es have been around the longest. There

    also other technologies which are b

    explored today, and wiil be briefly discusse

    Fingertip Recognition

    Fingerprint recognition looks at the un

    patterns found on fingertips. A greater va

    of fingerprint recognition devices is avail

    than for any other biometric. Some emulate

    traditional police method of matching minu

    i.e. the points o n the fingertips where print

     

    es end or divide; others use straight pat

    matching devices; and still others are a

    more unique, including things like moire fr

  • 8/18/2019 Biometria EYES

    4/9

    The fingerprint scanners shine a light through

     A 100 match is not required - only one

    Fingerprinting has a head start over other

    High Accuracy.  Fingerprint technology is

    accurate; however, a fingerprint scanner

    might deny access if you place too much or

    too little pressure on it.

    Undemanding.

     Fingerprinting doesn't signifi-

    cantly

     dr in

     computing resources-u nlike face

    recognition (q,v,), which relies on full-motion

    video,

    Inexpensive. Fingertip scanners can even be

    embedde d in keyboards and mice,

    Easy Installation.  Fingerprint scann ers are as

    simple toset upa sa new keyboard and require

    no tr ining to use.

    As the prices of these devices and process-

      fall,

      using fingerprints for user verifi-

     tech-

    Fingerprint verification may be a good choice

    s, where you can give users

    ogies High, Medium and Low).

    ource: lAEE}

    The relationship between False

    Accept R ate FAR) and the probability

    of verification.

     Source: FBI)

    access application area seems to be based

    almost exclusively on fingerprints, due to the

    relatively low co st, small size, and ease of inte-

    gration of fingerprint authentication devices.

    On the other hand, fingertip recognition is

    rather invasive as literally a hands-on te chno lo-

    gy. Also, its simplest forms are rather easy to

    spoof (for instance, simply breathing on a low-

    cost PC mouse with built-in fingertrip recogni-

    tion device may be enou gh to fool it), and som e

    security implications should be carefully pon-

    dered. For instance, fingerprint recognition

    devices are being introduced on luxury cars,

    but in April 2005 a band of car hijackers in

    Kuala Lumpur simply chopped off a car's

    owner finger to get around the vehicle's hi-tech

    security system.

    Facial Recognition

    Recognising the shapes and positioning of

    the features of a person's face is a complex

    task, and facial recognition software has only

    D N A

    Far

    [ dec

    Facial thermogram

    Fingerprint

    Gai l

    Hand geometry

    Hand vein

    Iris

    Keystroke

    Odor

    Palmprint

    Retina

    U

    n

    v

    s

    y

    H

    M

    H

    H

    M

    M

    M

    M

    H

    L

    H

    M

    H

    D

    i

    s

    n

    v

    H

    M

    L

    H

    H

    L

    M

    M

    H

    L

    H

    H

    H

    P

    e

    m

    a

    e

    H

    H

    M

    L

    H

    L

    M

    M

    H

    L

    H

    H

    M

     

    o

    e

     

    y

    L

    M

    H

    H

    M

    H

    H

    M

    M

    M

    L

    M

    I,

    P

    e

    o

    m

    a

    e

    H

    M

    L

    M

    H

    L

    M

    M

    H

    L

    L

    H

    H

     

    c

    e

    a

    y

    L

    H

    H

    H

    M

    H

    M

    M

    L

    M

    M

    M

    L

     

    i

    r

    c

    u

    m

    v

    o

    L

    M

    H

    L

    M

    M

    M

    L

    L

    M

    L

    M

    L.

    recently begun to accomplish it. First a camera

    captures the image of a face, and then the s oft-

    ware extracts pattern information it can com-

    pare with user templates. Face recognition

    uses one of two technique s. The first compa res

    feature sizes and relationships, such as nose

    length and the distance between your eyes.

    The second method matches your most signif-

    icant image data, like the size and shape of

    your nose, ears, eyes and mouth with a record

    of your face stored in a database.

    Tbe m inutiae in a fingertips used by a

    recognition system to create the template.

     Photo: CNR)

    With either method, no one has to share a

    potentially grimy finger scanner. Better yet.

    face recognition is completely unobtrusive and

    requires no special action from the subject: the

    system captures your face in moving video,

    isolates features, and identifies them on the fly.

    And,

      the system is smart enough to recognis

    your face even if you forgot to shave or your

    eyes are bloodshot-

    Facial recognition is highly accurate, and fur-

    thermore the software provides an audit trail -

    with time, date, and face print - of anyone try-

    ing to break into the security system. On the

    other ha nd, the system is rather expensive, it is

    complex to set up, and is demanding in terms

    of computing power. Facial recognition also

    has some shortcomings when trying to identify

    individuals in different environmental settings

    (such as changes in lighting or/and changes in

    the physical facial features of people, such as

    new scars). Also, of all of the biom etric techn ol-

    ogies, facial recognition has to deal the most

    with privacy rights issues.

    These aspects have slowed down its wide-

    spread acceptance. Popular applications for

  • 8/18/2019 Biometria EYES

    5/9

    Iris/Retinal Recognition

    The two eye-based systems, iris and retina,

    are generally considered to offer the best

    security, because of tbe distinctiveness of the

    patterns and the quality of tbe capture devices.

    Further, the structure of the iris and the retina

    rarely change over the lifetime of an individua l.

    There has been some confusion between iris

    and retinal recognition, in tbat tbe two are

    apparently similar. However, the two technolo-

    gies are very much different.

    TTie pattern of the iris (the band of tissue that

    surrounds tbe p upil of the eye) is com plex, w ith

    a variety of characteristics unique in each per-

    son.

      Iris-based biometric involves analysing

    features found in the colored ring of tissue that

    surrounds tbe pupil. Iris scanning, undoubtedly

    the less intrusive of the eye-related biometrics,

    uses a fairly conventional camera element and

    requires no close conta ct betwe en the user and

    tbe reader. In addition, it has the potential for

    higher than average template matching perfor-

    mance. Iris biometrics work with glasses in

    place and is one of the few devices that can

    work well in identification mode. On the other

    hand,

     ease of use and system integration have

    not traditionally been strong points with iris

    scanning devices, but you can expect improve-

    ments in tbese areas as new products emerge.

    Some popular applications for ihs scanning

    are verifying employees, and expediting the

    immigration process for incoming passengers

    at airports. Also, iris recognition has been used

    to identify refugees seeking hu manitarian aid in

    Afghanistan.

    Retina recognition is probably the single

    most secure of all biometric systems. It works

    with the retina, the layer of blood vessels locat-

    ed at the back of the eye near the optic nerve.

    This technique involves using a low-intensity

    light source through an optical coupler to scan

    the unique p atterns of the retina. The only thing

    that is actually determined is the pattern of the

    blood vessels, but since this pattern is unique

    in each person, identification can be precise.

    Retinal scanning can be quite accurate, but

    the retinal image is difficult to capture and dur-

    ing enrollment the user must look into a recep-

    tacle and focus on a given point while holding

    very still so the camera can perform the cap ture

    properly. This is not particularly convenient if

    you wear glasses or are concerned about hav-

    ing close contact with the reading device. For

    these reasons, retinai scanning is not warmly

    accepted by all users, even though the technol-

    ogy itself can work   well.

    Retinal recognition is used for high security

    physical access entry, such as nuclear and

    government installations, where use r s acce p-

    tance is not a matter for particular concern.

    Hand Geometry Recognition

    With the hand geometry system, the user

    aligns a hand according to guide marks on a

    hand reader hardware, and the reader capt

    a three-dimensional Image of the fingers

    knuckles and stores the data in a template

    Hand geometry has been around for sev

    years, and it was used for a security syste

    the 1996 Olympic Games. It offers a good

    ance of performance characteristics and is

    atively easy to use. Accuracy can be very

    if desired and flexible performance tuning

    configuration can accommodate a wide ra

    of application s. Further, ease of integration

    otber systems and processes makes h

    geometry an obvious first step for many

    metric projects. Hand geometry might be

    able where there are more users or whe re u

    access the system infrequently and are

    haps less disciplined in their approach to

    system. The most popular applications so

    are are time and attendance recording.

    Finger Geometry Recognition

    These devices are similar to hand geom

    systems. The user places one or two fin

    beneath a camera that captures the sha

    and lengths of the areas of the finger and

    knuckles. The system constructs a three

    mensional image and matches the data aga

    the stored templates to determine identity.

    Palm Recognition

    Similar to fingerprint recognition, palm

    metrics (not to be confused w ith hand geo

    Examples of biometric characteristics that are or could be used for biometric systems: a) DNA, b) ear, c) face,

    d) facial therm ograph , e) hand therm ograp h, f) hand vein, g) fingerprint, h) gait, i) hand geo metry, j) iris, k) palmprint, I) retina, m) signatu

    and n) voice.

     Source: lAEE)

  • 8/18/2019 Biometria EYES

    6/9

    ) focuses on the various textures , such as

    ges and other minutiae, found on the palm.

    The voice recognttion method captures the

    with

      advanced voice systems can extend

      long-

    Voice authenticators use a telephone or

    to work with background

    Signature verification systems have one

    rson's signature as proof of identity.

    Actually, signature recognition systems, also

    called dynamic signature verification systems,

    go far beyond simply looking at the shape of a

    signature: They measure both the distinguish-

    ing features of the signature as such,

      nd

      the

    distinguishing features of the process of

      sign-

    ing.  These features include pen pressure,

    speed,

     and the points at which the pen is lifted

    from the paper. These behavioural patterns are

    captured through a specially designed pen or

    tablet (or both) and compared with   a template

    of process patterns.

    Bkxnvtrtc Acc*ss

    Control Cofw ol*

    QuatMh ESE-100O,

    8 Port RS-232 Strtal O«vtc«

    Eth«m«t

    Top;

     A fingerprint lock

    system.

      Photo: Smarthome)

    Middle: IGI Infinite

    Group and U ltra-Scan

    Corp. have developed

    an innovative fingertip

    technology based on

    ultrasonic scanning.

    This is claimed to raise

    scanning accuracy

    to levels previously

    unattainable within

    the industry.

     Photo: IGI)

    The problem is that our

    signatures vary significant-

    ly over time and from one

    instance to another, so

    strong accuracy requires

    multiple samples and an

    extended verification pro-

    cess.

    Keyboard Dynamics

    Keyboard dynamics  is a

    specific biometric tech nol-

    ogy for computer access

    security. It measures the

    dwell time (the length of time you hold down

    each key) as well as flight time (the time it takes

    you to move between keys). Taken over the

    course of several login sessions, these two

    metrics produce a measurement of rhythm

    unique to each user. Once the biometric data is

    collected, it is encrypted and stored (locally In

    the case of the desktop-only products, or in  a

    central database for the netvi/ork solutions).

    When a user tries to log on, the software com -

    pares the incoming biometric data against the

    stored data. Biometrics template can also be

    stored in a smart card which offers "persona

    confidentiality" as the template need not be

    stored in a central server (or service p roviders)

    Other Technologies

    There are other biometric technologies that

    are being examined today, but there are no

    commercial applications available yet. Re-

    searchers are developing or examining the fea-

    sibility of systems based on the analysis of

    DNA (currently too slow to be of real use), vein

    patterns, thermograms (facial, hand or hand

    veins), gait recognition (the way people walk),

    earlobe recognition, brain mapping, and even

    bodily odours.

    Limitations of Biometrics

    The success of a biometric system is meas-

    ured according to a number of criteria, and

    each technology has both strengths and weak-

    nesses. The most important criteria are con-

    cerned with accuracy, and involve the con-

    cepts of the False Reject Rate (also referred to

    as FRR or Type t Errors), and the False Accept

    Rate (a,k.a. FAR or Type 2 Errors). The False

    Reject Rate can be defined as the proba bility o

  • 8/18/2019 Biometria EYES

    7/9

    The dots represent the main measurement

    points for a facial recognition system.

     Photo: Automa)

    the chances that a legitimate, registered user

    will be denied access to the high security area

    by the fingerprint scanner? The False Accept

    Rate can be defined as the probability of an

    impostor being granted authorisation by the

    biometric system. For example, once again

    referring to the verification scenario, what are

    the chances that an impostor will be granted

    access to the high security area by the finger-

    print scanner?

    It is important to appreciate that the FRR and

    FAR are dependent not only on the technology

    being used and the characteristics and perfor-

    mance of the specific systems, but also and

    indeed critically on the threshold level as estab-

    lished by the administrator. Ideally, we vi/ould of

    course like to be able to set our threshold so

    that the probability of verification is 100 and

    both the FRR and FAR are 0 . Unfortunately,

    that is not possible, so we must compromise.

    This compromise is a bit difficult, because the

    probability of verification and the FAR are not

    Denomination of the main points in the iris

    that are useful for recognition purposes.

     Photo: University of Cambridge)

    The Handpunch 2000 hand geometry

    recognition system

    by Recognition Systems Inc.

     Photo: Recognition Systems)

    separated entities; rather, they are connected

    with each other. If we raise the verification

    threshold, the FAR decreases, but the probab il-

    ity of correct verification also decreases. If we

    lower the verification threshold, the probability

    of correct verification increases, but so does

    the False Accept Rate.

    The False Accept Rate and the False Reject

    Rate are two common criteria used in evaluat-

    ing the performance of biometric systems, and

    biometric product vendors often cite them in

    their product descriptions. However, they don't

    present a complete picture. The fact is,

    people's physical traits change over time,

    especially with alterations due to accidents or

    aging.

      And even in the short term, problems

    can occur because of humidity in the air, dirt

    and sweat on the user (especially w ith finger or

    hand systems), and inconsistent ways of inter-

    facing with the system, such as not taking

    enough time for the system to make an accu-

    rate identification. Further, users of biometric

    systems, like the users of all systems, must be

    trained to use them most efficiently.

    These and other issues limit the accuracy of

    biometric devices.

     Still,

      there's little doubt that

    biometric systems are more accurate than

    crypts

    radial furrow i

    pigment frill

    pupilary area

    ciliary are a

    other kinds of security systems, beca

    they're based on users' actual physical cha

    teristics, not on what they knovi/ (as with p

    words) or what they're carrying (such a

    badges).

    Biometrics success is also judged via a n

    ber of other factors. Vulnerability to fraud,

    known as barrier to attack, reflects how lik

    is that a person can fraudulently get past

    security (see below). Long-term stability d

    with issues such as whether a system is u

    for very infrequent users, as welt as whethe

    not users' characteristics alter over time. O

    effectiveness measures can include fac

    that m ight interfere with the system , its size

    its ease of use.

    Vulnerability

    The ease by which a biometric system

    be defeated or spoofed determines its vu

    ability. This encomp asses a numb er of d iffe

    considerations, including:

    -  Liveness Examples include spoofing a

    recognition device using a picture of

    authorised person, or a tape recording o

    authorised person's voice on speaker re

    nition system;

    -  Deception Exampfes include an impo

    attempting numerous hand geometry

    numbers until he finds one for which his h

    is a sufficient matc h, or a latex glove w ith

    fingerprints of an authorised person mo

    into it;

    -  Data Security The template informatio

    some netvi/orked biometric sensors is tr

  • 8/18/2019 Biometria EYES

    8/9

    mitted to a processor

      or

     analysis. Data secur-

    ity in this contex t refers to the interception and

    subsequen t m isuse of this data to circurTivent

    the system;

    The manner in which an unattended

    device is installed may render it vulnerable

     to

     a

    physical attack in an effort to defeat it. Some

    devices used in access control applications

    have built-in relays that unlock portals, so

    opening the device and shorting these con-

    tacts

     vi ouid

     be one way to defeat the system.

    Some of the limitations inherent with uni-

    Retina recognition

    systems are arguably

    the most secure

    of all biometrics.

    However, they are not

    immune from user s

    acceptance problems.

    (Photo: biometricwatch)

    Position and structure

    of the retina.

    (Photo: biometricwatch)

    tems, are expected to be more reliable due to

    the presence of multiple, independent pieces of

    evidence. These systems are also able to meet

    the stringent performance requirements im-

    posed by various applications. Further, multi-

    modal biometric systems provide anti-spoofing

    measures by making it difficult for an intruder to

    simultaneously spoof the multiple biometric

    traits of a legitimate user. By asking the user to

    present a random subset of biometric traits

    5AFAEL^>

      Muiti

      iometric Login

     dentification   I   nput data

     

    r

    The Retina

    optic Nerve Head

    (e,g.,

     right index and right m iddle fingers, in that

    order), the system ensures that a live user is

    indeed present at the point of data acquisition.

    Thus, a challenge-response type of authentica-

    tion can be facilitated using multimodal biomet-

    ric systems,

    A multimodat biometric system can operate

    in one of three different modes: serial mode,

    parallel mo de, or hierarchical m ode. In the

     seri-

    al mode of operation, the output of one biomet-

    ric trait is typically used to narrow down the

    number of possible identities before the next

    trait is used. This serves as an indexing sch eme

    in an identification system. For example, a mul-

    timodal biometric system using face and finger-

    prints could first employ face information to

    retrieve the top few matches, and then use fin-

    gerprint information to converge onto a single

    identity. This is in contrast to a parallel m ode of

    operation where information from multiple traits

    is used simultaneously to perform recognition.

    This difference is crucial. In the cascade oper-

    ational mode, the various biometric character-

    istics do not have to be acquired simultaneou s-

    ly. Further, a decision could be arrived at wi th-

    out acquiring all the traits, which reduces the

    overall recognition time. In the hierarchical

    scheme , individual classifiers are combine d in a

    tree-like structure.

    Rafael was contracted by the Israeli MoD

    to evaluate face recognition technologies

    and determine whether these can be

    used in the w ar against terrorism.

    The outcome of the study suggested

    multimodal biometrics, involving both

  • 8/18/2019 Biometria EYES

    9/9