Scribd Logo
Upload

Welcome to Scribd!

  • 92 views

    An Introduction On Several Biometric Modalities: Yuning Xu

    Uploaded by

    pummykid
    This document summarizes several biometric modalities including fingerprints, palmprints, iris scans, voice recognition, and facial recognition. It describes typical accuracy rates and applications for each modality. It also discusses techniques for extracting features from fingerprints like minutiae points and from palmprints using Gabor filters. The document notes that multimodal biometrics that combine two or more modalities can help overcome issues with any single modality and improve overall recognition rates.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd

    An Introduction On Several Biometric Modalities: Yuning Xu

    Uploaded by

    pummykid
    92 views35 pages
    This document summarizes several biometric modalities including fingerprints, palmprints, iris scans, voice recognition, and facial recognition. It describes typical accuracy rates and applications for each modality. It also discusses techniques for extracting features from fingerprints like minutiae points and from palmprints using Gabor filters. The document notes that multimodal biometrics that combine two or more modalities can help overcome issues with any single modality and improve overall recognition rates.

    Original Title

    biometrics

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document summarizes several biometric modalities including fingerprints, palmprints, iris scans, voice recognition, and facial recognition. It describes typical accuracy rates and applications for each modality. It also discusses techniques for extracting features from fingerprints like minutiae points and from palmprints using Gabor filters. The document notes that multimodal biometrics that combine two or more modalities can help overcome issues with any single modality and improve overall recognition rates.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    92 views35 pages

    An Introduction On Several Biometric Modalities: Yuning Xu

    Uploaded by

    pummykid
    This document summarizes several biometric modalities including fingerprints, palmprints, iris scans, voice recognition, and facial recognition. It describes typical accuracy rates and applications for each modality. It also discusses techniques for extracting features from fingerprints like minutiae points and from palmprints using Gabor filters. The document notes that multimodal biometrics that combine two or more modalities can help overcome issues with any single modality and improve overall recognition rates.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 35

    An introduction on several biometric

    modalities
    Yuning Xu
    ` The way human beings use to recognize each
    other: equip machines with that capability
    ` Passwords can be forgotten, tokens can be
    lost
    ` Post-9/11 era: thirst for ever-increasing
    security control
    ` …
    Typical
    Modality Example Invasiveness Accuracy
    Applications
    Law
    Fingerprint Moderate zzz enforcement,
    financial, POS

    Palmprint Moderate zzz Access control

    Moderate/ ATMs, access


    Iris zzz
    high control
    Hand Access control,
    Moderate z
    Geometry border control
    Surveillance,
    Face Low zz
    Passports
    Low/Moderat Access control,
    Voice z
    e logon
    Financial,
    Signature Moderate zz
    PocketPC
    ` The earliest, most widely studied, most
    acceptable, most widely deployed …
    ` Best commercial system: capable of
    identifying more than 98% of matches, with a
    false accept rate of 0.01% (NEC)
    ◦ As published by The Fingerprint Vendor Technology
    Evaluation (FpVTE) 2003 conducted by the National
    Institute of Standards & Technology (NIST)
    Ridge ending

    Enclosure
    Singular points
    Bifurcation

    Island

    Minutiae
    And there’s more:
    Ridges
    Ridge count
    Texture
    Orientation field
    Ridge frequency
    …
    ` If higher resolution scanner is used, i.e.
    ≥ 1000 pixels per inch (ppi). (current AFIS system
    500 ppi.
    Minutiae is the most used technique
    Minutia features

    Extraction of minutiae

    Image skeleton

    Gray-scale image
    High contrast Typical dry print Faint print

    Low contrast Typical wet print Creases / scars


    ` Traditional image processing
    methods (Gaussian, low pass etc.)
    cannot work
    ` Fingerprint: oriented texture
    ` Ridges only need enhancing in a
    direction parallel to their orientation,
    and at a specific frequency

    We need location specific filtering


    ` A sinusoidal plane of particular
    frequency and orientation,
    modulated by a Gaussian
    envelope: ,
    where

    and

    3-D

    1-D

    Fourier spectrum
    Divide into cells, Apply gabor filter
    each has an corresponding to a
    orientation angle specific orientation
    and a frequency and frequency, to
    each cell
    Each minutiae point has:
    • (x, y) location
    • Θ direction
    • pixels of the ridge
    associated with
    particular minutia

    Binarization

    Thinning
    Template
    Ridge • Compare all
    possible pairs of
    minutiae from the
    template and input
    Minutia di images, using the
    point ridges associated with
    minutiae.
    • Compute a
    correlation between
    Input Ridge two planar curves:

    S=
    ∑d D i i
    Minutia Di
    point ∑d ∑Di
    2
    i
    2
    Template
    For those pairs that
    pass the similarity
    threshold, estimate
    rotation and
    translation parameters
    using the two ridges
    associated, and align
    the two point sets
    Input
    • Turn each (x, y, Θ) into polar coordinates (r, e, Θ)
    • Find similarity using string matching algorithm
    ` Completely different
    approach
    ` Texture-based, rather
    than minutiae-based
    ` Experimental result has
    comparable level of
    accuracy as that of
    fingerprint or iris
    Copped Region Of Real parts of the
    Original palmprint image Interest results after filtering
    with the 4 Gabor
    filters

    Gabor filter revisited: The filters


    • a Gabor filter bank consists of 4
    complex gabor filter that differ
    only in its orientation, i.e. of
    orientation 0°, 45°, 90°, 135°
    • each filter is applied to the ROI,
    strengthening texture at a
    specific orientation, at the same
    time attenuating noise
    ` Let Mj be the magnitude of the image filtered with the jth
    filter, and Pj the phase, then PalmCode is generated
    according the following way: ( hr is the real part of the code,
    while hi is the imaginary part)
    Imaginary part of PalmCode

    Real part of PalmCode

    ` Hamming distance between two PalmCode is used


    as the similarity score
    Original image of an eye
    “Unrolled” iris

    Real Part of Iris Code

    • Any given iris has a unique


    texture that is generated
    through a random process
    before birth Imaginary Part of Iris Code
    • Gabor filters turn out, again, to
    be very good at detecting
    patterns in this unique texture
    • Matching is done again in
    hamming distance comparison
    • Uses texture information (lost in
    optical and minutiae based
    schemes)
    • Performs well with poor quality
    prints
    • Features are statistically
    independent from minutiae and
    can be combined with minutiae
    matchers for higher accuracy
    • Requires accurate alignment of
    the two prints (unreliable in poor
    prints)
    • Not invariant to translation,
    orientation and non-linear
    distortion.
    • Less Accurate than minutiae
    based matchers
    ` In theory, two codes independently
    generated from same person would
    be exactly the same
    ` In reality, not true, due to imperfect
    cameras, lighting or small rotational
    errors
    ` If the distance between them is
    below a certain threshold: match!
    ` Assumption: statistical
    independence, only the same
    person can fail test
    ` Iris has more randomness than the United Arab Emirates’
    other two modalities, as inferred by border control since
    the high accuracy of the technology 2001: 7 trillion
    comparions, 73,180 mis-
    matches
    At Disney World,
    fingerprints of guests
    are used to make sure
    the ticket is used by
    the same person from
    day to day
    Fingerprint minutiae data is
    US-VISIT, requires encrypted in this Biometric
    travelers to provide card for federal workers,
    fingerprint for mandated by DHS
    verifying identity
    IrisCode matching using Dr.
    Daugman’s algorithm helps
    confirms the woman found 18
    years later is indeed the famous
    Afghan girl

    1984 2002

    Image courtesy of National Geographics


    ` Stores image of facial recognition,
    fingerprint recognition, or iris
    scans (usually in JPEG format) in a
    Symbol for biometric
    chip
    passports, usually
    ` US-version to appear mid-2007 printed on the cover
    of the passports
    ` Even though recognition rates are increasing
    and many modalities are in the very high 90%,
    real-life applications do worse than this
    ` Failure to enroll is the biggest issue
    ◦ some people's fingerprints / palmprints are of poor
    quality (scars, calluses etc)
    ◦ Some people’s iris is mostly hidden under eyelid,
    some people are not comfortable with their iris
    being scanned
    ` The most practical way to overcome this is to
    use more than one modality
    ` Fingerprint with palmprint, with iris, with
    face, or even with voice, you name it
    ` The simpleminded approach is to combine
    the final match "scores"
    ◦ but this can be proven to be suboptimal
    ` More intelligent methods of fusion are being
    earnestly sought
    ` Focus of immediate research
    ` A. Jain and L. Hong, On-line Fingerprint
    Verification,Proc. 13th ICPR, Vienna, pp. 596-
    600, 1996.
    ` Kong, A., Zhang, D., and Kamel, M, Palmprint
    identification using featurelevel fusion, Pattern
    Recogn. 39, 3, Mar. 2006
    ` J Daugman, How Iris Recognition Works, IEEE
    Conf. on ICIP, 2002.
    ` Anil K. Jain, Sharath Pankanti, Salil Prabhakar, Lin
    Hong, Arun Ross, "Biometrics: A Grand
    Challenge," icpr, pp. 935-942, 17th
    International Conference on Pattern Recognition
    (ICPR'04) - Volume 2, 2004.

    You might also like