ppt fingerprint

Upload: sumanta-kar

Post on 03-Apr-2018

254 views

Category:

Documents


6 download

TRANSCRIPT

  • 7/28/2019 Ppt Fingerprint

    1/34

    1

    Fingerprint Based Ignition

    System

    ARIJIT MITRA

    SUNNY DUTTA

    SUMIT KUMAR SHRIVASTAVA

    NOOR HASSAN

    Mentor: Prof Siladitya Sen

  • 7/28/2019 Ppt Fingerprint

    2/34

    INDEX

    2

  • 7/28/2019 Ppt Fingerprint

    3/34

    3

    Biometric information is widely used these days in various security systems.Fingerprints are the oldest and perhaps most widely used for biometricidentifications

    Here we have chosen to focus on the use of fingerprints for vehicle ignition asopposed to the use of conventional keys which are not that safe in this ageof modern technology

    Block Diagram:

    Introduction

  • 7/28/2019 Ppt Fingerprint

    4/34

    System Blocks

    1.Fingerprint Recognition Software

    2.Hardware interface module

    3.Ignition System Module

    4

  • 7/28/2019 Ppt Fingerprint

    5/34

    5

    Fingerprint

    A fingerprint is the feature pattern of one finger . Each person has his

    own fingerprints with the permanent uniqueness. So fingerprints have being

    used for identification and forensic investigation for a long time

    Fingerprint

  • 7/28/2019 Ppt Fingerprint

    6/34

    66

    Fingerprint Classification

    Left Loop Right Loop

    Whorl Arch Tented Arch

    DeltaPore

  • 7/28/2019 Ppt Fingerprint

    7/34

    Minutia

    However, shown by intensive research on fingerprint

    recognition, fingerprints are not distinguished by their

    ridges and furrows, but by Minutia

    7

  • 7/28/2019 Ppt Fingerprint

    8/34

    8

    Minutiae-Based Approach

    Minutiae

    terminations bifurcations

    Ridge Valley

  • 7/28/2019 Ppt Fingerprint

    9/34

    9

    Verification (AFAS) vs. Identification (AFIS)

    Sensor

    Minutia

    Extractor

    Minutiae

    Matcher

    System

    Database

    System Level Design

    SystemDatabase

    Users

    Magnetic

    Card.

    User

    1:m Match

    Identification

    1:1 MatchVerification

    User ID

  • 7/28/2019 Ppt Fingerprint

    10/34

    10

    Algorithm Level Design

    Thinning

    Minutiae Marking

    Remove False Minutiae

    Minutia extraction

    Preprocessing

    Image Segmentation

    Image EnhancementImage Binarization

    Post-processing

    Minutia Extractor:

  • 7/28/2019 Ppt Fingerprint

    11/34

    11

    Algorithm Level Design

    Find Reference Minutia Pair

    Affined TransformReturn Match Score

    Minutia Matcher:

  • 7/28/2019 Ppt Fingerprint

    12/34

    12

    Minutia Extractor- Segmentation

    Block directional estimation

    Foreground : have a dominant directionBackground : No global direction

  • 7/28/2019 Ppt Fingerprint

    13/34

    13

    Fingerprint Image Segmentation

    Ridge Flow Orientation Estimate

    Edge detector: get gradient x (gx),gradient y (gy)

    Estimate the according to:tg2 = 2 sigma(gx*gy)/sigma(gx

    2-gy2)

    Region of Interest

    Morphological Method

    Close + Open

  • 7/28/2019 Ppt Fingerprint

    14/34

    14

    Fingerprint Image Segmentation

  • 7/28/2019 Ppt Fingerprint

    15/34

    15

    Fingerprint Image Segmentation

    Area Close Open

    ROI + Bound

  • 7/28/2019 Ppt Fingerprint

    16/34

    16

    Fingerprint Image Enhancement

    Histogram Equalization

  • 7/28/2019 Ppt Fingerprint

    17/34

    17

    Fingerprint Image Enhancement

    Fourier Transform

    i

  • 7/28/2019 Ppt Fingerprint

    18/34

    18

    Preprocessing - Enhancement

  • 7/28/2019 Ppt Fingerprint

    19/34

    19

    Fingerprint Image Binarization

  • 7/28/2019 Ppt Fingerprint

    20/34

    20

    Common Approaches:

    Local Adaptationgray value of each pixel g

    if g > Mean(block gray value) , set g = 1;

    Otherwise g = 0

    Directly ridge Retrieval from Gray Image

    get Ridge Maximums Implying binarization

    Fingerprint Image Binarization

  • 7/28/2019 Ppt Fingerprint

    21/34

    21

    Fingerprint Image Binarization

    Directly ridge Retrieval

    1.Estimate ridge direction D2.Advance by a step length3.Along the direction orthogonal to D

    Return to ridge Center4.go to 1

    1.Block ridge flow orientation O2.Get direction P orthogonal to O3.Project block image to the lines along P

  • 7/28/2019 Ppt Fingerprint

    22/34

    22

    Minutia extraction stage - Thinning

  • 7/28/2019 Ppt Fingerprint

    23/34

    23

    Minutia extraction stage - Thinning

    Morphological Approaches:

    bwmorph(binaryImage,''thin'',Inf)

    Parallel thinning algorithm:

    1) 2=< N(p1)

  • 7/28/2019 Ppt Fingerprint

    24/34

    24

    Preprocessing Steps:0 1 0

    0 1 01 0 1

    0 0 00 1 0

    0 0 1

    Bifurcation

    Termination

    Minutia extraction

  • 7/28/2019 Ppt Fingerprint

    25/34

    25

    Minutia extraction

  • 7/28/2019 Ppt Fingerprint

    26/34

    26

    Post-processing stage

    False Minutia Remove:

    Two disconnected terminations

    short distance

    Same/opposite direction flow

    Two terminations at a ridge

    are too close

  • 7/28/2019 Ppt Fingerprint

    27/34

    27

    Post-processing stage

    False Minutia Remove:

  • 7/28/2019 Ppt Fingerprint

    28/34

    28

    Minutia Match

    Minutia Representation:

    Mn ( Position, Direction , Associate Ridge)

    tg = (yp-y0)/(xp-x0);

    Xp = sigma(xi)/Lpath;Yp = sigma(yi)/Lpath;

    ridge

    Minutiax0 x1 x2 x3 x4 x5 x6 x

    y

    Lpath

    Generally, ridge endings and bifurcations are consolidated

  • 7/28/2019 Ppt Fingerprint

    29/34

    29

    Simple Relax Match Algorithm :

    Minutia Match

    1. For each pair of Minutia

    2. Construct the Transform Matrix

    TM =

    cos

    sin

    0

    sin

    cos

    0

    0

    0

    1

    x

    y

    xi_new

    yi_new

    i_new

    xi x( )

    yi y( )

    i

    =TM *

    (x,y, )

    (xi,yi, i)

  • 7/28/2019 Ppt Fingerprint

    30/34

    30

    Simple Relax Match Algorithm :

    Minutia Match

    For any two minutia from different image,If They are in a box with small length

    And their direction has large consistence

    They are Matched Minutia

    Match Score =

    Num(Matched Minutia)

    Max(Num Of Minutia (image1,image2));

  • 7/28/2019 Ppt Fingerprint

    31/34

    31

    Alignment based Algorithm :

    Minutia Match

    ridge

    Minutiax0 x1 x2 x3 x4 x5 x6 x

    y

    Ridge information is used to

    determine the goodness of areference Minutia pair

    Ridge_direction

    If two ridge are matched well

    Continue use the

    Relax Box Match Or

    Use

    String Match

  • 7/28/2019 Ppt Fingerprint

    32/34

    32

    Fingerprint Verification

    Performance Evaluation Index

    FRR: False Rejection Rate

    FRR = 2/total1

    FAR: False Acceptance Rate

    FAR = 3/total2

    Total1 = m*(n+1)*n/2

    Total2 = m*(m-1)/2

    SameFinger

    Program

    result (Yes/No)

    Different

    Finger

    1 Yes 2 No

    3 Yes 4 No

    F10 F11 F12 F13 F1n

    F20 F21 F22 F23 F2n

    F30 F31 F32 F33 F3n

    Fm0 Fm1 Fm2 Fm3 Fmn

  • 7/28/2019 Ppt Fingerprint

    33/34

    33

    APPLICATIONS

    FINGER PRINT WALLET

    MOBILE

  • 7/28/2019 Ppt Fingerprint

    34/34

    34

    DRAWBACKS