14872203 fingerprint project

Upload: tarungoel11

Post on 09-Apr-2018

217 views

Category:

Documents


0 download

TRANSCRIPT

  • 8/8/2019 14872203 Fingerprint Project

    1/12

    Finger Print Recognition Progress Report 1

    CHAPTER -I INTRODUCTION

    General Statement of the Problem

    In order to aid forensics in criminal identification, authenticationin civilianapplications and for preventing unauthorized there is a need todevelop a finger printrecognition and analysis system.

    Background

    Fingerprint verification is an important biometric technique forpersonal identification. Biometrics are automated methods of

    recognizing an individual based on their physiological (e.g.,fingerprints, face, retina, iris) or behavioral characteristics (e.g., gait,signature). Biometric-based solutions are able to provide forconfidential financial transactions and personal data privacy.

    Importance of problem

    Each biometric has its strengths and weaknesses and the choicetypically depends on the application. No single biometric is expected toeffectively meet the requirements of all the applications. The matchbetween a biometric and an application is determined depending upon

    the characteristics of the application and the properties of thebiometric.

    Information

    Fingerprints are graphical flow-like ridges present on humanfingers. They are fully formed at about seven months of fetusdevelopment and finger ridge configurations do not change throughoutthe life of an individual except due to accidents such as bruises andcuts on the fingertips. This property makes fingerprints a veryattractive biometric identifier. Fingerprint system can be separated intotwo categories Verification and identification.

    Identification system recognizes an individual by searching theentire template database for a match. It conducts one-to-manycomparisons to establish the identity of the individual. In anidentification system, the system establishes a subjects identity (orfailsif the subject is not enrolled in the system database) without thesubject having to claim an identity.

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    2/12

    Finger Print Recognition Progress Report 2

    DetailedDescription of Fingerprint System

    The various steps involved in a typical fingerprint recognitionsystem are shownBelow

    Figure 1: Various steps in a Fingerprint system

    A finger print system works in two modes they are Enrollmentmode and Authentication mode. Enrollment mode: fingerprint systemis used to identify and collect the related information about the person

    and his/her fingerprint image. Authentication mode: fingerprint systemis used to identify the person who is declared to be him/her.

    Figure 2: Enrollment and Authentication stages of a fingerprint system

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    3/12

    Finger Print Recognition Progress Report 3

    CHAPTER -II OBJECTIVES

    The overall objective of the project is to develop a finger printsystem based on directional filter bank technique which works onminutiae. A point in the fingerprint image is designated as a minutia ifit belongs to an ending, beginning or bifurcation of a ridge. The

    extraction of minutiae relies heavily on the quality of the input images.

    Simple smoothing and sharpening

    Contrast stretching

    Dry and wet area detection

    Steps In The Design Process

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    4/12

    Finger Print Recognition Progress Report 4

    .

    Figure 3: Image Preprocessing and Feature Extraction

    CHAPTER -III PHASES

    Image Preprocessing

    To eliminate extraction of erroneous minutiae &consequently mining the mismatch as much as possible, imagepreprocessing is a necessary step before any feature extraction ispreformed.

    Histogram Equalization

    Extraction and Modification of Ridge Direction

    Dynamic Threshold

    Ridgeline Thinning

    Histogram Equalization

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    5/12

    Finger Print Recognition Progress Report 5

    The method used for the unwanted part of the image is made lighter so as to

    emphasize the desired parts. Then the accumulation of histogram from 0 to I is given by

    Extraction and Modification of Ridge Direction

    The introduction of unnecessary false minutiae in the feature extraction process.

    To prevent this directional information of ridges is obtained & modified.

    Figure 4: Ridges Direction

    The effect of modifying the directional codes is shown in fig.

    Figure 5: Before Enhancement Figure 6: After Modification Directional

    Dynamic Threshold

    Mapping of all data points having gray level more than the average gray level in a

    16 x 16 sampling square 255 ( white ) and all other to zero (black). The result of it shownin fig.

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    6/12

    Finger Print Recognition Progress Report 6

    Figure 7: After Dynamic Threading

    Ridgeline Thinning

    Before the features can be extracted, the fingerprints have to be thinned or

    skeletons so that all the ridges are one pixel thick. Applying the thinning functions the

    following shows the result as under.

    Figure 8: Before Thinning Figure9: After Thinning

    The basic features extracted from a fingerprint image are ridgeending and ridge bifurcation. Mask used for features extraction is

    Figure 10: 3x 3 Windows for Feature Extraction

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    7/12

    Finger Print Recognition Progress Report 7

    Features Extraction

    The two basic features extracted from a fingerprint image areridge endings & bifurcations.

    Response of the result for ridge ending is

    Response of the result for ridge bifurcation is

    CHAPTER V DELIVERABLES

    MATLAB source code.

    Function to enhance the fingerprint and then applying basic globalthreshold image is differentiated from background

    function image = enhanced(img)img = double(img);img1 = histeq(img);T = graythresh(img1)% T = 200 ;% global C1 C2 G1 G2% C1 = 0 ;% C2 = 0 ;

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    8/12

    Finger Print Recognition Progress Report 8

    % G1 = 0 ;% G2 = 0 ;% img = thresholding(img1,T) ;% u1 = G1/C1 ;% u2 = G2/C2 ;

    % T = (u1+u2)/2 ;% C1 = 0 ;% C2 = 0 ;% G1 = 0 ;% G2 = 0 ;% img1 = thresholding(img,T) ;% u1 = G1/C1 ;% u2 = G2/C2 ;% T = (u1+u2)/2 ;% C1 = 0 ;

    % C2 = 0 ;% G1 = 0 ;% G2 = 0 ;image = thresholding(img1,T) ;image

    %%%%Helper Function Starts%%%%%%

    function imag2 = thresholding(img,T)[M,N] = size (img);

    for i=1:Mfor j=1:Nif ( img(i,j) > T )

    img(i,j) = 1 ;imag2 = img(i,j);

    % G1 = G1 + img(i,j) ;% C1 = C1 + 1 ;

    elseimg(i,j) = 0 ;imag2 = img(i,j);

    % G2 = G2 + img(i,j) ;% C2 = C2 + 1 ;

    end

    endendimag2

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    9/12

    Finger Print Recognition Progress Report 9

    %%%%%Helper Function Ends%%%%%%%%

    Function "Preprocessing" is used to preprocess the image for featuresextraction. The main objective of the function is to change the finger ridges into 1pixel thick line which is mandatory for the extraction of bifurcation & minutiae.

    %Syntax:%I = imread('fingerprint.tif');%%then pass the image matrix 'I' as an argument and the function will%return the 'image' in which ridges are 1 pixel thickl%%image = preprocessing(img);

    function image = preprocessing(img)img = histeq(img);

    %T = threshold valueT = graythresh(img) ;%bwimage is image got from thresholding using 'im2bw' functionbwimage = im2bw(img,T);bw1 = bwmorph(bwimage,'thin',inf);%bw1 is 1 pixel thick ridge line which was the main objective of thewhole%process. This is necessary for the extraction of the features from the%finger print images.comp = imcomplement(bw1);

    image = comp

    Function "Features" extracts the minutiae points, ridge endings &bifurcations , and write them to a file. This will use the function preprocessing asauxiliary function to preprocess the image for features extraction. Implementingthe following 3x3 window for features extraction.

    % X1 X2 X3% X8 M X4% X7 X6 X5%% M is the center pixel and it will decide whether the center pixel% is a ridge ending ( M = 2 ), or it is ridge bifurcation ( M = 6 )%% Syntax:% fingerprint = imread('fingerprint.tif');% Features_extract(fingerprint);

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    10/12

    Finger Print Recognition Progress Report

    10

    function Features_extract(image)

    image1 = preprocessing( image );image = imcomplement( image1 );

    [M,N] = size( image ) ;imview( image ) ;

    K = M -2 ;L = N -2 ;x = 1 ;y = 1 ;m = 1 ;n = 1 ;

    global C

    for i=2: Kfor j=2: L

    C = 0 ;

    C = abs( image(i,j+1) - image(i,j) ) ;C = C + abs( image(i,j+2) - image(i,j+1) ) ;C = C + abs( image(i+1,j+2) - image(i,j+2) ) ;C = C + abs( image(i+2,j+2) - image(i+1,j+2) ) ;

    C = C + abs( image(i+2,j+1) - image(i+2,j+2) ) ;C = C + abs( image(i+2,j) - image(i+2,j+1) ) ;C = C + abs( image(i+1,j) - image(i+2,j) ) ;C = C + abs( image(i,j) - image(i+1,j) ) ;

    if ( C == 2 )

    ending1(x) = i ;ending2(y)= j ;x = x + 1 ;y = y + 1 ;

    endif ( C == 6 )

    bif1(m) = i ;bif2(n) = j ;m = m + 1 ;n = n + 1 ;

    end

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    11/12

    Finger Print Recognition Progress Report

    11

    endendsave minut

    GANTT CHART

    Stages

    Figure 11: Gantt chart Time

    REFERENCES

    Journal Articles

    1) K. Jain, L. Hong, S. Pankanti, and R. Bolle, An identity authentication systemusing fingerprints,Proc. IEEE, vol. 85, pp. 1365-388, Sept. 1997

    2) K. Jain, L. Hong, and R. Bolle, On-line fingerprint verification,IEEE Trans.

    Pattern Anal. Machine Intell., vol. 19, pp. 302314, Apr. 1997

    3) Aho, A. V., Hopcroft, J.E., and Ullman J. D., 1983, Data Structures andAlgorithms, Addison-Wesley Publishing Company, Massachusetts, USA

    Books

    Created by Blue Lions

  • 8/8/2019 14872203 Fingerprint Project

    12/12

    Finger Print Recognition Progress Report

    12

    Rafeel C. Gonzalez, Richard E. Woods,Digital Image Processing, 2nd Edition,

    PrenticeHall, New York, 2002

    Rafeel C. Gonzalez, Richard E. Woods,Digital Image Processing using MATLAB,

    2nd Edition, PrenticeHall, New York, 2002

    Web Pages

    1) http://www.atvs.diac.upm.es/publicaciones/publicaciones_en.htm2) http://fpserver.cse.cuhk.edu.hk/paper/fingertechpart2.pdf3) http://www.research.ibm.com/ecvg/pubs/sharat-minver.pdf4) http://www.cordis.lu/infosec/src/stud5fr.htm

    Created by Blue Lions

    http://www.atvs.diac.upm.es/publicaciones/publicaciones_en.htmhttp://fpserver.cse.cuhk.edu.hk/paper/fingertechpart2.pdfhttp://www.research.ibm.com/ecvg/pubs/sharat-minver.pdfhttp://www.cordis.lu/infosec/src/stud5fr.htmhttp://www.atvs.diac.upm.es/publicaciones/publicaciones_en.htmhttp://fpserver.cse.cuhk.edu.hk/paper/fingertechpart2.pdfhttp://www.research.ibm.com/ecvg/pubs/sharat-minver.pdfhttp://www.cordis.lu/infosec/src/stud5fr.htm