Minor Project report

Submitted by

Vikash Kumar
Sudipta Sarkar
Ram Pratap Sharma
Pushkar Kumar

Under The Guidance of

Dr. H.A.Ansari & Md. Azizar
Rahaman.

Stream: Computer Science and Engineering.

Future Institute Of Engineering And
Management.
Sonarpur,Kolkata-700150.

Content Page Number

Chapter 1:Introduction………………………….3

1
1.1 What is A Fingerprint
1.2 What is Fingerprint Recognition

Chapter 2:Objective…………………………......5

Chapter 3:Description…………………………..6
3.1Histogram equalization
3.2Fourier transformation
3.3Thining technique
3.4Region of Interest

Chapter 4:Coding………………………………10

Chapter 5:Hardware
And Software Requirements……….13

Chapter 6:Solution Of Problem………………14

Chapter 7:Program Flow……………………..15

Chapter 8:Applications Of The Project………16

Chapter 9:Conclusion And Future Scope……17

Chapter 10:Bibliography……………………..18

Chapter 1: Introduction
1.1 What is A Fingerprint ?
A fingerprint is the feature pattern of one finger. It is believed with strong
evidences that each fingerprint is unique. Each person has his own
fingerprints with the permanent uniqueness. So fingerprints have being used

2
for identification and forensic investigation for a long time. Fingerprint
recognition is one of the most reliable identification techniques.
Fingerprint technology is the most widely used for security purposes. The
Technology is being frequently used in criminal investigation purpose.

1.1 A fingerprint image acquired by an Optical Sensor.

Fingerprint Image can be classified into following six category.

1.2 (a)Arch (b)tented arch (c)right loop

(d)Left loop (e)Whorl (f)twin loop

There are many characteristics in a fingerprint .

3
 Fig1.3

Among all these characteristics we take two characteristics for our Project.One
is bifurcation and another one is ridge ending.

1.2 What is Fingerprint Recognition?

The fingerprint recognition problem can be grouped into two
sub-domains: one is fingerprint verification and the other is fingerprint
identification. Fingerprint verification is to verify the authenticity of one
person by his fingerprint. The user provides his fingerprint together with his
identity information like his ID number. The fingerprint verification system
retrieves the fingerprint template according to the ID number and matches
the template with the real-time acquired fingerprint from the user. Usually it
is the underlying design principle of AFAS (Automatic Fingerprint
Authentication System).Fingerprint identification is to specify one person’s
identity by his fingerprint(s). Without knowledge of the person’s identity, the
fingerprint identification system tries to match his fingerprint(s) with those in
the whole fingerprint database. It is especially useful for criminal investigation
cases. And it is the design principle of AFIS (Automatic Fingerprint
Identification System). However, all fingerprint recognition problems, either
verification or identification, are ultimately based on a well-defined
representation of a fingerprint. As long as the representation of fingerprints
remains the uniqueness and keeps simple, the fingerprint matching, either for
the 1-to-1 verification case or 1-to-m identification case, is straightforward and
easy.

Chapter 2: Objective

4
The principle objective of our project is to recognize an image.
Here we take an image as input and then we apply Histogram equalization
and Fourier transforms which is Enhancement technique .Then we thin that
image. After that we match that input image with the stored image and find
how much it is matched with the stored image.

Strategy of the project is divided into following steps.

1. Loading the Fingerprint Image.

2. Increase the perceptional information of the image by

• Histogram Equalization Method.

• Fast Fourier Transform.

3. Region of Interest.
4. Direction Estimation of each contour of block of Fingerprint.
5. Thinning Technique.
6. Verification.

In present course we attempt some of the steps of our strategy.

Chapter 3: Description

5
 Our fingerprint recognition system is ultimately based on a well-
defined representation of a fingerprint recognition Technique.Taking a
Fingerprint at first we enhanced the quality of that image to make the image
clearer for easy further operations. Since the fingerprint images acquired from
sensors or other medias are not assured with perfect quality, those
enhancement methods, for increasing the contrast between ridges and
furrows and for connecting the false broken points of ridges due to insufficient
amount of ink, are very useful for keep a higher accuracy to fingerprint
recognition. various methods that are adopted in our fingerprint recognition
system to enhance the image quality are Fingerprint Enhancement by
Histogram Equalization and Fingerprint Enhancement by Fourier
Transform.

3.1 Loading the Fingerprint Image

3.2 Increase the perceptional information of the

image by

• Histogram Equalization.
• Fast Fourier Transform.

(i)Histogram Equalization :

Histogram equalization is to expand the pixel value distribution of an

image so as to increase the perceptional information. The original histogram
of a fingerprint image has the bimodal type [Figure 3.1.], the histogram after
the histogram equalization occupies all the range from 0 to 255 and the
visualization effect is enhanced [Figure 3. 2].

6
Figure 3. 1 The Original histogram of a Figure 3. 2 Histogram after the
fingerprint image. Histogram Equalization.

The right side of the following figure [Figure 3.1] is the output after the histogram
equalization.

Figure 3.3 Histogram Enhancement. Original Image (Left)

Enhanced image (Right)

(ii)Fourier Transformation :

In Fingerprint Enhancement by Fourier Transform, We divide the

image into small processing blocks (32 by 32 pixels) and perform the Fourier
transform according to:

7
 (1)

for u = 0, 1, 2, ..., 31 and v = 0, 1, 2, ..., 31.

In order to enhance a specific block by its dominant frequencies, we multiply

the FFT of the block by its magnitude a set of times. Where the magnitude of
the original FFT = abs(F(u,v)) = |F(u,v)|.

Get the enhanced block according to

(2) ,

where F-1(F(u,v)) is done by:

for x = 0, 1, 2, ..., 31 and y = 0, 1, 2, ..., 31.The k in formula (2) is an

experimentally determined constant, which we choose k=0.45 to calculate.
While having a higher "k" improves the appearance of the ridges, filling up
small holes in ridges, having too high a "k" can result in false joining of ridges.
Thus a termination might become a bifurcation. Figure 3.4 presents the image
after FFT enhancement.

Figure 3.4 Fingerprint enhancement by FFT

Enhanced image (left), Original image (right)

The enhanced image after FFT has the improvements to connect some falsely
broken points on ridges and to remove some spurious connections between
ridges.

3.3 Region of Interest :

8
In general, only a Region of Interest (ROI) is useful to be recognized for each
fingerprint image. The image area without effective ridges and furrows is first
discarded since it only holds background information. Then the bound of the
remaining effective area is sketched out since the minutia in the bound region
are confusing with those spurious minutia that are generated when the ridges
are out of the sensor.

3.4 Thinning Technique :

Thinning is a Technique to eliminate the redundant pixels of ridges till the

ridges are just one pixel wide. It uses an iterative, parallel thinning algorithm.
In each scan of the full fingerprint image, the algorithm marks down
redundant pixels in each small image window. And finally removes all those
marked pixels after several scans. Here we count that, from the edge, after
how many black pixels there is one or more white pixel .Then we store the first
and last pixel positions. Then we make the color of all those black pixels white
except a particular pixel which is situated at the location ((first pixel position
+ last pixel position)/2).

The result of a good thinning algorithm are ---

a) The thinned image obtained should be of single pixel width with no
discontinuities.
b) Each ridge should be thinned to its centre pixel.
c) Noise and singular pixels should be eliminated.
d) No further removal of pixels should be possible after completion of thining
process.

CHAPTER 4 : CODING

clear

9
figwin = figure('Position',[300,400,600,500],...
'Name','vikash testing figure',...
'NumberTitle','off',...
'Color',[0.7,0.7,0.7]);

AxesHandle1 = axes('position',[0.2,0.2,0.35,0.58]);
AxesHandle2 = axes('position',[0.6,0.2,0.35,0.58]);

% Loading the Fingerprint Image

textLoad='fingerprint image';
uicontrol(figwin,'position',[0,350,70,40],...
'string','LOAD IMAGE',...
'Callback',...
['image1=vloadimage;'...
'subplot(AxesHandle1);'...
'imagesc(image1);'...
'title(textLoad);'...
'colormap(gray);'
]);

%IMAGE ENHANCEMENT

%Enhancement by histogram Equalization

text_eq='Enhancement by histogram Equalization';

uicontrol(figwin,'position',[0,300,70,40],...
'string','HIST EQ.',...
'Callback',...
['subplot(AxesHandle2);'...
'image1=histeq(uint8(image1));'...
'imagesc(image1); title(text_eq);']);

% Enhancement by fast fourier transform

text='Please input the FFT factor(0~1)';

text_fft='Enhancement by FFT';

uicontrol(figwin,'position',[0,250,70,40],...
'string','FFT',...
'Callback',...
['W=inputdlg(text);'...
'W=str2double(char(W));'...
'subplot(AxesHandle1);image1=vfftenhance(image1,W);'...
'imagesc(image1);title(text_fft);']);

% Region Of Interest(ROI)

text_ROI='Region Of Interest(ROI)';

10
uicontrol(figwin,'position',[0,200,70,40],...
'string','ROI',...

%Thinning

text31='Thinned-ridge map';
uicontrol(figwin,'position',[0,150,70,40],...
'string','THINNING',...

%Saving the features

uicontrol(figwin,'position',[0,100,70,40],...
'string','SAVE');

%Verification

uicontrol(figwin,'position',[260,25,150,40],...
'string','VERIFY');

For Loading Image

function image1=loadimage
% dialog for opening fingerprint files

[imagefile1 , pathname]= uigetfile('*.bmp;*.BMP;*.tif;*.TIF;*.jpg','Open An

Fingerprint image');

if imagefile1 ~= 0
cd(pathname);

image1=imread(char(imagefile1));
image1=255-double(image1);

end;

For Fast Fourier Transform

function [final]=fftenhance(image,f)

I = 255-double(image);

[w,h] = size(I);
%out = I;

w1=floor(w/32)*32;
h1=floor(h/32)*32;

11
inner = zeros(w1,h1);

for i=1:32:w1
for j=1:32:h1
a=i+31;
b=j+31;
F=fft2( I(i:a,j:b) );
factor=abs(F).^f;
block = abs(ifft2(F.*factor));

larv=max(block(:));
if larv==0
larv=1;
end;

block= block./larv;
inner(i:a,j:b) = block;
end;
end;

final=inner*255;

final=histeq(uint8(final));

Chapter 5: Hardware And Software

Requirements
Various Software And Hardware that are required to do this project is
discussed here.

12
1. Software :

a. MATLAB version 7

2. Hardware:

a. Ram: 256 Mb.

b. Hard Disk: 40 Gb.
c. Input device: Keyboard.
d. Output device: Computer Monitor.

Chapter 6: Solution of Problem

1. In the thinning technique we count the pixel width

horizontally .And then we convert that image into another
image whose pixel width is uniformly one. If any

13
 characteristic is present horizontally, then after the use of
thinning algorithm it becomes a point.

2. The value of the constant in Fast Fourier Transform should

be close to one.

Chapter 7: Program Flow

The Program follows this particular path - - -

14
Select an Image Histogram Equalization Fourier Transform

Region Of Interest Thinning Verification

100
80
60
East
40 West
20 North
0
1st 2nd 3rd 4th
Qtr Qtr Qtr Qtr

Chapter 8: Applications Of The

Project

Fingerprint recognition is a rapidly evolving Technology that has

been widely used in forensics such as criminal recognition and
prison security and has a very strong potential to be widely
adapted in a broad range of civilian applications.
Most of the Fingerprint Recognition applications are divided
into following three categories.

15
 1. Forensic:

a. Corpse Identification.
b. Criminal Investigation.
c. Terrorist Identification.
d. Parenthood Determination.
e. Missing Children.etc

2. Government:

a. National ID Card.
b. Corretional Facility.
c. Driver’s license.
d. Social Security.
e. Welfare Disbursement.
f. Border Control.
g. Passport Control.etc

3. Commercial:
a. Computer Network Logon.
b. Electronic Data Security.
c. E-Commerce.
d. Internet Access.
e. ATM,Credit card.
f. Physical access control.
g. Cellular Phones.
h. Personal Digital Assistance.
i. Mdical Records Management.
j. Distance Learning .etc.

Chapter 9: Conclusion And Future

Scope

Fingerprint Image enhancement is to make the image clearer for

easy further operations. Since the fingerprint images acquired
from sensors or other media are not assured with perfect quality,
enhancement methods, for increasing the contrast between ridges

16
and furrows and for connecting the false broken points of ridges
due to insufficient amount of ink, are very useful to keep a higher
accuracy to fingerprint recognition. Two methods are adopted in
the work: the first one is Histogram Equalization; the second one is
Fourier Transform.

1. Region Of Interest tells us which region of the fingerprint is

very useful for various features matching.
2. Improved thinning in the present work contributes to: The
image becomes perfectly thinned to single pixel width. More
number of bifurcations can be detected.
3. Also a program coding with MATLAB going through all the
stages of the fingerprint recognition is built. It is helpful to
understand the procedures of fingerprint recognition. And
demonstrate the key issues of fingerprint recognition.

Overall, a set of reliable techniques have implemented for

fingerprint recognition. These techniques can then be used to
facilitate the further study of the statistics of fingerprints. The
future scope of the work is to do Binarization of the image, to find
the direction of the bifurcation and ridges of the image,to extract
features, to find actual minutiae .So that the fingerprint
recognition could be made better which can improve the future
stages and the final outcome.

Chapter 10: Bibliography

[1] T. Chang. Texture analysis of digitized _ngerprints for

singularity detection. In Proc.

17
5th ICPR, pages 478{480, 1980.
[2] P. E. Danielsson and Q. Z. Ye. Rotation-invariant operators
applied to enhancement of
_ngerprints. In Proc. 9th ICPR, pages 329{333, Rome, 1988.
[3] J. G. Daugman. Uncertainty relation for resolution in space,
spatial-frequency, and ori-
entation optimized by two-dimensional visual cortical _lters. J.
Opt. Soc. Am., 2:1160{
1169, 1985.
[4] L. Hong, A. K. Jain, S. Pankanti, and R. Bolle. Fingerprint
enhancement. In Proc. 1st
IEEE WACV, pages 202{207, Sarasota, FL, 1996.
[5] D. C. Huang. Enhancement and feature puri_cation of
_ngerprint images. Pattern
Recognition, 26(11):1661{1671, 1993.
[6] A. Jain, L. Hong, and R. Bolle. On-line _ngerprint veri_cation.
IEEE Trans. Pattern
Anal. and Machine Intell., 19(4):302{314, 1997.
[7] A. K. Jain and F. Farrokhnia. Unsupervised texture
segmentation using Gabor _lters.
Pattern Recognition, 24(12):1167{1186, 1991.

18