IMAGE PROCESSING APPLICATIONS FOR BIOMETRIC

RECOGNITION AND SECURITY ISSUES

SESSION 2017-2018

A Major Project Report (Phase I) Submitted To

Rajiv Gandhi Prodhyogiki Vishvavidhyalaya, Bhopal-M.P.

In The Fulfillment Of The Degree Of

Bachelor Of Engineering (Electrical)

DEPARTMENT OF ELECTRICAL ENGINEERING

Supervisor: Submitted By

Prof. M.P.S. CHAWLA Bhavya Verma

Associate Professor EED Neha Bisen

SGSITS INDORE Piyusha Agrawal

Prakhar Saxena

Pratiksha Khatarkar

Mr. Abhishek Dubey

Asst. Professor EED

SGSITS INDORE

Department of Electrical Engineering

Shri Govindram Seksaria Institute of Technology & Science

Indore – M.P.
 Department of Electrical Engineering

Shri Govindram Seksaria Institute of Technology & Science

Indore – M.P.

November 2017

STATEMENT OF ORIGINALITY

In accordance with the requirement for the degree of bachelor of engineering in department of
electrical engineering. We present this project report of phase I entitled “Image Processing
Applications For Biometric Recognition And Security Issues”. This report/project (phase I)
was completed under the supervision of Prof. M.P.S. CHAWLA, Associate Prof. EED, SGSITS INDORE
(M.P.).

We declare that the work presented in the report is our own original work and all references
taken are duly acknowledged in the text and to the best of our knowledge. This material has
not been submitted either a whole or in part for a degree either at this institute or at any other
institution or elsewhere.
Name of the student Signature

Bhavya Verma

Neha Bisen

Piyusha Agrawal

Prakhar Saxena

Prartiksha Khatarkar

Date:
 Department of Electrical Engineering

Shri Govindram Seksaria Institute of Technology & Science

Indore – M.P.

SESSION 2017-2018
RECOMMENDATION
The Major Project Phase I Entitled “Image Processing Applications For
Biometric Recognition And Security Issues” Submitted By “Bhavya Verma,
Neha Bisen, Piyusha Agrawal, Prakhar Saxena, Pratiksha Khatarkar”, Towards
The Fulfillment Of Bachelors Of Engineering(Electrical) Of Rajiv Gandhi
Prodhyogiki Vishvavidhyalaya, Bhopal –M.P. Is Satisfactory Account Of The
Progress Made By Them In The Dissertation Work

Supervisor: Prof. & Head

Prof. M.P.S. CHAWLA DEPT. OF ELECTRICAL ENGG.

Asso. Prof. EED SGSITS INDORE

SGSITS INDORE
 Department of Electrical Engineering

Shri Govindram Seksaria Institute of Technology & Science

Indore – M.P

CERTIFICATE

This is to certify that “, Bhavya Verma, Neha Bisen, Piyusha Agrawal, Prakhar
Saxena Pratiksha Khatarkar” students of final year B.E.(electrical engineering
department ) in the year 2017of this institute have completed the project work
entitled “Image Processing Applications For Biometric Recognition And
Security Issues” based on syllabus and have submitted a satisfactory account of
their work in this project.

INTERNAL EXAMINER EXTERNAL EXAMINER

SIGNATURE SIGNATURE
 ACKNOWLEDGEMENT

First and foremost, we would like to express our sincere gratitude to our project
guide, of PROF. M.P.S. CHAWLA, ASSO. PROF. EED, SGSITS INDORE (MP). We all
are privileged to experience a sustained enthusiastic and involved interest from
his side. This fuelled our enthusiasm even further and encouraged us to boldly
step into what was a totally dark and unexplored expanse before us.
It gives the pleasure to offer thank to all the teachers & laboratory
assistants & peons for their kind help and suggestion. We like to thank our friend
and colleagues for their help and co-operation without which this project would
have not been possible.

Bhavya Verma
Neha Bisen
Piyusha Agrawal
Prakhar Saxena
Pratiksha khatarkar
 Overview of the Project

“Image Processing Applications For Biometric Recognition And

Security Issues” as the name suggests is a project based on the use of
the knowledge of image processing for fingerprint recognition and it's
importance in the field of security. This report mainly aims at
understanding the basic concepts of fingerprint, biometrics, image
processing and it's toolbox in MATLAB. Then we will come to know
about how to identify different type of fingerprints and their images.
Also we will learn about databases regarding fingerprints and where
they are being used.
From the security viewpoint the image processing is very important
technology and it helps one to gain the feeling of protectiveness among
oneself.
 CONTENTS

CHAPTERS -1 INTRODUCTION OF IMAGE PROCESSING 01

1.1 Overview of image processing 01

1.2 Conventional method used for security 2

1.3 Alternative approach to security 3

1.4 Conclusion 3

CHAPTERS -2 IMAGE PROCESSING 04

2.1 what is image processing 4

2.2 Different type of tasks involve 5

2.3 Purpose of image processing 6

2.4 Types 7

2.5 Application 8

2.6 Image processing toolbox 8

2.7 Basic IPT function 8

2.7.1 Reading image 8

2.7.2 Whos function 9

2.7.3 Displaying image 9

2.7.4 Writing image 9

2.8 Data classes 10

2.9 Image types 12

2.10 Converting between data classes and types 13

2.11 Improving image contrast using histogram equalization 14

2.12 Conclusion 14

CHAPTERS -3 BIOMETRICS 17
3.1 What are biometrics 17

3.2 Type of biometrics 17

 3.3 History of biometrics 17

3.4 Functioning factor of biometrics 18

3.5 Performance 20

3.6 Recent advance in emerging biometrics 21

3.7 What is finger print 22

3.8 Fingerprint representation 22

3.9 Minutiae 23

3.10 Pattern area 26

3.11 Conclusion 27

CHAPTER-4 PROBLEM FORMULATION 29

CHAPTER-5 CONCLUSION 30

CHAPTER-6 SCOPE FOR FUTURE WORK 31

REFERENCES 32
 CHAPTER 1
INTRODUCTION

1.1 OVERVIEW:
Image processing is the application of signal processing techniques to the
domain of images-two-dimensional signals such as photographs or video.
Image processing does typically involve filtering or enhancing an image
using various types of functions in addition to other techniques to extract
information from the images [4]. Thus Image processing and computer
vision are basically concerned with developing algorithms for analyzing the
contents of an image for various purposes like automated identification or
verification of human identity.
Thus our primary focus in this report will be on understanding the various
jargons involved in image processing and comprehend the basics of the
biometric systems which could be used for security purposes. Together the
combination of the two will lead to developing an algorithm which can serve
the greater purpose of image processing application to biometric
recognition and security concept.
Security is a trade off, a balancing act between attacker and defender.
Unfortunately, that balance is never static. Changes in technology affect
both sides. Society uses new technologies to decrease what is called the
scope of defection- what attackers can get away with-and attackers use
new technologies to increase it. What’s interesting is the difference
between how the two groups incorporate new technologies.
In the ever changing world of global data communications, inexpensive
Internet connections, and fast-paced software development, security is
becoming more and more of an issue. Security is now a basic requirement
because global computing is inherently insecure. As our data goes from
point A to point B on the Internet, for example, it may pass through several
other points along the way, giving other users the opportunity to intercept,
and even alter it. With the growing technology security systems are getting
evolved to face the growing threats. These security systems are designed
very carefully to provide the user with a safe and a reliable environment.
Biometrics is one such method which has proven to be very effective and
reliable.

Page|1
1.2 CONVENTIONAL METHODS USED FOR SECURITY PURPOSE

1. Personal Identification Number (PIN): This method is probably the

most commonly used for authentication on devices. The common
variant consists of a 4-digit pass-code to be entered via a keypad.

2. Passwords: Passwords are very well known for a lot of logon

processes, being it a personal computer or a web service. Passwords
need a character-based input device, a secret word or expression
used by authorized persons to prove their right to access,
information, etc.

3. Recognition-based passwords: These “passwords” are not based on

character or digit input and are more common these days. They
involve to draw a pattern, to select parts of a picture in a certain
sequence, or to substitute PIN-numbers with pictures.

In most cases, the security mechanism provided are easy to crack, the use
of PIN codes and passwords suffers from numerous usability and security
problems. The drawbacks of passwords are mostly due to authorized users
selecting simple or guessable combinations (e.g. their birth date), sharing
the password, using the same password for multiple purposes and
accounts or even writing it down. Furthermore, users tend to activate their
device and keep it active for long periods of time (more than 10 hours a
day). Thus in many cases devices are left unprotected and unsecured for
long periods of time. The small size and the high cost of the devices make
them susceptible to loss or theft. The large amount of mostly unprotected
data stored on the device puts the user at risk. This risk is amplified by lack
of awareness and the appropriate security mechanisms to mitigate it.

1.3 ALTERNATIVE APPROACH TO SECURITY

Among the growing security schemes, biometric based authentication
systems are proving to be very effective and reliable. Each and every
person in this world possess a unique biometric identity and these
characteristics are used in developing these systems.
Biometric security devices play a crucial role in verifying a person's identity
by enforcing access control methods through their unique biological traits.
These include optical, fingerprint, and voice recognition, which are used to
identify and authenticate a person.
Page|2
1. Retina scanners use the blood vessels in the back of the eye for
authentication. The blood vessel pattern in the back of the eye is unique
to the individual.
2. Iris scanner, which measures an individual's iris pattern, is non-intrusive.
Each person has a different colour pattern in the iris, and therefore, the
iris scanner is used to measure these characteristics.
3. Fingerprint scanners measure the whorl, loop, and arch patterns of the
finger, which are unique to everyone. Fingerprint scanners are also the
easiest to implement and are cost effective. Voice recognition measures
the tone and pitch in a person’s voice.
Biometric identities bases authentication systems are promising and
budding alternatives for password based authentication systems. Among all
the biometric identities, fingerprint is one of the most popular and renowned
technique.

1.4 Conclusion
It is very important for banking, companies to provide high security system
to their valuable .In this chapter by using image processing and verification
more security will be provided than any other system .the image processing
technique uses colour processing which use the primary image
filtering to eliminate the unaltered colour or object in the image. It is more
secured system which is cost effective. It compares the whether the image
is same and at the same place as that of initially recorded. to increase the
security of system ,it is recommended for future work to add recognition,
which will increase the system authentication and reliability that mean
increasing the efficiency of security work.

Page|3
 CHAPTER 2
IMAGE PROCESSING

2.1 WHAT IS IMAGE PROCESSING?

Image processing is a method to convert an image into digital form and
perform some operations on it, in order to get an enhanced image or to
extract some useful information from it [1,6]. It is a type of signal
dispensation in which input is image, like video frame or photograph and
output may be image or characteristics associated with that image. Usually
Image Processing system includes treating images as two dimensional
signals while applying already set signal processing methods to them.
It is among rapidly growing technologies today, with its applications in
various aspects of a business. Image Processing forms core research area
within engineering and computer science disciplines too.

Image processing basically includes the following three steps:

1.) Importing the image with optical scanner or by digital photography.

2.) Analyzing and manipulating the image which includes data compression
and image enhancement and spotting patterns that are not to human eyes
like satellite photographs.
3.) Output is the last stage in which result can be altered image or report
that is based on image analysis.

Figure 2.1: Fundamental Steps in Digital Image Processing

Page|4
2.2 Different Types of Tasks involved

1. Image acquisition, storage, transmission: digitization/quantization,

compression, encoding/decoding .

2. Image Enhancement and Restoration: for improvement of pictorial

information for human interpretation, both input and output are in the
image form (e.g., the first few application examples above).

3. Image Understanding and Image Recognition: information extraction

from images for further computer analysis (e.g., the rest of the
application examples above). Input is in image form, but output is
some none image representation of the image content, such as
description, interpretation, classification, etc.

4. Pre-processing stage of computer vision of an artificial intelligent

system (robots, autonomous vehicles, etc.).

Figure 2.2: Different Tasks Involved In Image Processing

Page|5
2.3 Purpose of Image processing

The purpose of image processing is divided into 5 groups [4]. They are:
1. Visualization - Observe the objects that are not visible.
2. Image sharpening and restoration - To create a better image.
3. Image retrieval - Seek for the image of interest.
4. Measurement of pattern – Measures various objects in an image.
5. Image Recognition – Distinguish the objects in an image.

2.4 Types

The two types of methods used for Image Processing are Analog and
Digital Image Processing. Analog or visual techniques of image processing
can be used for the hard copies like printouts and photographs. Image
analysts use various fundamentals of interpretation while using these visual
techniques. The image processing is not just confined to area that has to
be studied but on knowledge of analyst. Association is another important
tool in image processing through visual techniques. So analysts apply a
combination of personal knowledge and collateral data to image
processing.

Digital Processing techniques help in manipulation of the digital images by

using computers. As raw data from imaging sensors from satellite platform
contains deficiencies. To get over such flaws and to get originality of
information, it has to undergo various phases of processing. The three
general phases that all types of data have to undergo while using digital
technique are Pre- processing, enhancement and display, information
extraction.

2.5 Applications of Image Processing

Visual information is the most important type of information perceived,

processed and interpreted by the human brain. One third of the cortical
area of the human brain is dedicated to visual information processing.
Digital image processing, as a computer-based technology, carries out
automatic processing, manipulation and interpretation of such visual
information, and it plays an increasingly important role in many aspects of
our daily life, as well as in a wide variety of disciplines and fields in science
and technology, with applications such as television, photography, robotics,
remote sensing, medical diagnosis and industrial inspection.
1. Computerized photography(e.g., Photoshop)

Page|6
2. Space image processing (e.g., Hubble space telescope images,
interplanetary probe images)
3. Medical/Biological image processing (e.g., interpretation of X-ray
images, blood/cellular microscope images).
4. Automatic character recognition (zip code, license plate recognition)
5. Finger print/face/iris recognition
6. Remote sensing: aerial and satellite image interpretations
7. Reconnaissance
8. Industrial applications (e.g., product inspection/sorting)

Figure 2.3: Flowchart Representing The Various Steps In Image Processing

Page|7
2.6 IMAGE PROCESSING TOOLBOX

Image Processing Toolbox is a set of functions and algorithms for image

processing operation, analysis and visualization [1,5]. Image Processing
Toolbox supports a diverse set of image processing operation such as:
Image analysis and enhancement, linear filtering and filter design,
neighbourhood and block operation, spatial image transformation etc. In
this chapter, basic IPT functions are introduced along with some examples
and their results to have a better understanding of the topic.
As earlier mentioned that a digital image f(x,y) in MATLAB can be
represented as a MxN matrix where x ranges from 0 to M-1 and y ranges
from 0 to N-1 as origin is taken as (0,0). But, here, the IPT uses a slightly
different coordinate convention to represent the array. First, instead of
using (x,y), the toolbox use (r,c) to represent rows and columns. Secondly,
the origin of coordinates system is at (r,c) = (1,1). Thus r ranges from 1 to
M and c ranges from 1 to N.

2.7 BASIC IPT FUNCTIONS:

2.7.1 READING IMAGES

Images are read into the MATLAB environment using function imread,
whose syntax is:
>> imread(‘filename’)
Here, filename is a string containing the complete name of the image file
including any applicable extension. To read an image whose location is
outside the current directory, we have to mention the complete URL of that
image.
For Example- If our image is located at the desktop(say) then, we can write
the following syntax to read that image file:

>> f= imread('C:\Users\Bhavya\Desktop\index.jpeg');

Page|8
2.7.2 whos function
The whos function displays the additional information about an array.
Example-
>> whos f
RESULT-
Name Size Bytes Class Attributes

f 194x259x3 150738 uint8

2.7.3 Displaying Images

Images are displayed at MATLAB desktop using the function imshow which
has the basic syntax-
>>imshow(f)
RESULT-

Figure 2.4: Displaying Image Result

2.7.4 Writing Images

Images are written to disk using the function imwrite which has the
following basic syntax
imwrite(‘filename’)
Page|9
With this syntax, the string contained in filename must include recognized
file format extension. Alternatively, we can assign another file format
extension explicitly according to our need.
EXAMPLE-
>> imwrite(f, 'C:\Users\Bhavya\Desktop\test2.jpg’)
A more general syntax that can be used only for JPEG/JPG format images-
>>imwrite(f, 'C:\Users\Bhavya\Desktop\test2.jpg’,’quality’,q)
Where q is an integer between 0 to 100 (the lower the number higher will
be the degradation to the image compression). The size of the image file
reduce depending on the value of q.

2.8 DATA CLASSES

Although we work with integer coordinates, the values of the pixels

themselves are not restricted to be integers in MATLAB [1]. The various
data types that are supported by MATLAB are listed in the table 3.1 in the
next page.

Page|10
 DATA CLASSES
NAME DESCRIPTION

Double-precision, float-point numbers in the approximate range -10^308 to

Double 10^308(8 bytes per element)

unit8 Unsigned 8-bit integers in the range[0,255](1 byte per element)

unit16 Unsigned 16-bit intergers in the range[0,65535](2 bytes per element)

unit32 Unsigned 32-bit integer in the range[0,429467295](4 bytes per element)

int8 Signed 8-bit intergers in the range[-128,127](1 byte per element)

int16 Signed 16-bit integers in the range[-32768,32767](2 bytes per element)

int32 Signed 32-bit integers in the range[-2147483648,2147483467](4 bytes per element)

Single-precision floating point numbers with values in the approximate range-10^38

Single to 10^38(4 bytes per element)
Char Characters(2 bytes per element)
Logical Values are 0 or 1 (1 byte per element)

Table 2.1: Data

Classes: The first eight entries are referred to as numeric classes; the ninth entry
is the character class and the last entry is of class logical

Page|11
2.9 IMAGE TYPES

IMAGE TYPE INTERPRETATION

Binary Logicalarray containing only 0s and 1s,

(Also known as a bilevel image) interpreted as black and white, respectively.

Indexed Array of class logical, uint8, uint16,

(Also known as a pseudocolor image) single, or double whose pixel values are
direct indices into a colormap. The colormap
is an m-by-3 array of class double. For
single or double arrays, integer values
range from [1, p]. For logical, uint8, or
uint16 arrays, values range from [0, p-1].

Grayscale Array of class uint8, uint16, int16,

(Also known as an intensity, gray scale, or gray single, or double whose pixel values
level image) specify intensity values.

For single or double arrays, values range

from [0, 1]. For uint8, values range from
[0,255]. For uint16, values range from [0,
65535]. For int16, values range from [-
32768, 32767]

Truecolor m-by-n-by-3 array of class uint8, uint16, single,

(Also known as an RGB image ) or double whose pixel values specify intensity
values.
For single or double arrays, values range from [0,
1]. For uint8, values range from [0, 255]. For
uint16, values range from [0, 65535]

Table 2.2: Image Types

 An image is characterized by both its class and types. For instance, a

statement discussing an “uint8 intensity image” is simply referring to
an intensity image whose pixels are of data class uint8.
 The important point to be noted is that pixels in binary image can only
be of data class logical.

Page|12
2.10 CONVERTING BETWEEN DATA CLASSES AND TYPES

This operation are frequent in IPT application. When converting between

data classes, it is important to keep in mind the value ranges for each data
class. Converting between data classes has following general syntax:
B= data_class_name(A)
Where data_class_name is one of the names from the following-
double,uint8, uint16, int8 , int16, int32, single, char, logical [1,5].
As stated earlier that ranges of the data types have to be kept in mind while
performing the data type conversion because after conversion pixel value
changes according to the range of the data type in which it is being
converted. This can be understood by studying the following case:
Suppose that A is an array of class double and some of its value lie outside
the range [0, 255]. Now, if we convert the data type into uint8 class, then,
MATLAB converts pixel’s value to 0 for all values less than zero, and
converts it to 255 for all values greater than 255.
FOR EXAMPLE
f=
-0.5 0.5
0.75 1.5

g = im2uint8(f)
After performing conversion, we get a matrix g
g=
0 128
191 255

The summarized table for conversion is given in the next page-

Page|13
 Name Converts Input to Valid Input Image Data Classes
im2uint8 uint8 logical,uint8,uint16 and double
im2uint16 uint16 logical,uint8,uint16 and double
mat2gray double(in range[0,1]) Double
im2double double logical,uint8,uint16 and double
im2bw Logical uint8,uint16 and double
Table 2.3: Conversion Between Data Types

2.11 IMPROVING IMAGE CONTRAST USING HISTOGRAM

EQUALIZATION

An image histogram is a graphical representation of the tonal distribution of

an image. It plots the number of pixels for each tonal value. The horizontal
axis of the graph represent the tonal variations, while the vertical axis
represent the number of pixel in that particular tone. The left side of the
horizontal axis represent the black and dark areas, the middle represents
medium grey and the right hand side represents the light and pure white
areas.

Figure 2.5: Sample Image

the above can be plotted from the following syntax:

>>imhist(f)
Page|14
 Figure 2.6: Histogram Representing The Sample Image

Now, we can observe the from the histogram that the tonal distribution is
concentrated to the left hand side which represent the dark and grey areas
which is evident from the given photo.
The image contrast of the given image can be improve using histogram

Figure 2.7: Sample Image With Different Contrast

Page|15
equalization in which tonal distribution is spread over the full range
horizontal axis. This equalization is achieved using histeq function.
I = histeq(f);

>> imhist(I)

Figure 2.8: Histogram Equalisation

Page|16
2.12 CONCLUSION
Thus we see that Digital image processing is the use of computer
algorithms to perform image processing on digital images. As a
subcategory or field of digital signal processing, digital image processing
has many advantages over analog image processing. It allows a much
wider range of algorithms to be applied to the input data and can avoid
problems such as the build-up of noise and signal distortion during
processing. Since images are defined over two dimensions (perhaps more)
digital image processing may be modelled in the form of multidimensional
systems.

Page|17
 CHAPTER 3
BIOMETRICS

3.1 What are biometrics ?

Biometrics is the technical term for body measurements and calculations. It
refers to metrics related to human characteristics. Biometrics authentication
(or realistic authentication) is used in computer science as a form of
identification and access control. It is also used to identify individuals in
groups that are under surveillance.
Biometric identifiers are then distinctive, measurable characteristics used to
label and describe individuals. Biometric identifiers are often categorized as
physiological versus behavioural characteristics. Physiological
characteristics are related to the shape of the body. Behavioural
characteristics are related to the pattern of behaviour of a person.

3.2 Types of Biometrics:

Fingerprint , Palm Veins, Face Recognition, DNA, Palm Print, Hand

Geometry, Iris recognition, Retina Recognition, Odour/ Scent, Typing
Rhythm , Gait , and Voice are some of the types of biometrics use now
days. Apart from them many other biometrics have been planned or are in
work for future.

3.3 History of Biometrics:

The earliest form of Biometrics appeared on the scene back in the 1800's.
Alphonse Bertillon, a Persian anthropologist and police desk clerk,
developed a method for identifying criminals that became known as
Bertillonage. Bertillonage was a form of anthropometry, a system by which
measurements of the body are taken for classification and comparison
purposes. Bertillon's system of anthropometry required numerous and
precise measurements of the bony parts of a humans anatomy for
identification. It also involved recording shapes of the body in relation to
movements and differential markings on the surface of the body such as
scars, birth marks, tattoos, etc. Bertillon estimated that the odds
of duplicate records were 286,435,456 to 1 if 14 traits were used. This was
the primary system of criminal identification used during the 19th century.
Page|18
3.4 Functioning factors of Biometrics:
The selection of a particular biometric for use in a specific application
involves a weighting of several factors. Jain et al. (1999)[2,3] identified
seven such factors to be used when assessing the suitability of any trait for
use in biometric authentication.

1. Universality means that every person using a system should possess

the trait.
2. Uniqueness means the trait should be sufficiently different for
individuals in the relevant population such that they can be
distinguished from one another.
3. Permanence relates to the manner in which a trait varies over time.
More specifically, a trait with 'good' permanence will be reasonably
invariant over time with respect to the specific matching algorithm.
4. Measurability (collectability) relates to the ease of acquisition or
measurement of the trait. In addition, acquired data should be in a
form that permits subsequent processing and extraction of the
relevant feature sets.
5. Performance relates to the accuracy, speed, and robustness of
technology used (see performance section for more details).
6. Acceptability relates to how well individuals in the relevant population
accept the technology such that they are willing to have their
biometric trait captured and assessed.
7. Circumvention relates to the ease with which a trait might be imitated
using an artefact or substitute.

The block diagram illustrates the two basic modes of a biometric system.
First, in verification (or authentication) mode the system performs a one-to-
one comparison of a captured biometric with a specific template stored in a
biometric database in order to verify the individual is the person they claim
to be. Three steps are involved in the verification of a person. In the first
step, reference models for all the users are generated and stored in the
model database. In the second step, some samples are matched with
reference models to generate the genuine and impostor scores and
calculate the threshold. Third step is the testing step. This process may use
a smart card, username or ID number (e.g. PIN) to indicate which template
should be used for comparison. 'Positive recognition' is a common use of
the verification mode, "where the aim is to prevent multiple people from
using the same identity".

Page|19
Second, in identification mode the system performs a one-to-many
comparison against a biometric database in an attempt to establish the
identity of an unknown individual. The system will succeed in identifying the
individual if the comparison of the biometric sample to a template in
the database falls within a previously set threshold. Identification mode can
be used either for 'positive recognition' (so that the user does not have to
provide any information about the template to be used) or for 'negative
recognition' of the person "where the system establishes whether the
person is who she (implicitly or explicitly) denies to be". The latter function
can only be achieved through biometrics since other methods of personal
recognition such as passwords, PINs or keys are ineffective.

Fig.1 Main Logical block of Biometric System

Page|20
3.5 Performance:

The following are used as performance metrics for biometric systems:

1. False match rate (FMR, also called FAR = False Accept Rate): the
probability that the system incorrectly matches the input pattern to a
non-matching template in the database. It measures the percent of
invalid inputs that are incorrectly accepted. In case of similarity scale,
if the person is an imposter in reality, but the matching score is higher
than the threshold, then he is treated as genuine. This increases the
FMR, which thus also depends upon the threshold value.
2. False non-match rate (FNMR, also called FRR = False Reject Rate):
the probability that the system fails to detect a match between the
input pattern and a matching template in the database. It measures
the percent of valid inputs that are incorrectly rejected.
3. Relative operating characteristic (ROC): The ROC plot is a visual
characterization of the trade-off between the FMR and the FNMR. In
general, the matching algorithm performs a decision based on a
threshold that determines how close to a template the input needs to
be for it to be considered a match. If the threshold is reduced, there
will be fewer false non-matches but more false accepts. Conversely,
a higher threshold will reduce the FMR but increase the FNMR. A
common variation is the Detection error trade-off (DET), which is
obtained using normal deviation scales on both axes. This more
linear graph illuminates the differences for higher performances (rarer
errors).
4. Equal error rate or crossover error rate (EER or CER): the rate at
which both acceptance and rejection errors are equal. The value of
the EER can be easily obtained from the ROC curve. The EER is a
quick way to compare the accuracy of devices with different ROC
curves. In general, the device with the lowest EER is the most
accurate.
5. Failure to enroll rate (FTE or FER): the rate at which attempts to
create a template from an input is unsuccessful. This is most
commonly caused by low quality inputs.
6. Failure to capture rate (FTC): Within automatic systems, the
probability that the system fails to detect a biometric input when
presented correctly.
7. Template capacity: the maximum number of sets of data that can be
stored in the system.

Page|21
3.6 Recent advances in emerging biometrics:

8. In recent times, biometrics based on brain (electroencephalogram) and

heart (electrocardiogram) signals have emerged. The research group
at University of Kent led by Ramaswamy Palaniappan has shown that
people have certain distinct brain and heart patterns that are specific for
each individual. The advantage of such 'futuristic' technology is that it is
more fraud resistant compared to conventional biometrics like
fingerprints. However, such technology is generally more cumbersome
and still has issues such as lower accuracy and poor reproducibility over
time. This new generation of biometrical systems is called biometrics of
intent and it aims to scan intent. The technology will analyze
physiological features such as eye movement, body temperature,
breathing etc. and predict dangerous behaviour or hostile intent before it
materializes into action.
9. On the portability side of biometric products, more and more vendors
are embracing significantly-miniaturized Biometric Authentication
Systems (BAS) thereby driving elaborate cost savings especially for
large scale deployments.

3.7 What is Fingerprint :

1. A fingerprint in its narrow sense is an impression left by the friction

ridges of a human finger. The recovery of fingerprints from a crime
scene is an important method of forensic science. Fingerprints are
easily deposited on suitable surfaces (such as glass or metal or
polished stone) by the natural secretions of sweat from the eccrine
glands that are present in epidermal ridges. These are sometimes
referred to as "Chanced Impressions".
2. In a wider use of the term, fingerprints are the traces of an impression
from the friction ridges of any part of a human or other primate hand.
A print from the sole of the foot can also leave an impression of
friction ridges.
3. Deliberate impressions of fingerprints may be formed by ink or other
substances transferred from the peaks of friction ridges on the skin to
a relatively smooth surface such as a fingerprint card. Fingerprint
records normally contain impressions from the pad on the last joint of
fingers and thumbs, although fingerprint cards also typically record
portions of lower joint areas of the fingers.

Page|22
3.8 Fingerprint Representation
The uniqueness of a fingerprint is determined by the topographic relief of its
ridge structure and the presence of certain ridge anomalies termed as
minutiae points[7]. Typically, the global configuration defined by the ridge
structure is used to determine the class of the fingerprint, while the
distribution of minutiae points is used to match and establish the similarity
between two fingerprints. Automatic fingerprint identification systems, that
match a query print against a large database of prints (which can consist of
millions of prints), rely on the pattern of ridges in the query image to narrow
their search in the database(fingerprint indexing), and on the minutiae
points to determine an exact match(fingerprint matching). The ridge flow
pattern itself is rarely used for matching fingerprints.
The main ingredients of any fingerprint that are useful during pattern
recognition and matching tasks are the features it possesses.
The features are defined by type, position, orientation and so on and they
exhibit uniqueness from fingerprint to fingerprint. Fingerprint features are
classified into two categories; namely local and global features. The local
features are the tiny, unique characteristics of fingerprint ridges that are
used for identification. They are found in the local area only and are
invariant with respect to global transformation. Two or more impressions of
same finger may have identical features but still differ because they have
minutia points that are different .

3.9 Minutiae
Minutiae, in fingerprinting terms, are the points of interest in a fingerprint,
such as bifurcations (a ridge splitting into two) and ridge endings[7].
Examples are:
a.) ridge endings - a ridge that ends abruptly
b.) ridge bifurcation - a single ridge that divides into two ridges
c.) short ridges, island or independent ridge - a ridge that commences,
travels a short distance and then ends.
d.) ridge enclosures - a single ridge that bifurcates and reunites shortly
afterward to continue as a single ridge
e.)spur - a bifurcation with a short ridge branching off a longer ridge
Page|23
f.) crossover or bridge - a short ridge that runs between two parallel ridges

Fig.1a Types Of Minutiae

Basic Ridge Patterns:

The ridge patterns are the patterns formed from the dark areas of the
finger tip epidermis produced when a finger is pressed against a
smooth surface. The valleys are the bright areas. Ridges and valleys
run in parallel as shown in Figure 2.

Page|24
The ridges form pattern of left loop, right loop, whorl, arch and tented
arch as shown in Figure 3. In the loop pattern, the ridges enter from
either side, re-curve and pass out or tend to pass out the same side
they entered. In the right loop pattern, the ridges enter from the right
side while the ridges enter from the left side in the left loop. In a whorl
pattern, the ridges are usually circular while in the arch pattern, the
ridges enter from one side, make a rise in the centre and exit
generally on the opposite side.

FIGURE 3: Basic Types Of Fingerprint Pattern

Page|25
3.10 Pattern Area

The pattern area is the part of the fingerprint where the global
features are found. Fingerprints can be read and classified based on
the information in this area. The following are the information
available in the pattern area of a fingerprint [2-4]:
a. Type Lines and Ridge Count: Type Lines are the two innermost
ridges that start parallel, diverge, and surround or tend to surround
the pattern area. When there is a definite break in a type line, the
ridge immediately outside that line is considered to be its
continuation. The Ridge Count is most commonly the number of
ridges between the Delta and the Core. To establish the ridge
count, an imaginary line is drawn from the Delta to the Core and
each ridge that touches this line is counted. The ridge count
between the core and delta shown in Figure 4 is the number of
ridges crossed by the imaginary lines drawn across the ridges.

1. Position: The position of the minutia point refers to its x, y location,

either in an absolute sense or relative to fixed points like the Delta
and Core points.
2. Type: Different types of minutiae are found in the fingerprint
pattern area. They include termination, bifurcation, lake,
independent ridge, point or island, spur, cross over and so on.
3. Spatial Frequency: Spatial frequency refers to how far apart the
ridges are in the neighbourhood of the minutia point. It is
measured by the average distance apart of the ridges.

4. Orientation: The minutia orientation is defined by its direction. The

orientations of the ridge ending and bifurcation of Figure 5 are
marked as and β respectively.

Page|26
5. Curvature: The curvature refers to the rate of change of ridge
orientation. The curvature, c of one of the two ridge endings of Figure
6 is obtained from the absolute difference between 2 of Figure 6(b)
and 1 of Figure 6(a). It is the displacement angle resulting from the
change in orientation of the ridge pattern.

6. Core and Delta Areas: The core area is located at the approximate
center of the finger impression as shown in Figure 7 and it is used as
a reference point for reading and classifying the print. The Delta area
is the region in the ridge pattern where there is triangulation or a
dividing of the ridges as shown in Figure 7. It is also the point of the
first bifurcation, abrupt ridge ending, meeting point of two ridges, dot,
fragmentary ridge, or any point upon a ridge at or nearest to the
center of divergence of two type lines, located at or directly in front of
their point of divergence. It is a definite fixed point used to facilitate
ridge counting and tracing.

Page|27
3.11 CONCLUSION
Biometrics (or biometric authentication) consists of methods for uniquely
recognizing humans based upon one or more intrinsic, physical or
behavioral In traits computer science, in particular, biometrics is used as
access control. It is also used to identify individuals in groups that are
under surveillance. Biometric characteristics can be divided in two main
classes: Physiological (fingerprint, face recognition, iris recognition etc) and
Behavioral (voice, vocal tract etc).

A biometric system can operate in the following two modes: verification

mode & Identification mode. Fingerprint recognition or fingerprint
authentication refers to the automated method of verifying a match
between two human fingerprints. Fingerprint recognition identifies people
by using the impressions made by the minutiae ridge formations or patterns
found on the fingertips. Finger printing takes an image of a
person's fingertips and records its characteristics - whorls, arches, and
loops are recorded along with patterns of ridges, furrows, and minutiae.

Page|28
 CHAPTER-4
PROBLEM FORMULATION

Our Project will deal with the acquiring of fingerprints samples taken from
the crime scene/the sample which is to be analyzed. The image of the
same will be enhanced and processed through numerous stages and filters
using MATLAB functions such as Histogram Equalization, Neighbourhood
Operations, Linear and Non Linear Filtering, Spatial Image Transformation,
Image restoration, Deblurring, Binarization in the Region of Interest where
the enhancement is required.
Then, after the pre-processing stage termination and the bifurcation is
done and thinning and minutiae will be extracted. The next and last
stage is the post processing stage in which orientation is calculated ,
lines are drawn at minutiae points. Then, these minutiae and the
orientation are stored which will be further cross-matched with the entire
set of fingerprints stored in the database using Minutiae Based
Techniques.

Page|29
 CHAPTER-5
CONCLUSION

Image Processing is the use of computer algorithms to perform image

processing on digital images. As a subcategory or field of digital signal
processing, digital image processing has many advantages over analog
image processing. It allows a much wider range of algorithms to be applied
to the input data and can avoid problems such as the build-up of noise and
signal distortion during processing. Since images are defined over two
dimensions (perhaps more) digital image processing may be modelled in
the form of multidimensional systems.
Biometrics (or biometric authentication) consists of methods for uniquely
recognizing humans based upon one or more intrinsic, physical or
behavioural In traits computer science, in particular, biometrics is used as
access control. It is also used to identify individuals in groups that are
under surveillance. Biometric characteristics can be divided in two main
classes: Physiological (fingerprint, face recognition, iris recognition etc) and
Behavioural (voice, vocal tract etc).

A biometric system can operate in the following two modes: verification

mode & Identification mode. Fingerprint recognition or fingerprint
authentication refers to the automated method of verifying a match
between two human fingerprints. Fingerprint recognition identifies people
by using the impressions made by the minutiae ridge formations or patterns
found on the fingertips. Finger printing takes an image of a
person's fingertips and records its characteristics - whorls, arches, and
loops are recorded along with patterns of ridges, furrows, and minutiae.
Also we see that the image processing technique provides us a better
approach to tackle security analysis and with the help of the above
techniques the security problems can be resolved to a particular level.

Page|30
 CHAPTER-6
SCOPE OF FUTURE WORK

As the presented report is useful for small database system therefore it is

felt to learn more methods and call function which are used for handling
large database systems.
In addition to this fingerprint sensor should be able to work even in case of
absurd fingerprints i.e. the case of wound, unwanted colour etc. This
situation demand for making provisions for perfect matching, and reducing
processing time also in order to attend the actual fingerprint database from
a large database system with minimum efforts and assured guarantee.
To achieve the above expected application, statistical signal processing
methods are the reasonable options.

Page|31
 References

[1]R. Gonzalez, R. Woods and S. Eddins, Digital image processing using MATLAB®. Chennai
[etc.]: McGraw Hill Education (India) Private Limited, 2016.

[2]"Biometrics", En.wikipedia.org, 2017. [Online]. Available:

http://en.wikipedia.org/wiki/Biometrics. [Accessed: 01- Dec- 2017].

[3]"Minutiae", En.wikipedia.org, 2017. [Online]. Available:

http://en.wikipedia.org/wiki/Minutiae. [Accessed: 01- Dec- 2017].

[4]2017. [Online]. Available:

http://bme.med.upatras.gr/improc/enhancement_point_processing.htm. [Accessed: 30- Nov-
2017].

[5]M. Brezinski, A. Press and M. Beck, "An Introduction To Digital Image Processing With
Matlab | Rgb Color Model | Integer (Computer Science)", Scribd, 2017. [Online]. Available:
http://www.scribd.com/doc/53194495/34/Non-linear-%EF%AC%81lters#page=15. [Accessed:
01- Dec- 2017].

[6]A. Randhawa, "Review Paper on Image Enhancement and Its Techniques", International
Journal Of Engineering And Computer Science, 2017.

[7]2017. [Online]. Available: https://www.researchgate.net/publication/45523951_A_Karnaugh-

Map_based_fingerprint_minutiae_extraction_method. [Accessed: 01- Dec- 2017].

[8]"Bit Depth", Cambridgeincolour.com, 2017. [Online]. Available:

http://www.cambridgeincolour.com/tutorials/bit-depth.htm. [Accessed: 30- Nov- 2017].

[9]2017. [Online]. Available:

https://in.mathworks.com/help/help/pdf_doc_images/images_tb.pdf. [Accessed: 01- Dec- 2017].

[10]2017. [Online]. Available:

https://www.wfu.edu/matthews/misc/graphics/formats/formats.html. [Accessed: 01- Dec- 2017].

Page|32