Final Lekha Report

General Seminar Report Biometrics : Fingerprint Technology
Contents
Acknowledgement…………………………………………………………………………..02
Abstract……………………………………………………………………………………..03
Chapter I - Introduction……………………………………………………………………..04
Chapter II - Literature Survey……………………………………………………………....07
Chapter III – Fingerprints…………………………………………………………………...08
Chapter IV – Fingerprint Scanners…………………………………………………………12
Chapter V – Fingerprint Recognition………………………………………………………19
Chapter VI – Fingerprint Images……………………………………………………………22
Conclusion……………………………………………………………………………………23
References…………………………………….……………………………………………...24
MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 1 2451-15-735-136

ACKNOWLEDGEMENT
I would like to express my immense gratitude to all those who have directly or indirectly helped
me in completing seminar on BIOMETRICS : FINGERPRINT TECHNOLOGY. I would like to
thank them for their effective guidance & kind cooperation without which I would not have been
able to introduce a good presentation and complete this report.
I am greatly thankful to Dr. B. Sarala, Professor and Head of the department of Electronics &
Communication Engineering and to our seminar coordinators Mr.G.V.Chalapathi Rao,Asst.prof.
and Mrs.K.V.B.L. Deepthi, Asst. Prof., for their encouragement and advice during our work.
I would like to express my thanks to my parents and friends who were ready with a positive
comment all the time , whether it was an off-hand comment to encourage me or a constructive
piece of criticism .

ABSTRACT
Reliable user authentication is becoming an increasingly important task in the Web-
enabled world. The consequences of an insecure authentication system in a corporate or
enterprise environment may include loss of confidential information, denial of service, and
compromised data integrity. The prevailing techniques of user authentication, which involve the
use of either passwords and user IDs (identifiers), or identification cards and PINs (personal
identification numbers), suffer from several limitations . Once an intruder acquires the user ID
and the password, the intruder has total access to the user's resources.
Fortunately, automated biometrics in general, and Fingerprint Technology in particular,

can provide a much more accurate and reliable user authentication method. Biometrics is a
rapidly advancing field that is concerned with identifying a person based on his or her
physiological or behavioral characteristics. Examples of automated biometrics include
fingerprint, face, iris, and speech recognition. Because a biometric property is an intrinsic
property of an individual, it is difficult to surreptitiously duplicate and nearly impossible to
share. The greatest strength of biometrics, the fact that the biometrics does not change over time,
is at the same time its greatest liability.

CHAPTER I
INRODUCTION
The concept of fingerprint biometrics has been in existence for thousands of years. Potters from
East Asia used to place their fingerprints on clay as it cured. Fingerprints were also used in the
19th century by criminologists for identification of habitual criminals. However, biometrics first
appeared in the 1970s as an automated technology.
An organization can enjoy limitless benefits by correctly deploying biometric technology.

Today’s economy is an evolving one and technological advancements have changed the way in
which organizations function and conduct businesses. Modern organizations need to be adaptive,
flexible and agile to survive in the competitive business environment. Fingerprint technology can
benefit organizations in a variety of sectors such as health care, government, retail enterprises,
technology organizations, manufacturing industry, libraries, universities etc.
Commercial applications started using biometrics for controlling physical access to buildings.
With the advancements in technology, this trend continues to grow. The increasing need to
reduce instances of fraud as well as to provide secured access to physical and logical assets have
made fingerprint biometrics a very popular and widely used technology.
Biometrics is a very strong authentication mechanism as it based on something that you are as
opposed to something you know or something you have. Passwords and tokens are highly
vulnerable to being lost or stolen. A weak or compromised password is the primary reason for
the rising cases of security and data breaches. Passwords are the weakest link in an
organization’s security system and even strong passwords cannot resist sophisticated hacker
attacks. Further, the costs of maintaining password and token based systems are very high and
inefficient. Resetting lost or forgotten passwords takes up IT support time and reduces employee
productivity.
Employee identification and workforce management becomes faster, accurate and more efficient
with fingerprint technology. Unlike magnetic strip cards or passwords, individuals always carry
their fingerprints with them and they cannot be lost or forgotten. Tracking attendance of
employees in manufacturing organizations prevents employee time theft and reduces fraudulent
behavior. A biometric system enables automated calculation of employee hours thus reducing
paper wastage and time spent in manual reconciliation of attendance data. Fingerprint biometrics
can provide both physical access to company buildings and logical access to internal resources
such as enterprise computers and systems.

Governments and organizations all around the world are choosing biometric technology to
combat identity fraud and security breaches, secure confidential data, reduce costs and to
improve overall user experience. Biometrics is one of the rapidly growing fields in the
information technology sector with fingerprint recognition expected to remain the most dominant
form of biometric technology.
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).
Block Diagram of a biometric system :

A biometric system can operate in the following two modes. In verification 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. In Identification mode the system performs a one-to-many comparison against a biometric
database in attempt to establish the identity of an unknown individual.

CHAPTER II
LITERATURE SURVEY
Existing authentication systems relying on knowledge-based approaches like passwords or

token-based such as magnetic cards and passports contain serious security risks due to the
vulnerability to engineering-social attacks and the easiness of sharing or compromising
passwords and PINs. However, due to large biometric database and complicated biometric
measures, it is difficult to design both an accurate and fast biometric recognition. Particularly,
fast fingerprint indexing is one of the most challenging problems faced in fingerprint
authentication system. A specific contribution by introducing a new robust indexing scheme that
is able not only to fasten the fingerprint recognition process but also improve the accuracy of the
system has been done.[1]
Most fingerprint recognition techniques are based on minutiae matching. However, this
technology still suffers from problems associated with the handling of poor quality impressions.
One problem besetting fingerprint matching is distortion. Distortion changes both geometric
position and orientation, and leads to difficulties in establishing a match among multiple
impressions acquired from the same finger tip. Marking all the minutiae accurately as well as
rejecting false minutiae is another issue still under research. Also some novel changes like
segmentation using morphological operations, improved thinning, false minutiae removal
methods, minutia marking with special considering the triple branch counting, minutia
unification by decomposing a branch into three terminations, and matching in the unified x-y
coordinate system are introduced.[2]
Fingerprint Matching Using Level 3 Features. Fingerprint friction ridge details are generally
described in a hierarchical order at three levels, namely, Level 1 (pattern), Level 2 (minutiae
points) and Level 3 (pores and ridge shape). Although high resolution sensors (∼1000dpi) have
become commercially available and have made it possible to reliably extract Level 3 features,
most Automated Fingerprint Identification Systems (AFIS) employ only Level 1 and Level 2
features. As a result, increasing the scan resolution does not provide any matching performance
improvement . They develop a matcher that utilizes Level 3 features, including pores and ridge
contours, for 1000dpi fingerprint matching. Level 3 features are automatically extracted using
wavelet transform and Gabor filters and are locally matched using the ICP algorithm.[3]

CHAPTER III
FINGERPRINTS
2.1 Fingerprint patterns:
Fingerprints are the tiny ridges, whorls and valley patterns on the tip of each finger. They
form from pressure on a baby's tiny, developing fingers in the womb. No two people have been
found to have the same fingerprints -- they are totally unique. There's a one in 64 billion chance
that your fingerprint will match up exactly with someone else's.
Fingerprints are even more unique than DNA, the genetic material in each of our cells. Although
identical twins can share the same DNA -- or at least most of it -- they can't have the same
fingerprints.
Fingerprinting is one form of biometrics, a science that uses people's physical characteristics to
identify them. Fingerprints are ideal for this purpose because they're inexpensive to collect and
analyze, and they never change, even as people age.
Although hands and feet have many ridged areas that could be used for identification,
fingerprints became a popular form of biometrics because they are easy to classify and sort.
They're also accessible.
Fingerprints are made of an arrangement of ridges, called friction ridges. Each ridge contains
pores, which are attached to sweat glands under the skin. You leave fingerprints on glasses,
tables and just about anything else you touch because of this sweat.
Scientists look at the arrangement, shape, size and number of lines in these fingerprint patterns
to distinguish one from another. They also analyze very tiny characteristics called minutiae,
which can't be seen with the naked eye.All of the ridges of fingerprints form patterns as follows :
1. Arch
In arches, the ridges of the finger run continuous from one side of the finger to the other with no
recurving. There are two sub-groups that further define the arch pattern:
Plain Arch---this pattern has a consistency of flow to it. It starts on one side of the finger, and
then the ridge cascades upward slightly, almost resembling a wave out on the ocean. The plain
arch then continues its journey along the finger to the other side. The plain arch is the simplest of
the fingerprint patterns to discern.

Tented Arch---this pattern is similar to the plain arch in that it starts on one side of the finger and
flows out in a similar pattern to the other side. However, the difference in the tented arch lies in
the ridges in the center, which are not continuous as in the case of the plain arch. The ridges,
which adjoin each other in the center, converge and thrust upward, giving the impression of a
pitched tent.
2. Loop
In loops, the ridges make a backward turn but do not twist. This backward turn, or loop, is
differentiated by how the loop flows on the hand and not how it flows on the card on which the
imprint is taken. The imprint on the fingerprint card is similar to the reverse image we see when
we look in the mirror at ourselves. There are two sub-groups that Henry identified in this
category:
Radial Loop---these are loops that flow toward the radius bone of the hand or, in other words,
when the downward slope of the loop is from the direction of the little finger toward the thumb
of the hand.
Ulnar Loop---these are loops that flow toward the ulna bone of the hand or, in other words, when
the downward slope of the loop is from the direction of the thumb toward the little finger of the
hand.
3. Whorls
In whorls, there are patterns in which there are two or more deltas (first ridge nearest the
divergence point of two type lines) and there exists a recurve preceding each delta. There are
four sub-groups of whorls:
Plain Whorl--- in these whorls, the ridges make a turn of one complete circuit and, therefore, are
circular or spiral in shape. The plain whorl is the simplest form of whorl and the most common.
There are at least two deltas and a ridge whose circuit may be spiral, oval or circular in shape.
Central Pocket --- in these whorls, one or more of the simple recurves of the plain whorl recurves
a second time.
Double Loop--- in these whorls, there are two separate loop formations. In each of these
formations, there are two entirely separate and distinct sets of shoulders and deltas.
Accidental Whorl--- in these whorls, the composition of the pattern is derived from two distinct
types of patterns with at least two deltas. Whorls which contain ridges matching the
characteristics of a particular whorl sub-grouping are classified as accidental whorls.

4. Composites
In composites, there are patterns found in fingerprints which are combinations of arch, loop and
whorl. Henry subdivided the composites into four sub-groups:
Central Pocket Loop---these loops recurve a second time forming a pocket within the loop.
Twinned Loop---also referred to as the Double Loop, these loops consist of two separate loop
formations.
Lateral Pockets Loop---these loops are similar to the Twinned Loop except that their ridges bend
sharply down on one side before recurving, actually forming a pocket. The F.B.I. finds it too
difficult to locate these two loops, and classifies both kinds as Double Loops.
Accidental Loops---these loops are a combination of any two types of pattern with the exception
on the plain arch that basically has no pattern.

2.2 Fingerprint reader

An electronic device that records a digital image of the fingerprint pattern is known as a
fingerprint reader. The captured image is known as a live scan which is then digitally processed.
The distinguishing features are extracted and a fingerprint biometric template is created. This
biometric template is stored and will be used for matching later.

CHAPTER IV
FINGERPRINT SCANNERS
In simple words fingerprint scanner is an electronic device used for capturing digital image of
fingerprint patterns. Fingerprints scanners come in different sizes, shaped, equipped with
different sensor types and technology; depending on the usage. Access control is a common
application of fingerprint scanners and access control fingerprint scanners come with networking
capability to connect with a standalone computer or a computer network through wire or wireless
means. On the other hand, a USB fingerprint scanner is only active when connected to a
smartphone or a computer, which should be running a supporting app.
Fingerprint scanners for access control often come with supporting software. Supporting
software installed on a designated computer can communicate with fingerprint scanner to import
data like clock-in and clock-out time of employees; can generate different reports and matrices,
depending on the capability of the software. While access control fingerprint scanners have
capability to scan and store fingerprint template without any assistance from an additional IT
system, there are tiny scanners available in the market, which have no processing capability
unless they are connected with a smartphone or a computer. They just scan the fingerprint and
send it to the app, and then the app can perform further processing.
A fingerprint scanner consists of :
1. A reader or scanning device.
2. Software that converts the scanned information into digital form and compares match
points.
3. A database that stores the biometric data for comparison.

How does a fingerprint scanner work ?
Fingerprint scanners may employ different types of sensors to scan and generate the digital
image of fingerprint patterns. Fingerprint sensors make use of different techniques to scan
fingerprints, for example a sensor may be optical, capacitive, thermal, etc. When a finger is put
on the scanning area, digital image of fingerprint patterns is read by the sensor. This digital
image is pre-processed to remove unnecessary noise and enhance the image quality. This
enhanced image is taken through fingerprint algorithm to identify unique points like ridge
endings, bifurcation, short ridge, island, spur, etc. These details are called minutiae. Since there
are a huge number of possibilities for the location of minutiae, fingerprints are theoretically
unique. A biometric template is generated after post-processing the fingerprint image, which is
stored in a database.
There are two main ways of scanning fingers. An optical scanner works by shining a bright
light over your fingerprint and taking what is effectively a digital photograph. If you've
ever photocopied your hand, you'll know exactly how this works. Instead of producing a dirty
black photocopy, the image feeds into a computer scanner. The scanner uses a light-sensitive
microchip (either a CCD, charge-coupled device, or a CMOS image sensor) to produce a digital
image. The computer analyzes the image automatically, selecting just the fingerprint, and then
uses sophisticated pattern-matching software to turn it into a code.
Another type of scanner, known as a capacitive scanner, measures your finger electrically.
When your finger rests on a surface, the ridges in your fingerprints touch the surface while the
hollows between the ridges stand slightly clear of it. In other words, there are varying distances
between each part of your finger and the surface below. A capacitive scanner builds up a picture
of your fingerprint by measuring these distances. Scanners like this are a bit like
the touchscreens on things like iPhones and iPads.
1. Optical scanner :
Optical sensing is the earliest method used for capturing fingerprint features. Optical fingerprint
sensors make use of an image sensor to capture image of the fingertip surface. The basic
configuration of capturing fingerprint image by an optical sensor is more or less same as a digital
photography camera. This captured image is then post-processed to enhance quality and make it
usable for fingerprint recognition algorithm. Optical sensors have high resolution image sensor
to capture as much details as possible. The higher the resolution, the finer details the sensor can
discern about your finger, increasing the level of security.

Optical sensors have inbuilt light source to illuminate fingertip surface as external lighting
cannot be of much help when fingertip is placed on the scanning surface. Source of light is
mostly LEDs to keep the power consumption low. The positive side of optical sensors is that
they are cheap and found mostly on inexpensive biometric devices, however, they are
comparatively easy to spoof as they only make use of a two dimensional fingerprint image.
There are optical fingerprint sensors that come with liveness detections as well, to safeguard
from spoofing.
A row of LEDs scans bright light onto the glass (or plastic) surface on which your finger is
pressing (sometimes called the platen).The quality of the image will vary according to how
you're pressing, how clean or greasy your fingers are, how clean the scanning surface is, the light
level in the room, and so on.Reflected light bounces back from your finger, through the glass,
onto a CCD or CMOS image sensor.The longer this image-capture process takes, the brighter the
image formed on the image sensor.
If the image is too bright, areas of the fingerprint (including important details) may be washed
out completely—like an indoor digital photo where the flash is too close or too bright. If it's too
dark, the whole image will look black and details will be invisible for the opposite reason.
An algorithm tests whether the image is too light or too dark; if so, an audible beep or LED
indicator alerts the operator and we go back to step 1 to try again.If the image is roughly
acceptable, another algorithm tests the level of detail, typically by counting the number of ridges
and making sure there are alternate light and dark areas (as you'd expect to find in a decent
fingerprint image). If the image fails this test, we go back to step 1 and try again.

Providing the image passes these two tests, the scanner signals that the image is OK to the
operator (again, either by beeping or with a different LED indicator). The image is stored as an
acceptable scan in flash memory, ready to be transmitted (by USB cable, wireless, Bluetooth, or
some similar method) to a "host" computer where it can be processed further. Typically, images
captured this way are 512×512 pixels (the dimensions used by the FBI), and the standard image
is 2.5cm (1 inch) square, 500 dots per inch, and 256 shades of gray.The host computer can either
store the image on a database (temporarily or indefinitely) or automatically compare it against
one or many other fingerprints to find a match.
Factors that affect the image quality in optical sensors :
The quality of fingerprint image captured by optical sensors may get affected by many real world
factors. These factors may include stray light from another source or surface contamination such
as fingerprint impression left behind by a previous user. Other factors that affect image quality
are oil, dirt, condensation or ice and any scratches on the surface.
Compared to other scanner types, it is relatively easy to deceive optical scanners with impostor
fingerprints by presenting a convincing picture of a fingerprint. Optical scanner manufacturers
have thus introduced a variety of techniques that can validate a live finger. One such technique is
electro-optical imaging that enhances optical sensors and improves its resistance to deception. In
electro-optical imaging, a voltage is placed across a light-emitting polymer film. When the
individual places his finger on the sensor, the fingerprint ridges present a ground to the polymer
surface that creates a small current and generates light. This produces a high contrast image as
the valleys of the fingerprint remain dark and the polymer is directly linked with the optical
detector.
2. Capacitive scanners :
Capacitive scanners make use of pixel array of capacitors instead of visible light, to produce the
image of fingerprints. An array of tiny capacitors is placed just below the scanning surface to
collect fingerprint details. When fingertip touches the scanning surface, charge of capacitors
changes which are located just below the friction ridges. This difference of charge beneath the
friction ridges and valleys is tracked by an op-amp integrator circuit, which can then be recorded
by an analogue-to-digital converter.
Like optical scanners, capacitive fingerprint scanners generate an image of the ridges and valleys
that make up a fingerprint. But instead of sensing the print using light, the capacitors use
electrical current.

The diagram below shows a simple capacitive sensor. The sensor is made up of one or
more semiconductor chips containing an array of tiny cells. Each cell includes two conductor
plates, covered with an insulating layer. The cells are tiny -- smaller than the width of one ridge
on a finger.
The sensor is connected to an integrator, an electrical circuit built around an inverting

operational amplifier. The inverting amplifier is a complex semiconductor device, made up of a
number of transistors, resistors and capacitors. The details of its operation would fill an entire
article by itself, but here we can get a general sense of what it does in a capacitance scanner.
(Check out this page on operational amplifiers for a technical overview.)
Like any amplifier, an inverting amplifier alters one current based on fluctuations in another
current (see How Amplifiers Work for more information). Specifically, the inverting amplifier
alters a supply voltage. The alteration is based on the relative voltage of two inputs, called the
inverting terminal and the non-inverting terminal. In this case, the non-inverting terminal is
connected to ground, and the inverting terminal is connected to a reference voltage supply and
a feedback loop. The feedback loop, which is also connected to the amplifier output, includes
the two conductor plates.
As you may have recognized, the two conductor plates form a basic capacitor, an electrical
component that can store up charge . The surface of the finger acts as a third capacitor plate,
separated by the insulating layers in the cell structure and, in the case of the fingerprint valleys, a

pocket of air. Varying the distance between the capacitor plates (by moving the finger closer or
farther away from the conducting plates) changes the total capacitance (ability to store charge) of
the capacitor. Because of this quality, the capacitor in a cell under a ridge will have a greater
capacitance than the capacitor in a cell under a valley.
To scan the finger, the processor first closes the reset switch for each cell, which shorts each
amplifier's input and output to "balance" the integrator circuit. When the switch is opened again,
and the processor applies a fixed charge to the integrator circuit, the capacitors charge up. The
capacitance of the feedback loop's capacitor affects the voltage at the amplifier's input, which
affects the amplifier's output. Since the distance to the finger alters capacitance, a finger ridge
will result in a different voltage output than a finger valley.
The scanner processor reads this voltage output and determines whether it is characteristic of a
ridge or a valley. By reading every cell in the sensor array, the processor can put together an
overall picture of the fingerprint, similar to the image captured by an optical scanner.
The main advantage of a capacitive scanner is that it requires a real fingerprint-type shape, rather
than the pattern of light and dark that makes up the visual impression of a fingerprint. This
makes the system harder to trick. Additionally, since they use a semiconductor chip rather than a
CCD unit, capacitive scanners tend to be more compact that optical devices.
A comparison of optical and capacitive based fingerprint scanners :
The sensor type is optical in an optical scanner as the name suggests. In optical scanners, the
sensor surface does not require any special treatment or maintenance. Optical sensors are very
durable in nature. They are scratch-resistant and the glass plate is made of an unbreakable
material that is as hard as quartz. Optical scanners are also resistant to shock, extreme weather
and ESD. They are designed to perform well in high traffic as well as rough or outdoor
environments. It has a large imaging area that results in a larger as well as a higher resolution
image. The manufacturing cost is lower in optical scanners. It also has a long life and almost
zero maintenance.
A capacitive scanner has a semiconductor or chip type of sensor. The coatings on the surface of
capacitive scanners are uneven and wear out over time. This results in a degraded performance
and also shortens the lifetime of the product. Capacitive sensors usually need some kind of a
surface treatment such as ESD and other protective coatings. These sensors are not as durable as
optical sensors and can be damaged by electrostatic discharge. Repeated handling and everyday
exposure can corrode the surface easily. Moreover, silicon chips are thin and inherently fragile
and prone to be damaged by hard external impact and scratches. A capacitive scanner usually has
a smaller imaging area as compared to an optical scanner which results in a smaller image size

with lower resolution. It is expensive to produce surface coatings of consistent quality. There can
also be other expenses such as replacement, downtime and maintenance costs.
3. Ultrasonic scanners :
Qualcomm’s 3D in-display ultrasonic fingerprint scanner is based on what used to be called
Sense ID. Rather than existing photographic or capacitive-based fingerprint scanners, ultrasonic
fingerprint scanners make use of very high-frequency ultrasonic sound. You can’t hear it, but
these waves are used to map out the details of the user’s fingerprint. Fortunately, there’s no need
to swipe, just touch the finger to the sensor like the top of the line capacitive fingerprint
scanners.
To actually capture the details of a fingerprint, the hardware consists of both a transmitter and a
receiver. An ultrasonic pulse is transmitted against the finger that is placed over the scanner.
Some of this pulse’s pressure is absorbed and some of it is bounced back to the sensor,
depending upon the ridges, pores and other details that are unique to each fingerprint.
There isn’t a microphone listening out for these returning signals. Instead, a sensor that can
detect mechanical stress is used to calculate the intensity of the returning ultrasonic pulse at
different points on the scanner. Scanning for longer periods of time allows for additional depth
data to be captured, resulting in a highly detailed 3D reproduction of the scanned fingerprint.
Ultrasonic fingerprint technology works very differently to capacitive fingerprint scanners,

which are only able to reproduce 2D images. 3D details are much more difficult to forge or fool
than a 2D image, making the ultrasonic system much more secure. It goes without saying that
ultrasound is also much more secure than optical fingerprint scanners, which have all but fallen
out of favor.
Another added perk of this ultrasonic fingerprint scanner technology is that it allows the
fingerprint scanner to still operate through thin materials, such as glass, aluminum, or plastic.
The sensor is just 0.15 millimeters thick and can scan through up to 800 µm of glass and up to
650 µm of aluminum. Therefore, the scanner can be embedded under the case or under the
display as we’re seeing in the Samsung Galaxy S10, allowing for a more discrete look and
thinner bezels.

CHAPTER V
FINGERPRINT RECOGNITION
A fingerprint-based biometric system is essentially a pattern recognition system that recognizes a

person by determining the authenticity of her fingerprint. Depending on the application context,
a fingerprint-based biometric system may be called either a verification system or an
identification system:
1. A verification system authenticates a person’s identity by comparing the captured fingerprints

with her own biometric template(s) pre-stored in the system. It conducts one-to-one comparison
to determine whether the identity claimed by the individual is true.
2. An identification system recognizes an individual by searching the entire template database

for a match. It conducts one-to-many comparisons to establish the identity of the individual.
Throughout this paper the generic term recognition is used where it is not necessary
distinguishing between verification and identification. The block diagrams of a fingerprint-based
verification system and an identification system are depicted in Figure 1; user enrollment, which
is common to both tasks is also graphically illustrated. The enrollment module is responsible for
registering individuals in the biometric system database (system DB). During the enrollment
phase, the fingerprint of an individual is acquired by a fingerprint scanner to produce a raw
digital representation. A quality check is generally performed to ensure that the acquired sample
can be reliably processed by successive stages. In order to facilitate matching, the raw digital
representation is usually further processed by a feature extractor to generate a compact but
expressive representation, called a template. The verification task is responsible for verifying
individuals at the point of access. During the operation phase, the user’s name or PIN (Personal
Identification Number) is entered through a keyboard (or a keypad); the biometric reader
captures the fingerprint of the individual to be recognized and converts it to a digital format,
which is further processed by the feature extractor to produce a compact digital representation.
The resulting representation is fed to the feature matcher, which compares it against the template
of a single user (retrieved from the system DB based on the user’s PIN).

In the identification task, no PIN is provided and the system compares the representation of the
input biometric against the templates of all the users in the system database; the output is either
the identity of an enrolled user or an alert message such as “user not identified.” Because
identification in large databases is computationally xpensive, classification and indexing
techniques are often deployed to limit the number of templates that have to be matched against
the input. The main building blocks of any fingerprint-based verification and identification
system are: 1) sensing, 2) feature extraction, and 3) matching. The output is affected by two
types of errors: mistaking biometric measurements from two different fingers to be from the
same finger (called false match) and mistaking two biometric measurements from the same
finger to be from two different fingers (called false non-match). Note that these two types of
errors are also often denoted as false acceptance and false rejection, but the notation “false

match/false non-match” is generally preferable because it is not application dependent .There is a

strict tradeoff between FMR (false match rate) and FNMR (false non-match rate) in every
biometric system. In fact, both FMR and FNMR are functions of a system accuracy threshold. If
t is decreased to make the system more tolerant with respect to input variations and noise, then
FMR increases; vice versa, if t is raised to make the system more secure, then FNMR increases
accordingly. Besides FMR and FNMR, a “compact” value is generally used to summarize the
accuracy of a verification system: the Equal-Error Rate (EER) denotes the error rate at the
threshold t for which false match rate and false non-match rate are identical: FMR = FNMR.

CHAPTER VI
FINGERPRINT IMAGES
The main parameters characterizing a digital fingerprint image are as follows :
Resolution: This indicates the number of dots or pixels per inch (dpi). 500 dpi is the minimum
resolution for FBI-compliant scanners and is met by many commercial devices; 250 to 300 dpi is
probably the minimum resolution that allows the extraction algorithms to locate the minutiae in
fingerprint patterns.
Area: The size of the rectangular area sensed by a fingerprint scanner is a fundamental
parameter. The larger the area, the more ridges and valleys are captured and the more distinctive
the fingerprint becomes. An area greater than or equal to 1 × 1 square inches (as required by FBI
specifications) permits a full plain fingerprint impression to be acquired. In most of the recent
fingerprint scanners aimed at non-AFIS market, area is sacrificed to reduce cost and to have a
smaller device size. Small-area scanners do not allow a whole fingerprint to be captured, and the
users encounter difficulties in re-presenting the same portion of the finger. This may result in a
small overlap between different acquisitions of the same finger, leading to false non-match
errors.
Number of pixels: The number of pixels in a fingerprint image can be simply derived by the
resolution and the fingerprint area: a scanner working at r dpi over an area of height(h) ×
width(w) inch2 has rh × rw pixels.
Dynamic range (or depth): This denotes the number of bits used to encode the intensity value
of each pixel. The FBI standard for pixel bit depth is 8 bits, which yields 256 levels of gray. •
Geometric accuracy: This is usually specified by the maximum geometric distortion introduced
by the acquisition device, and expressed as a percentage with respect to x and y directions.
Image quality: It is not easy to precisely define the quality of a fingerprint image, and it is even
more difficult to decouple the fingerprint image quality from the intrinsic finger quality or status.
In fact, when the ridge prominence is very low (especially for manual workers and elderly
people), when the fingers are too moist or too dry, or when they are incorrectly presented, most
of the scanners produce poor quality images.

CHAPTER VII
CONCLUSION
Recent developments in fingerprint scanners have focused on reducing both their cost and size.
Although lower cost and size are essential to enable a wide deployment of the technology in
civilian applications, some of these developments have been made at the expense of fingerprint
image quality (e.g., dpi resolution, etc.). It is very likely that while the market will continue to
drive down scanner prices, it will also require higher-quality products at the same time.
Manufacturers will continue to innovate low-cost small-size scanner designs, but they will also
take care that their products deliver high quality-images of large areas of the finger. Robust
extraction of fingerprint feature remains a challenging problem, especially in poor quality
fingerprints. Development of fingerprint-specific image processing techniques is necessary in
order to solve some of the outstanding problems. For example, explicitly measuring (and
restoring or masking) noise such as creases, cuts, dryness, smudginess, and the like will be
helpful in reducing feature extraction errors. Algorithms that can extract discriminative non-
minutiae-based features in fingerprint images and integrate them with the available features and
matching strategies will improve fingerprint matching accuracy. New (perhaps, model-based)
methods for computation (or restoration) of the orientation image in very low-quality images is
also desirable to reduce feature extraction errors. Most of the fingerprint matching approaches
introduced in the last four decades are minutiae-based, but recently correlation-based techniques
are receiving renewed interest. New texture-based methods have been proposed and the
integration of approaches relying on different features seems to be the most promising way to
significantly improve the accuracy of fingerprint recognition systems.
 Today’s business world need some computerized authentication for security purpose and
the character recognition fulfill their need.
 Current methods don’t work well and they don’t operate much like the human brain.
 The best commercial neural networks are now so good that they are used by banks to
process cheques, and by post offices to recognize addresses.

REFERENCES
 http://bias.csr.unibo.it/maltoni/handbook/
 http://computer.howstuffworks.com/fingerprint-scanner.htm
 www.scribd.com.
 www.bayometric.com
 Hoi Le, The Duy Bui, “Online fingerprint identification with a fast and distortion tolerant
hashing.” [1]
 Manvjeet Kaur, Mukhwinder Singh, Akshay Girdhar, and Parvinder S. Sandhu, “Fingerprint
Verification System using Minutiae Extraction Technique.” [2]
 Anil Jain, Yi Chen, and Meltem Demirkus, “Pores and Ridges: Fingerprint Matching Using
Level 3 Features.” [3]


Final Lekha Report

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Final Lekha Report

Uploaded by

Copyright:

Available Formats

General Seminar Report Biometrics : Fingerprint Technology

Chapter II - Literature Survey……………………………………………………………....07

Chapter III – Fingerprints…………………………………………………………………...08

Chapter IV – Fingerprint Scanners…………………………………………………………12

Chapter V – Fingerprint Recognition………………………………………………………19

Chapter VI – Fingerprint Images……………………………………………………………22

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 1 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 2 2451-15-735-136

Fortunately, automated biometrics in general, and Fingerprint Technology in particular,

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 3 2451-15-735-136

An organization can enjoy limitless benefits by correctly deploying biometric technology.

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 4 2451-15-735-136

Biometrics (or biometric authentication) consists of methods for uniquely recognizing

Block Diagram of a biometric system :

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 5 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 6 2451-15-735-136

Existing authentication systems relying on knowledge-based approaches like passwords or

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 7 2451-15-735-136

2.1 Fingerprint patterns:

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 8 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 9 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 10 2451-15-735-136

2.2 Fingerprint reader

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 11 2451-15-735-136

A fingerprint scanner consists of :

1. A reader or scanning device.

3. A database that stores the biometric data for comparison.

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 12 2451-15-735-136

How does a fingerprint scanner work ?

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 13 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 14 2451-15-735-136

Factors that affect the image quality in optical sensors :

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 15 2451-15-735-136

The sensor is connected to an integrator, an electrical circuit built around an inverting

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 16 2451-15-735-136

A comparison of optical and capacitive based fingerprint scanners :

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 17 2451-15-735-136

Ultrasonic fingerprint technology works very differently to capacitive fingerprint scanners,

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 18 2451-15-735-136

A fingerprint-based biometric system is essentially a pattern recognition system that recognizes a

1. A verification system authenticates a person’s identity by comparing the captured fingerprints

2. An identification system recognizes an individual by searching the entire template database

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 19 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 20 2451-15-735-136

match/false non-match” is generally preferable because it is not application dependent .There is a

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 21 2451-15-735-136

The main parameters characterizing a digital fingerprint image are as follows :

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 22 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 23 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 24 2451-15-735-136

MVSREC-B.E.4/4 SEM.-I,SEC-’C’ 25 2451-15-735-136

You might also like