INDEPENDENT STUDY SEMINAR

ON

BIOMETRICS

DEPTT OF BIOMEDICAL ENGG

DRONACHARYA COLLEGE OF ENGINEERING
FARRUKH NAGAR, GURGAON
2010- 2011
 BIOMETRICS
An

INDEPENDENT STUDY SEMINAR

Submitted by

SHOBHA SAINI

in partial fulfillment for the award of the degree

of

BACHELORS OF ENGINEERING

IN

BIOMEDICAL ENGINEERING

DRONACHARYA COLLEGE OF ENGINEERING

FARRUKHNAGAR, HARYANA
BIOMETRICS consists of methods for uniquely recognizing humans based upon one or
more intrinsic physical or behavioral traits. In computer science, in particular, biometrics is used
as a form of identity access management and access control. It is also used to identify individuals
in groups that are under surveillance.

WHY WE USE BIOMETRICS?

It makes it possible to guarantee in an absolute, infallible way and ultra confidential safety, the
recognition and access control with the physical places or the information processing systems,
revolutionizing in same time the securisation and the authentification of E-business and E-trade.

Biometric characteristics can be divided in two main classes:

 Physiological are related to the shape of the body. Examples include, but are not limited
to fingerprint, face recognition, DNA, Palm print, hand geometry, iris recognition, which
has largely replaced retina, and odour/scent.

 Examples of physical biometrics include:

Bertillonage - measuring body lengths
Fingerprint - analyzing fingertip patterns
Facial Recognition - measuring facial characteristics
Hand Geometry - measuring the shape of the hand
Iris Scan - analyzing features of colored ring of the eye
Retinal Scan - analyzing blood vessels in the eye
Vascular Patterns - analyzing vein patterns
DNA - analyzing genetic makeup

 Behavioral are related to the behavior of a person.

 Examples of behavioral biometrics include:

Speaker Recognition - analyzing vocal behavior
Signature - analyzing signature dynamics
Keystroke - measuring the time spacing of typed words
Strictly speaking, voice is also a physiological trait because every person has a different vocal
tract, but voice recognition is mainly based on the study of the way a person speaks, commonly
classified as behavioral.

It is possible to understand if a human characteristic can be used for biometrics in terms of the
following parameters:

 Universality – each person should have the characteristic.

 Uniqueness – is how well the biometric separates individuals from another.
 Permanence – measures how well a biometric resists aging and other variance over
time.
 Collectability – ease of acquisition for measurement.
 Performance – accuracy, speed, and robustness of technology used.
 Acceptability – degree of approval of a technology.
 Circumvention – ease of use of a substitute.

A biometric system can operate in the following two modes:

 Verification – A one to one comparison of a captured biometric with a stored template to

verify that the individual is who he claims to be. Can be done in conjunction with a smart
card, username or ID number.
 Identification – A one to many comparison of the captured biometric against a biometric
database in attempt to identify an unknown individual. The identification only succeeds
 in identifying the individual if the comparison of the biometric sample to a template in
the database falls within a previously set threshold.

The first time an individual uses a biometric system is called an enrollment. During the
enrollment, biometric information from an individual is stored. In subsequent uses, biometric
information is detected and compared with the information stored at the time of enrollment. Note
that it is crucial that storage and retrieval of such systems themselves be secure if the biometric
system is to be robust. The first block (sensor) is the interface between the real world and the
system; it has to acquire all the necessary data. Most of the times it is an image acquisition
system, but it can change according to the characteristics desired. The second block performs all
the necessary pre-processing: it has to remove artifacts from the sensor, to enhance the input (e.g.
removing background noise), to use some kind of normalization, etc. In the third block necessary
features are extracted. This step is an important step as the correct features need to be extracted
in the optimal way. A vector of numbers or an image with particular properties is used to create a
template. A template is a synthesis of the relevant characteristics extracted from the source.
Elements of the biometric measurement that are not used in the comparison algorithm are
discarded in the template to reduce the file size and to protect the identity of the enrollee.

If enrollment is being performed, the template is simply stored somewhere (on a card or within a
database or both). If a matching phase is being performed, the obtained template is passed to a
matcher that compares it with other existing templates, estimating the distance between them
using any algorithm (e.g. Hamming distance). The matching program will analyze the template
with the input. This will then be output for any specified use or purpose (e.g. entrance in a
restricted area).
How Biometrics Works
Your fingerprints, retina scans and voice recognition are all biological properties. These unique
human characteristics are being used in conjunction with other forms of technology for
identification and verification purposes. Most biometric systems measure and record biometric
characteristics of a person and matches the results to a database which contains information
about individual people.
Biometric systems compare unique human characteristics against a database which contains
information of many individuals. The matching of information occurs between a person's human
characteristic and data from a database. Biometric systems involve both one-to-one and one-to-
many matches. Verification, also known as authentication, uses one-to-one matches, whereas
identification uses one-to-many matching.
There are two types of human characteristics used for biometric recognition, physical and
behavioural. Fingerprints, hand geometry, facial and iris recognitions are various forms of
physiological biometrics which are measured to derive specific data to identify an individual.
Voice verification, keystroke dynamics, signatures and an individual's actions are forms of
behavioural characteristics, which are also measured to obtain information to directly or
indirectly verify a person's identity.

PERFORMANCE

The following are used as performance metrics for biometric systems:

 false accept rate or false match rate (FAR or FMR) – 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 which are incorrectly accepted.
 false reject rate or false non-match rate (FRR or FNMR) – 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 which are incorrectly rejected.
 receiver operating characteristic or relative operating characteristic (ROC) –
The ROC plot is a visual characterization of the trade-off between the FAR and the
FRR. In general, the matching algorithm performs a decision based on a threshold
which 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 less false non-matches but more
false accepts. Correspondingly, a higher threshold will reduce the FAR but increase
the FRR. A common variation is the Detection error trade-off (DET), which is
obtained using normal deviate scales on both axes. This more linear graph illuminates
the differences for higher performances (rarer errors).
 equal error rate or crossover error rate (EER or CER) – the rate at which both
accept and reject 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 most accurate.
 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.
  failure to capture rate (FTC) – Within automatic systems, the probability that the
system fails to detect a biometric input when presented correctly.
 template capacity – the maximum number of sets of data which can be stored in the
system.

TYPES:

Biometric security (identification) systems identify a human from a measurement of a physical

characteristic or behavioral trait (for example, hand geometry, retinal scan, iris scan, fingerprint
patterns, facial characteristics, DNA sequence characteristics, voice prints, and hand written
signature) to determine or verify an identity. There is typically an enrollment process in which
the biological information is taken and stored in a database for future identification or
verification.

Because biometric security technology relies on biological information about a person, it is

typically thought of as more reliable than other identification methods. There are several
different types of biometric security technologies:
1. FACIAL RECOGNITION

This technology identifies individuals by analyzing certain facial characteristics such as the
distance between the eyes, the length of the nose, and the angle of the jaw. Facial recognition
works for both verification and identification and is often used for surveillance purposes.

• Humans have always had the innate ability to recognize and distinguish between faces,
yet computers only recently have shown the same ability.

• Identix®, a company based in Minnesota, is one of many developers of facial recognition

technology. Its software, FaceIt®, can pick someone's face out of a crowd, extract the
face from the rest of the scene and compare it to a database of stored images. In order for
this software to work, it has to know how to differentiate between a basic face and the
rest of the background. Facial recognition software is based on the ability to recognize a
face and then measure the various features of the face.

• Every face has numerous, distinguishable landmarks, the different peaks and valleys that
make up facial features. FaceIt defines these landmarks as nodal points. Each human
face has approximately 80 nodal points.
Some of these measured by the software are:

– Distance between the eyes

– Width of the nose

– Depth of the eye sockets

 – The shape of the cheekbones

– The length of the jaw line

These nodal points are measured creating a numerical code, called a faceprint, representing the
face in the database.

2. FINGERPRINT RECOGNITION

This is the most widely used method of biometric authentication. Fingerprint recognition is based
on features found in the impressions made by unique ridges and valleys on the surface of a
human's fingertips.

• Fingerprints remain constant throughout life.

• In over 140 years of fingerprint comparison worldwide, no two fingerprints have ever
been found to be alike, not even in identical twins.

• Good fingerprint scanners have been installed in PDAs like the iPaq Pocket PC; so
scanner technology is also easy.

• Requires clean hands.

• Fingerprint identification involves comparing the pattern of ridges and furrows on the
fingertips, as well as the minutiae points of a specimen print with a database of prints on
file.

3. HAND GEOMETRY

This is based on the measurement and analysis of the shape of a person's hand. Unlike
fingerprints, the human hand is not descriptive enough for identification. However, it can be used
for verification by combining various individual features, such as width, height, and length of the
fingers, or distance between joints.

• Hands and fingers are unique -- but not as unique as other traits, like fingerprints or irises.

• Businesses and schools typically use hand and finger geometry readers to authenticate
users, not to identify them.

• Disney theme parks use finger geometry readers to grant ticket holders admittance to
different parts of the park.

• Systems that measure hand and finger geometry use a digital camera and light. You place
your hand on a flat surface, aligning your fingers against several pegs to ensure an
accurate reading. Then, a camera takes one or more pictures of your hand and the shadow
 it casts. It uses this information to determine the length, width, thickness and curvature of
your hand or fingers. It translates that information into a numerical template.

Strengths and Weaknesses

• Since hands and fingers are less distinctive than fingerprints or irises, some people are
less likely to feel that the system invades their privacy. However, many people's hands
change over time due to injury, changes in weight or arthritis.

4. IRIS RECOGNITION

This is the process of recognizing a person by analyzing the distinctly colored ring that surrounds
the pupil of the eye. With more than 250 unique characteristics, the iris is believed to go
unchanged throughout a person's lifespan. This technology is typically used for access control
into a facility.

• Iris scanning - at the heart of the system is a CCD digital camera. It uses both
visible and near-IR light to take a clear, high-contrast picture of an iris.

• The iris is a visible but protected structure, and it does not usually change over time.
Most of the time, people's eyes also remain unchanged after eye surgery, and
blind people can use iris scanners as long as their eyes have irises. Eyeglasses and
contact lenses typically do not interfere or cause inaccurate readings.

• When you look into an iris scanner, either the camera focuses automatically or you use a
mirror or audible feedback from the system to make sure that you are positioned
correctly. Usually, your eye is 3 to 10 inches from the camera. When the camera takes a
picture, the computer locates:

– The center of the pupil

– The edge of the pupil

– The edge of the iris

– The eyelids and eyelashes

It then analyzes the patterns in the iris and translates them into a code

5. RETINAL SCAN

This is the measuring of blood vessel patterns from the back of an eye. However, retinal
scanning is not yet readily available because some find this biometric system to be disturbing,
since it involves the person to stand very still while a light source is shined in their eye.

• Some people confuse iris scans with retinal scans.

 • Retinal scans, however, are an older technology that required a bright light to
illuminate a person's retina.
• The sensor would then take a picture of the blood vessel structure in the back of the
person's eye.
• Some people found retinal scans to be uncomfortable and invasive.
• People's retinas also change as they age, which could lead to inaccurate readings.
• Still used in some high security facilities.

6. VOICE RECOGNITION

Technology is a biometric security technology used to uniquely identify individuals based on the
different characteristics in their voice such as tone, pitch, cadence, etc. The system captures
samples of the individual's speech and then converts them to an electronic format to create a
biometric template.

7. SIGNATURE

Dynamic signatures are verified by measuring an individual's signature. This method of

biometrics studies the speed, direction, pressure and the total time it took for the person to create
the signature. As well this method can determine where the stylus was raised and lowered from
the writing surface.

8. KEYSTROKES

This method of biometrics examines a person's keystrokes on a keyboard. This method can
determine the speed, pressure, total time to type particular words and time between hits on
specific keys. This method is still in the development stage to improve robustness and
distinctiveness

9. VEIN GEOMETRY

• A person's veins are completely unique.

• Twins don't have identical veins, and a person's veins differ between their left and right
sides.
• Many veins are not visible through the skin, making them extremely difficult to
counterfeit or tamper with. Their shape also changes very little as a person ages.

Vein scanners use near-infrared light to reveal the patterns in a person’s veins.

• Place your finger, wrist, palm or the back of your hand on or near the scanner. A camera
takes a digital picture using near-IR light. The hemoglobin in your blood absorbs the
light, so veins appear black in the picture. Software creates a reference template based on
the shape and location of the vein structure.
 • Scanners that analyze vein geometry are completely different from vein
scanning tests that happen in hospitals.Vein scans for medical purposes
usually use radioactive particles.Biometric security scans use light that
is similar to the light that comes from a remote control.

Factors Cause Biometric Systems to Fail?

Biometric system performance varies according to sample quality and the environment in which
the sample is being submitted. While it is not possible to definitely state if a biometric
submission will be successful, it is possible to locate factors that can reduce affect system
performance.

Deformations

 Fingerprint

 Cold finger 
 Dry/oily finger 
 High or low humidity 
 Angle of placement 
 Pressure of placement 
 Location of finger on platen (poorly placed core) 
 Cuts to fingerprint 
 Manual activity that would mar or affect fingerprints (construction, gardening) 

 Voice recognition

 Cold or illness that affects voice

 Different enrollment and verification capture devices
 Different enrollment and verification environments (inside vs. outside)
 Speaking softly
 Variation in background noise
 Poor placement of microphone / capture device 
 Quality of capture device 
 Facial recognition

 Change in facial hair 

 Change in hairstyle 
 Lighting conditions 
 Adding/removing glasses 
 Change in weight 
 Change in facial aspect (angle at which facial image is captured)

 Iris-scan

 Too much movement of head or eye

 Glasses
 Colored contacts

 Retina-scan

 Too much movement of head or eye

 Glasses

 Hand geometry

 Jewelry
 Change in weight
 Bandages
 Swelling of joints

 Signature-scan

 Signing too quickly

 Different signing positions (e.g., sitting vs. standing)
Advantages
Biometric systems use the unique human characteristics of an individual. For this reason there is
an extremely low probability for two humans to share the same biometric data. Furthermore,
biometric characteristics of a person are near impossible to duplicate and can only be altered or
lost due to a serious accident. Biometrics has proven to be a secure method to ensure data
integrity, therefore, many banks, businesses and governments have incorporated biometrics as
part of their security procedures.

Disadvantages
There are two types of recognition errors, False Accept Rate (FAR) and False Reject Rate
(FRR). FAR is considered to be the most serious recognition error, which occurs when biometric
data does not match, but are accepted as a match by the system. FRR is when biometric data that
matches is rejected by the system. This recognition error can be caused by incorrect alignment or
dirt on scanner.