Fingerprint Recognition
INTRODUCTION
DEFINITION
Your fingerprints are like unique keys you carry everywhere. In theory, no-one else has
the same prints as you. Fingerprint recognition refers to the automated method of
identifying or confirming the identity of an individual based on the comparison of two
fingerprints. Fingerprint identification is popular because of ease of acquisition and the
numerous sources (ten fingers) available for collection. Fingerprints are usually
considered to be unique, with no two fingers having the exact same dermal ridge
characteristics.
BACKGROUND
The analysis of fingerprints for matching purposes generally requires the comparison of
several features of the print pattern. These include patterns, which are aggregate
characteristics of ridges, and minutia points, which are unique features found within the
patterns. A swipe reader has a small contact surface over which you swipe your
fingerprint. On a touch reader you just have to press and release your finger. In
general touch readers are easier to use whereas swipe readers require a bit of practice
the first times the device is used.
Basic patterns
There are three basic patterns of fingerprint ridges. An arch is a pattern where the
ridge enters one side of the finger, then rises in the centre forming an arch, and exits
on the other side of the finger. With a loop the ridge enters one side of the finger, then
forms a curve, and exits on the same side of the finger from which it entered. Finally
a whorl is the pattern
you have
when ridges form
circularly
around a central point.
Loop pattern
Minutiae features (points)
Arch pattern
Whorl pattern
Minutiae refer to specific points in a fingerprint, these are the small details in a
fingerprint that are most important for fingerprint recognition. There are three major
types of minutiae features: the ridge ending, the bifurcation, and the dot (also called
short ridge). The ridge ending is, as indicated by the name, the spot where a ridge
ends. A bifurcation is the spot where a ridge splits into two ridges. Spots are those
fingerprint ridges that are significantly shorter than other ridges.
TYPE OF BIOMETRIC
Fingerprint Recognition is a physiological/physical type of biometric. Physiological
identifiers provide more accuracy because usually they remain the same through the
years.
How does fingerprint biometrics work?
There are two main matching algorithm families to recognize fingerprints:
Pattern matching compares the overall characteristics of the fingerprints, not only
individual points. Fingerprint characteristics can include sub-areas of certain interest
including ridge thickness, curvature, or density. So basically the patterns described
above such as the arch, loop and whorl and other ridge features are extracted and
matched against the stores templates. During enrolment, these small sections of the
fingerprint and their relative distances are extracted from the fingerprint then
sophisticated pattern-matching software is used to turn it into a code.
Minutia matching compares specific details within the fingerprint ridges. At
registration (also called enrolment), the minutia points are located, together with their
relative positions to each other and their directions. At the matching stage, the
fingerprint image is processed to extract its minutia points, which are then compared
with the registered template stored in the database.
The Authentication Process (Steps) - know first
sentences
1) Sensor module, which captures the biometric data of an individual. An example is a
fingerprint sensor that images the ridge and valley structure of a users finger.
2) Feature extraction module, in which the acquired biometric data is processed to
extract a set of salient or discriminatory features. For example, the position and
orientation of minutiae points in a fingerprint image are extracted in the feature
extraction module of a fingerprint-based biometric system.
3) Matcher module, in which the features extracted during recognition are compared
against the stored templates to generate matching scores. For example, in the
matching module of a fingerprint-based biometric system, the number of matching
minutiae between the input and the template fingerprint images is determined and a
matching score is reported. The matcher module also encapsulates a decision making
module, in which a users claimed identity is confirmed (verification) or a users identity
is established (identification) based on the matching score.
4) System database module, which is used by the biometric system to store the
biometric templates of the enrolled users. The enrolment module is responsible for
enrolling individuals into the biometric system database. During the enrolment phase,
the biometric characteristic of an individual is first scanned by a biometric reader to
produce a digital representation of the characteristic. In order to facilitate matching,
the input digital representation is further processed by a feature extractor to generate
a compact but expressive representation, called a template. Depending on the
application, the template may be stored in the central database of the biometric
system or be recorded on a smart card issued to the individual. Usually, multiple
templates of an individual are stored to account for variations observed in the biometric
trait and the templates in the database may be updated over time.
Hardware (readers)
1. Optical readers are the most common type of fingerprint readers. The type of
sensor in an optical reader is a digital camera that acquires a visual image of the
fingerprint. Advantages are that optical readers start at very cheap prices.
Disadvantages are that readings are impacted by dirty or marked fingers, and
this type of fingerprint reader is easier to fool than others.
2. Capacitive readers, also referred to as CMOS readers, do not read the
fingerprint using light. Instead a CMOS reader uses capacitors and thus electrical
current to form an image of the fingerprint. CMOS readers are more expensive
than optical readers. An important advantage of capacitive readers over optical
readers is that a capacitive reader requires a real fingerprint shape rather than
only a visual image. This makes CMOS readers harder to trick.
3. Ultrasound readers use high frequency sound waves to penetrate the
epidermal (outer) layer of the skin. They read the fingerprint on the dermal skin
layer, which eliminates the need for a clean, unscarred surface. This type of
fingerprint reader is far more expensive than the first two, however due to their
accuracy and the fact that they are difficult to fool the ultrasound readers are
already very popular.
4. Thermal readers sense, on a contact surface, the difference of temperature in
between fingerprint ridges and valleys. Thermal fingerprint readers require a
swipe across the surface. They have a number of disadvantages such as higher
power consumption and a performance that depends on the environment
temperature.
Hardware Requirements
Sensors are used to collect the digital image of a fingerprint surface. (various types
described above). May also be used to store templates.
Tokens for systems that store biometric templates on tokens rather than being stored
on central database.
Individual workstations for storing templates that are not stored on central database.
Software
The two main categories of fingerprint matching techniques are minutiae-based
matching and pattern matching. Pattern matching simply compares two images to see
how similar they are. They compare those patterns described above like the arch, loop
and whorl in the two images. Pattern matching is usually used in fingerprint systems to
detect duplicates. The most widely used recognition technique, minutiae-based
matching, relies on the minutiae points described above, specifically the location and
direction of each point.
Software Requirements
Software solutions provided by software development companies. For example,
DigitalPersona Fingerprint Reader Software.
Pattern-matching software
The advantages include:
AcceptanceAs most people are familiar with the use of fingerprinting for
identification purposes, it is generally accepted as a technology. Most people
understand its applicability to access control.
AccuracyBy and large, fingerprint technology is accurate. There is a small chance
of rejection of a legitimate print, i.e., there is a chance of accepting a false print or a
chance of rejecting a legitimate print. The chances of accepting a false print are very
low.
Ease of useVery little time is required for enrolment with a fingerprint scanning
system. Unlike other biometric devices, such as retina scanners, fingerprint scanners do
not require concentrated effort on the part of the user. Accordingly, one could consider
fingerprint scanning to be relatively nonintrusive.
InstallationChanges in technology have made fingerprint scanners relatively easy
to install and inexpensive. Most fingerprint scanners are now very small and portable.
Plug-and-play technologies have made installation very easy. In many cases, the
scanning device has been incorporated into keyboards, mouse buttons and even
notebook computers.
TrainingDue to the intuitive nature of scanning fingerprints, such devices require
no training to use and little training to support.
UniquenessAs noted previously, fingerprints are a unique identifier specific to the
individual.
SecurityFingerprints cannot be lost or stolen, and are difficult to reproduce.
Furthermore, storing fingerprint templates as statistical algorithms rather than
complete copies ensures that the ability to reproduce these unique identifiers is
significantly reduced.
The disadvantages include:
AcceptanceAlthough also an advantage, user acceptance is not guaranteed.
Fingerprint scanning crosses the fine line between the impersonal and nonintrusive
nature of passwords and personal identification numbers (PINs), and utilising part of an
individuals body to identify him/her. Some people view this as an invasion of
privacy or worse.
InjuryInjury, whether temporary or permanent, can interfere with the scanning
process. In some cases reenrolment is required. For example, bandaging a finger for a
short period of time can impact an individual if fingerprint scanning is used in a wide
variety of situations. Something as simple as a burn to the identifying finger could
prevent use of an automatic teller machine (ATM).
SecurityAs some authors have argued, there is nothing to suggest that the same
technology that is used to store fingerprints as statistical algorithms cannot
also be used or modified to recreate accurate depiction of the print itself. This
raises serious concerns related to how such data should be stored, maintained and
protected to prevent fraudulent use.
It can make mistakes with the dryness or dirty of the fingers skin, as well as with the
age (is not appropriate with children, because the size of their fingerprint changes
quickly).
People with no or few minutia points (surgeons as they often wash their hands with
strong detergents, builders, and people with special skin conditions) cannot enrol or use
the system.
Advantages over other biometrics:
-
Faster enrolment than with retina scanning
Does not require a lot of memory to store templates as with iris scanning
Easier to use than retina scanning which requires a well trained personnel
Cheaper equipment than many other biometrics and a wider variety of
fingerprint solutions available
Application
How it is used:
Fingerprint recognition systems are now pervasive in our daily life. Disney Parks, for
example, captures fingerprints of visitors when they initially enter the park to link the
ticket to the ticket holders fingerprint. Fingerprint verification is performed whenever
the same 5 ticket is presented for reuse to prevent fraudulent use of the ticket (e.g.,
sharing of a ticket by multiple individuals). Many automated teller machines (ATMs) in
Brazil use fingerprint recognition as a replacement for personal identification numbers
(PINs). Also, several laptop computer models are equipped with fingerprint sensors and
authenticate users based on their fingerprints.
Logical access control, for example there exist numerous fingerprint reader
devices and softwares for access control to personal computers
Physical access control, for example locks with a fingerprint reader
Fingerprint attendance systems for time and attendance management
Biometric alternative to loyalty card systems
Fingerprint sensors are best for devices such as cell phones, USB flash drives, notebook
computers and other applications where price, size, cost and low power are key
requirements.
Major corporations/groups that use it:
Fingerprint biometric systems are also used for law enforcement, background searches
to screen job applicants, healthcare, banks and welfare.
SECURITY EVALUATION
Accuracy
False Acceptance Rate (FAR) and False Rejection Rate (FRR) are too dependent on the
device, the software implementation and on how the system is used. Therefore we
cannot generalize this.
The False Acceptance rate (FAR) is the probability that the system incorrectly authorizes
a non-authorized person, due to incorrectly matching the biometric input with a
template.
The FRR or False Rejection Rate is the probability that the system incorrectly rejects
access to an authorized person, due to failing to match the biometric input with a
template.
To analyze the performance of a fingerprints recognition system is to collect a large
number of matching scores from the same finger and a large number of matching
scores from by different fingers.
AccuracyBy and large, fingerprint technology is accurate. There is a small
chance of rejection of a legitimate print, i.e., there is a chance of accepting a
false print or a chance of rejecting a legitimate print. The chances of
accepting a false print are very low.
Attacks on Fingerprint Recognition
These vulnerability points, depicted in the Fig. above, can broadly be divided into two
main groups:
Direct attacks
These attacks at the sensor level are referred to as direct attacks. It is worth noting that
in this type of attacks no specific knowledge about the system is needed (e.g. matching
algorithm used, feature extraction, feature vector format, etc.).
Examples of attacks on Sensors:
-
Fingerprint Spoofing: Making a dummy finger
Fingerprint obfuscation (or alteration) by abrading, cutting, burning, or
performing plastic surgery on fingertips in order to conceal ones identity for
specific purposes
reactivating latent prints on touch sensors
o capacitive: aspirate, graphite
o optical: coloured powder
Indirect attacks.
This group includes all the remaining seven points of attack identified in the Fig. above.
Attacks 3 and 5 might be carried out using a Trojan Horse that bypasses the feature
extractor, and the matcher respectively. In attack 6 the system database is
manipulated (e.g., a template is modified, added or deleted) in order to gain access to
the application. The remaining points of attack (2, 4, 7 and 8) are thought to exploit
possible weak points in the communication channels of the system, extracting, adding
or changing information from them. In opposition to direct attacks, in this case the
intruder needs to have some additional information about the internal working of the
recognition system and, in most cases, physical access to some of the application
components (feature extractor, matcher, database, etc.) is required.
SAFEGUARDS AGAINST ATTACKS
-
A simple, but effective solution is to block matching attempts if there are too
many false matches in a given period of time (e.g., it is highly unlikely that a
legitimate user can provide more than, say, 20 false matches per day).
Smart cards (multifactor authentication)
Liveness detection - Special finger scanners can measure the temperature or
conductivity of the skin to ensure it is presented by a living person.
