Beruflich Dokumente
Kultur Dokumente
2. Block Diagram:
1. Introduction
Recently while us discussing about
Biometrics we are concentrating on
Fingerprint scanning. For this we are using
FIM 3030N high voltage module as a scanner.
This module has in-built ROM, DSP and
RAM. In this we can store up to n no of
users fingerprints. This module can operate in
2 modes they are Master mode and User
mode. We will be using Master mode to
register the fingerprints which will be stored
in the ROM present on the scanner with a
unique id.
978-1-4673-5584-1/12/$31.002012 IEEE
IEEE-ICoAC 2012
3. Sensor:
In this we are using U 4000B
sensor for getting the Fingerprint image and to
store that in the database. It is an excellent
fingerprint input device can be widely applied
in social security, public security, attendance,
fingerprint encryption, embedded, and many
other applications.
U 4000B miniature
fingerprint scanner to automatically read the
fingerprint image, and through USB interface
to transfer digital fingerprint images to the
computer-controlled technology to support the
Biokey SDK development tools. Require
authentication for laptop computers, desktop
computer or other personal computing
devices, it is the ideal accessory.
U 4000B
3.1. Sensing:
Fingerprints can be sensed
using numerous technologies. The traditional
ink and paper method, still used by many
law enforcement agencies, involves applying
ink to the finger surface, rolling the finger
from one side of the nail to the other on a
card, and finally scanning the card to generate
a digital image.
In the more popular live-scan method,
a digital image is directly obtained by placing
the finger on the surface of a fingerprint
reader as shown in Figure 2. Optical sensors
based on the frustrated total internal reflection
(FTIR) technique are commonly used to
capture live-scan fingerprints in forensic and
government applications, while solid-state
IEEE-ICoAC 2012
pores, edge contour, and other details,
including incipient ridges, creases, and scars.
Level 1 features can be used to
categorize fingerprints into major pattern
types such as arch, loop, or whorl; level 2 and
level 3 features can be used to establish a
fingerprints individuality or uniqueness.
Higher-level features can usually be extracted
only if the fingerprint image resolution is
high. For example, level 3 feature extraction
requires images with more than 500-ppi
resolution.
Figure 3b shows the flow chart of a
typical minutiae feature extraction algorithm.
First, the algorithm estimates the friction ridge
orientation and frequency from the image.
4. How the fingerprint is recognized and
stored in the database:
During the enrollment phase, the
sensor scans the users fingerprint and
converts it into a digital image. The minutiae
extractor processes the fingerprint image to
identify specific details known as minutia
points that are used to distinguish different
users.
(a)
(b)
(c)
(d)
IEEE-ICoAC 2012
image (c) and at last the minutiae (d) is
matched and stored in the database.
6. Matching:
A fingerprint matching module
computes a match score between two
fingerprints, which should be high for
fingerprints from the same finger and low for
those from different fingers. Fingerprint
matching is a difficult pattern-recognition
problem due to large intraclass variations
(variations in fingerprint images of the same
finger) and large interclass similarity
(similarity between fingerprint images from
different fingers). Intraclass variations are
caused by finger pressure and placement
rotation, translation, and contact areawith
respect to the sensor and condition of the
finger such as skin dryness and cuts.
Meanwhile, interclass similarity can be large
because there are only three types of major
fingerprint patterns (arch, loop, and whorl).
Most fingerprint-matching algorithms
adopt one of four approaches: image
correlation,
phase
matching, skeleton
matching, and minutiae matching. Minutiaebased representation is commonly used,
primarily because
Forensic examiners have successfully
relied on minutiae to match fingerprints for
more than a century,
Minutiae-based representation is
storage efficient, and expert testimony about
suspect identity based on mated minutiae is
admissible in courts of law.
The current trend in minutiae matching
is to use local minutiae structures to quickly
find a coarse alignment between two
fingerprints and then consolidate the local
matching results at a global level. This kind of
matching algorithm4 typically consists of four
steps, as Figure 4 shows. First, the algorithm
computes pair wise similarity between
minutiae of two fingerprints by comparing
minutiae descriptors that are invariant to
rotation and translation. Next, it aligns two
fingerprints according to the most similar
IEEE-ICoAC 2012
6.1. How it matches with the stored image
6.1.1. Sensors identification process:
IEEE-ICoAC 2012
7. How to over come Duplication:
7.1. Altered/fake fingerprints:
People may alter their fingerprints in
different ways for many reasons. For example,
an unauthorized user may use a fake finger
that imitates a legitimate users fingerprint
template to access a computer system.
Criminals may cover their fingers with fake
fingerprints made of substances like glue or
they may intentionally mutilate their fingers to
avoid being identified by automated systems
or even human experts.
An essential countermeasure to thwart
the use of inanimate or fake fingers is liveness
detectionchecking if the finger is live by
measuring and analyzing various vital signs of
the finger such as pulse, perspiration, and
deformation. While software-based liveness
detection solutions that complement existing
fingerprint scanners may be more costeffective, they have not yet shown much
promise.
To deal with mutilated fingers, a
mutilation detector should be added, and, once
mutilation is detected, effort should be made
to identify the subject either by restoring the
original fingerprints or using only the
unaltered areas of the fingerprint. With the
adoption of multiple biometric traits in largescale identification systems such as the FBIs
NGI, multi-biometrics will be a powerful tool
to handle altered fingerprints.
Duplication can be avoided since each and
every Fingerprint has its uniqueness in
nature
IEEE-ICoAC 2012
threshold quality) templates and hence will
help to avoid false matches in the future.
Attention should be paid to the
sensor surface as the eye of the system. It
should not be touched or scratched with dirty
fingers or anything hard. If the sensor is dirty,
wet, or fails to work, it should be gently
cleaned with a dry, soft, lint-free cloth.
If someone has difficulty enrolling or
authenticating, the hands should be cleaned or
a different finger used. If the hands are too
dry, lotion can be applied, but not too much
because that can have the opposite effect. If
appropriate, the user might rub the finger to be
matched on his or her forehead to moisten it
with the skins natural oil.
8.4. Collectability:
Fingerprints are easy to
acquisition, the cheapest fingerprint readers
available use a digital camera. Fingerprint
readers that are more difficult to fool, such as
CMOS readers, are even not overly expensive.
In some environments, where for example
people are unable to wash their hands, more
expensive means might be necessary to
acquire a useable fingerprint image.
8.5. Acceptability:
Fingerprints
are
easily
accepted as soon as people reflect that they
leave their fingerprints everywhere and that no
sensitive information, such as medical
conditions, can be derived from fingerprints.
8.6. Circumvention:
There are a number of
concerns when using fingerprint recognition.
8.1. Universality:
Only very few people miss all
10 fingers. Most fingerprint recognition
software allows enrolling multiple fingers
which avoids that an individual is no longer
granted access after injury.
8.2. Uniqueness:
It is generally accepted that
fingerprints are unique to an individual.
However, there is a risk that fingerprints of
two different individuals match if the
fingerprint image is of insufficient quality.
Therefore the False Acceptance Rate (FAR) is
highly dependent on the quality of the
fingerprint reader.
8.3. Permanence:
Fingerprints do not change with
ageing, but as people age they lose collagen
which makes their fingerprint harder to read
and this can lead to significantly more false
rejects with elderly people. Injuries, such as
fire wounds, can damage a fingerprint but if
multiple fingers are enrolled the likelihood of
an authorized individual being denied access
is reduced.
Make
a
thorough
analysis
before
implementing fingerprint recognition as a
means for authentication or identification in a
high securityenvironment. Avoid
using
fingerprint
readers
without
liveliness
detection.
IEEE-ICoAC 2012
8.7. Performance:
In terms of speed, accuracy and
robustness the devices actually on the market
should cover any need, except maybe for big
corporations and government applications
where matching algorithms might become a
bottleneck.
9. Some of the advantages of our proposed
Method:
1. Since fingerprints are the composition
of protruding sweat glands, everyone
has unique fingerprints.
2. They do not change naturally.
3. Its reliability and stability is higher
compared to the iris, voice, and face
recognition method.
4. Fingerprint recognition equipment is
relatively low-priced compared to
other biometric system and R&D
investments are very robust in this
field.
5. Very high accuracy.
6. It is one of the most developed
biometrics.
7. Easy to use.
8. Small storage space required for the
biometric template, reducing the size
of the database memory required
9. It is standardized.
10. No need to carry License
11. It avoids Fraud & Duplication.
12. More economical and effective
method.
10. Conclusion:
Automated
fingerprint
identification systems
have
been
successfully deployed around the globe
for both law-enforcement and civilian
applications, and new fingerprintmatching applications continue to
emerge. The fingerprint will continue to
be the dominant biometric trait, and many
identity management and access control