 |
| |
 |
 |
| |
 |
|
 Advantages |
Since fingerprints are the
composition of protruding sweat glands, everyone has unique
fingerprints.
They do not change naturally.
Its reliability and stability is higher compared to
the iris, voice, and face recognition
method.
Fingerprint recognition equipment is relatively
low-priced compared to other biometric system and R&D
investments are very robust in this field. |
|
| Disadvantages |
Vulnerable to noise and
distortion brought on by dirt and twists.
Some people
may feel offended about placing their fingers on the same
place where many other people have continuously
touched.
Some people have damaged or eliminated
fingerprints. |
| |
 |
| There are two main types of sensors for inputting
fingerprints. One is an optical sensor using a prism or
hologram, and the other type is a non-optical sensor.
Recently, products employing both optical and non-optical
methods have been introduced. In the past, a semiconductor
sensor was the only non-optical choice, but now equipment with
ultrasonic sensors, another type of non-optical sensors, are
on the market. |
|
| Optical Fingerprint Sensor |
| Absorption |
| Figure 5.1 explains the basic
principle of absorption in an optical fingerprint
sensor. |
|
| * Figure
5.1 Principle of Absorption in Fingerprint Sensor |
 |
|
An absorption optical
fingerprint sensor is composed of a right-angled triangle
prism (4), light source (20),
a diffusion plate (3), a lens
group and an image sensor (6).
When a fingerprint is
placed on the contact surface, its ridges are closely pressed
onto the surface while its valleys are detached from
it.
The light radiated from light source becomes uniform
after undergoing the diffusion plate. The light reaches the
fingerprint contact surface after passing through the prism.
If the light touches the valley, total internal reflection
happens so that it reaches the image sensor composed of CCD
(Carge Coupled Device) element or CMOS (Complementary Metal
Oxide Semiconductor) element after going through the lens
group. On the other hand, if the light reaches the ridges
closely pushed onto the surface, some light goes to the image
sensor after the total internal reflection and some light is
absorbed in the ridges.
There are changes in luminous
intensity between light reflected from valleys and light from
ridges and the image sensor obtains the fingerprint image by
calculating the changes in the reflected light intensity
between the two.
The absorption optical fingerprint sensor
needs several LEDs (15-20) since the light should be
two-dimensionally uniform after going through the diffusion
plate. To capture a fingerprint image without distortion
brought on by different optical paths, enough distance is
required between the prism and the image sensor. |
 |
| Scattering |
| * Figure
5.2 Principle of scattering fingerprint sensor |
 |
|
The scattering optical
fingerprint sensor is mainly comprised of a
rectangular-triangle prism (13), light source (20), a lens
group (15), and an image sensor (16). When a fingerprint
is placed on the contact surface, its ridges are closely
pressed onto the surface while its valleys are detached from
it.
The light radiated from the source passes through the
prism and reaches the surface. The light perpendicularly goes
through the surface unlike the absorption sensor. If the light
reaches the valleys, it goes through the surface, radiating to
the outside. If it touches upon the ridges, scattering happens
at the ridges. The scattered light gets to the image sensor
composed of CCD or CMOS element through the lens group. The
light radiated to outside near the valleys seldom reaches the
image sensor. Only the scattered light near the ridges gets to
the sensor. As a result, a fingerprint image can be captured
since the valley area is dark and the ridge area is
bright.
The scattering optical fingerprint sensor doesn't
need a diffusion plate and its contrast is great. However, it
needs the rectangular prism, more expensive than the triangle
prism. |
|
|
| Semiconductor Fingerprint
Sensor |
| A semiconductor fingerprint
sensor is a prime example of non-optical sensors. Figure 5.3
shown below describes the basic principle of the semiconductor
fingerprint sensor. |
|
| * Figure
5.3 Basic principle of the semiconductor fingerprint sensor |
 |
The semiconductor fingerprint sensor
measures the electrostatic capacity between sensor
surface and skin, and translates it into an image. If a
user places his or her fingerprint on the surface, its
ridges are closely pressed on the surface and its
valleys have some space from the surface. In the case of
the ridges, the distance (d) between ridges and surface
is short so that the electrostatic capacity is high. On
the other hand, the valleys are distant from the surface
compared to the ridges, so the electrostatic capacity is
low. |
|
|
| The fingerprint image can be
captured by composing signals obtained from an array of
sensors on the semiconductor surface. The semiconductor
fingerprint sensor can be lighter and smaller. But it is
vulnerable to external shocks and chemical substances such as
sodium chloride from people's skin due to the physical traits
of a silicon wafer, which is fundamental to the sensor. To
address these disadvantages, the contact surface is being
coated. Developing a physically strong coating is one of the
major tasks facing semiconductor fingerprint sensors. |
|
| * Table
5.1 Comparison between optical and non-optical methods |
| Classification |
Optical |
Non-optical |
| Recognition means |
Light |
Pressure, heat, contact, static
electricity, ultrasound |
| Advantages |
Very safe. High perception rates. Strong
against external shocks and scratch. |
Impossible to duplicate. Able to
minimize the size. Low production and maintenance
costs. |
| Disadvantages |
Relatively big module. High production
and maintenance costs. |
Sensitive to environmental changes such
as static electricity and
temperatures. |
|
|
| |
 |
|
As shown in Figure 5.4 below,
the flows of the black lines are called ridges. Space
between the nearing ridges is called a valley. The flows
of the ridges that continue or are divided constitute a
particular finger-
print. An ending point is the
point at which a ridge ends, and a bifurcation point is
the point at which a ridge is divided into two ridges.
These points are called minutiae and are really
important information for the classification of an
automatic fingerprinting system. There are also other
important points for bulk fingerprinting DB:a core point
at which the highest or lowest ridge is shown and a
delta where three ridges
from three different
directions converge.
Figure 5.4 shown below displays
the minutiae on an actual fingerprint image. |
|
* Figure 5.4
Minutiae in the actual fingerprint
image |
|
|
| |
 |
|
To verify the identity of a user by automatically
extracting minutiae from his or her fingerprint image, a
fingerprint recognition algorithm is required. The fingerprint
recognition algorithm is composed of two main technologies:
image processing technology that captures the characteristics
of the corresponding fingerprint by having the image
under-
going several stages, and matching algorithm
technology that authenticates the identity by comparing
feature data comprised of minutiae with Templates in a
database.
Figure 5.5 shown below explains the overall block
map of the fingerprint recognition algorithm consisting of the
two technologies. |
|
| * Figure 5.5 Block map of the
fingerprint recognition algorithm consisting of the two
technologies |
 |
|
| Image
Processing |
| This part consists of six
stages. At the image enhancement stage, noise on the input
fingerprint image is eliminated and contrast is fortified for
the sake of successive stages. At the image analysis stage,
area where fingerprint is severely corrupted is cut out to
prevent adverse effects on recognition. The binarization stage
is designed to binarize a gray-level fingerprint image. The
thinning stage thins the binarized image. The ridge
reconstruction stage reconstructs the ridges by removing
pseudo minutiae. At the last stage, minutiae are extracted
from the reconstructed ridge image. |
|
 |
|
| Matching |
| After obtaining feature data of
a specific fingerprint, compare the corresponding user who is
already stored in the DB with Templates. If the fingerprint is
immensely destructed and only general ridges, not minutiae,
can be recognized, two algorithms can be used in parallel: an
algorithm based on minutiae and an algorithm based on the
overall ridge shape. |
|
 |
|
Matching stages show big
differences according to their types although they are based
on the same minutiae. Here, the most well-known matching
algorithm will be briefly explained. The matching process
consists of four main stages. First of all, the minutiae
analysis stage analyzes the geometric characteristics such as
distance and angle between standard minutiae and its
neighboring minutiae based on the analysis of the
image-processed feature data. After the analysis, all the
minutiae pairs have some kind of geometric relationship with
their neighboring minutiae, and the relationship will be used
as basic information for local similarity
measurement.
In Figure 5.7, picture (a) shows feature
data of the input fingerprint, and (b) shows the already
stored Template.
Finding a similar minutiae pair in (b)
against a minutiae pair in (a) is the local similarity
measurement.
Global similarity measurement means
calculating similarity of two fingerprints by finding minutiae
pairs in the local similarity measurement in both feature data
and selecting the greatest matching minutiae pairs in the
feature data.
Lastly, calculating final matching scores
with the global similarity value and comparing them with the
previously set critical value verifies the identity of the
user. |
|
|
