Novelty towards Highly Secured Personnel

licoricebedsSecurity

Feb 22, 2014 (3 years and 6 months ago)

65 views

393
Novelty towards Highly Secured Personnel
Authentication System by Blood Vessels

Valliappan Raman
Lecturer
Swinburne University of Technology
Sarawak Campus
Kuching Sarawak Malaysia
006082416353
vraman@swinburne.edu.my
Patrick Then
Lecturer
Swinburne University of Technology
Sarawak Campus
Kuching Sarawak Malaysia
006082416353
pthen@swinburne.edu.my


ABSTRACT
This paper explains about the blood vessel authentication system
that uses blood vessel patterns as a personal identifying factor.
The vessel information is very hard to replicate since vessels are
internal to the human body. The blood vessel authentication
technology provides high level of accuracy and delivers accurate
result.

Keywords
Blood Vessels, Recognition and Authentication.

1. INTRODUCTION

Biometric systems are based on the "certain" principal. These
systems rely on the principal that every human being is different.
In recent times biometric authentication has become a major
authentication system because it is one that is very hard to defeat.
Some countries already encode a traveler's fingerprint into their
passport documentation, and other countries are talking about
adding this feature. Biometrics can use not only fingerprints,
retina and facial scans for identification; they can also use voice
recognition as a form of authentication. Any part or feature of the
human body that is unique to each individual can theoretically be
used in an access control system.
Biometric systems can be used in two different modes. Identity
verification occurs when the user claims to be already enrolled in
the system (presents an ID card or login name); in this case the
verification biometric data obtained from the user is compared to
the users data already stored in the database. Identification (also
called search) identification occurs when the identity of the user is
a priori unknown. In this case the users biometric data is matched
against all the records in the database as the user can be anywhere
in the database or he/she actually does not have to be there at all.
It is evident that identification is technically more challenging and
costly. Identification accuracy generally decreases as the size of
the database grows. For this reason records in large databases are
categorized according to a sufficiently discriminating
characteristic in the biometric data. Subsequent searches for a
particular record identification are searched within a small subset
only. This lowers the number of relevant records per search and
increases the accuracy.
The current proposal describes a personal authentication system
using finger blood vessel information, which includes a finger
blood vessel characteristic data section for extracting person-to-
be-authenticated blood vessel characteristic data from a person-to-
be-authenticated finger blood vessel image; A Blood Vessel
Authentication System is a biometric access control device that
uses the unique image of the blood vessel pattern in a finger for
registration and authentication. The blood vessel image is created
using a permeating, near infrared light and a high resolution CCD
camera. Near-infrared light makes it possible to obtain the trans-
illumination image of the blood vessel pattern in the finger. An
algorithm extracts characteristic points from the digitized image to
achieve individual authentication against a stored registration
template. A one to seven digit PIN number is used to locate the
user's template in memory. Because vein patterns are next to
impossible to duplicate, the system can authenticate an individual
with a very low False Acceptance Rate.
Biometric authentication is basically divided into two types of
system. One is the system using physical characteristics (e.g.
finger print authentication, face detection and iris recognition
system) and other system using behavioral characteristics (e.g
signature recognition and authentication, handwriting
authentication). However, the former has a weakness for
replication because of using shapes of the living body, and later
has a problem with accuracy because there is a certain level of
error every time. In addition, both the type of authentication
system is generally large-sized and they spend a lot of costs,
which constrict the spread of these system.
In the present paper, a new biometric authentication system using
blood vessel is proposed. The system mainly focuses on template
matching and template creation to attain security. The paper is
organized as follows: The first section clearly explains the error
rates of the biometric authentication system; next section briefly
explains the existing works of the proposed system. In section 4
explains the methodology and working procedure of the proposed
394
system and then it explains implementation of the proposed
system in section 5. In section 6 it explains the feature and benefit
of the system. Finally future works and conclusion was made on
the last section 7.
2. Error Rates

There are two kinds of errors that biometric systems do:
1. False rejection (Type 1 error)  a legitimate us er is rejected
(because the system does not find the users current biometric data
similar enough to the master template stored in the database)

2. False acceptance (Type 2 error)  an impostor is accepted as a
legitimate user (because the system finds the impostors biometric
data similar enough to the master template of a legitimate user).

In an ideal system, there are no false rejections and no false
acceptances. In a real system, however, these numbers are non-
zero and depend on the security threshold. When there is higher
threshold, more false rejections and less false acceptances and the
lower the threshold there is less false rejections and more false
acceptances.

The number of false rejections/false acceptances is usually
expressed as a percentage from the total number of authorized/
unauthorized access attempts. In biometric systems, Error rates
are very important and manufacturers keenly concentrate on
security.

3. Existing Works

The blood vessel pattern authentication system is one of the most
accurate biometric authentication securities. Blood vessel patterns
are genetically determined, and unique to the individual. Lot of
new researches is focusing on this technology by advanced
countries. The idea is basically taken from some of the biometric
authentication techniques. One of the existing techniques is Palm
Vein authentication.
Palm vein authentication works by
comparing the pattern of veins in the palm of a person being
authenticated with a pattern stored in a database. According to
fujitsu research, vascular patterns are unique to each individual;
even identical twins have different patterns. And since the
vascular patterns exist inside the body, they cannot be stolen by
means of photography, voice recording or fingerprints, thereby
making this method of biometric authentication more secure than
others. Another existing research was on finger print recognition.
Fingerprint recognition is also known as image acquisition.
In this part of the process, a user places his or her finger on a
scanner. Numerous images of the fingerprint are then captured. It
should be noted that during this stage, the goal is to capture
images of the center of the fingerprint, which contains many of
the unique features. All of the captured images are then converted
into black and white images. Algorithms are mainly based on
template matching and template creation. Based on the existing
methods the idea is implemented in this paper.
4. Proposed Method

There are lots of biometric techniques available nowadays. A few
of them are in the stage of the research only (e.g. the odor
analysis), but a significant number of technologies is already
mature and commercially available (at least ten different types of
biometrics are commercially available nowadays: fingerprint,
finger geometry, hand geometry, palm print, iris pattern, retina
pattern, facial recognition, voice comparison and signature
dynamics. Our proposed biometric system is on highly secured
authentication system by blood vessels, its highly secured
compared to other authentication systems.
4.1 Blood Vessel authentication System
Finger Blood vessel recognition system is a technology that
verifies the identity of the person finger blood vessel based on the
fact that everyone has unique blood vessel in the finger parts. It is
one of the heavily used and active studies in biometric
technology.

4.1.1 How Finger Blood Vessel is captured
Using a permeating, high-resolution infrared CCD camera, data
on finger blood vessel patterns is photographed and registered. An
algorithm extracts characteristic points from the data to
accomplish individual authentication against the stored
registration template.


Figure 1 illustrates the capturing of finger blood vessels
through CCD camera




(a) (b)
Figure 2 illustrates the (a) hand image (b) finger blood vessel
image

395
Image
enhancement
Thinning
Vein Reconstruction
Blood Vessel
Extraction
Image Analysis
Binarization and
Compression
Matching
Global
Similarity
Local
Similarity
Vein
Analysis
4.1.2 Algorithm

To verify the identity of a user by automatically extracting blood
vessel from his or her finger blood vessel image, a finger blood
vessel recognition algorithm is required. The finger blood vessel
recognition algorithm is composed of two main technologies:
image processing technology that captures the characteristics of
the corresponding finger by having the image under-going several
stages, and matching algorithm technology that authenticates the
identity by comparing feature data comprised of blood vessel with
Templates in a database.






Fig 3 illustrates the image processing stages in Blood vessel
Authentication
This part consists of six stages. At the image enhancement stage,
noise on the input finger blood vessel image is eliminated and
contrast is fortified for the sake of successive stages. At the image
analysis stage, area where finger blood vessel is severely
corrupted is cut out to prevent adverse effects on recognition. The
binarization stage is designed to binarize a gray-level finger blood
vessel image and it is compressed. The thinning stage thins the
binarized image. The vessel reconstruction stage reconstructs the
veins in the blood vessel. At the last stage, blood vessel is
extracted from the reconstructed image.

After obtaining feature data of a specific finger blood vessel,
compare the corresponding user who is already stored in the DB
with Templates. If the finger blood vessel is immensely destructed
and only general vessel pattern, not single vessel, can be
recognized.

Matching stages show big differences according to their types
although they are based on the same blood vessel. Here, the most
well-known matching algorithm will be explained. The matching
process consists of four main stages. First of all, the blood vessel
analysis stage analyzes the geometric characteristics such as
distance and angle between standard veins and its neighboring
veins based on the analysis of the image-processed feature data.
After the analysis, all the vessel pairs have some kind of
geometric relationship with their neighboring vessels, and the
relationship will be used as basic information for local similarity
measurement. After the similarity measurement, a one to seven
digit PIN number is used to locate the user's template in memory.
Because vein patterns are next to impossible to duplicate, the
system can authenticate an individual with a very low False
Acceptance Rate.



Fig 4 illustrates the working procedure of blood vessel
authentication
5. Implementation of the Proposed System

The blood vessel authentication technology consists of image
sensing and software technology. The blood vessel sensor
captures an infrared ray image of the users finger. The lighting of
the infrared ray is controlled depending on the illumination
around the sensor, and the sensor is able to capture the blood
vessel image regardless of the position and movement of the
fingers. The software then matches the translated vessel pattern
with the registered pattern, while measuring the position and
orientation of the finger by a pattern matching method.
Implementation of a contactless identification system enables
applications in public places or in environments where hygiene
standards are required, such as in medical applications. In
addition, sufficient consideration was given to individuals who
are reluctant to come into direct contact with publicly used
devices.
6. Feature of the proposed system

The proposed system can focus on important features that include:
The blood vessel pattern is unique for each individual and even
identical twins have quite different patterns. It is postulated that
the no two vessel patterns are same, similar to that of iris
recognition, next feature is about the pattern of blood vessels are
individual specific and do not change with aging o r surface
effects. It can focus more on security and difficult to counterfeit.
Therefore the main benefit of the system is physiological burden
is less than other biometric technology. The system is to be
Start
Input
Image ID

Image
Compression

Correlation
Operation

Image
Processing

Compariso
Reject

Low

Approved
Stop
Read in
Registered
Image
396
implemented on matlab. Based on the experimental results, system
accuracy can be noted and it helps to enhance the system.

7. Conclusion and Future works

Blood vessel authentication system offer contactless
authentication and provides a highly secured solution, thus
promising a high-level of user acceptance. Blood vessels are
extremely difficult to duplicate and therefore contributes to a high
level of security. The info structure of the paper clearly explains
the blood vessel authentication system. Future, technology can
support in wide range of applications.

















8. REFERENCES

[1]. Bio-informatics Visualization Technology committee, Bio-
informatics Visualization Technology, Corona Publishing,
1997.
[2]. K.Karu, A.K Jain, Fingerprint Classification, Pattern
Recognition 29(30, 1996.
[3]. A. Senior, A combination fingerprint classifi er, IEEE Tran
Pattern Anal. Mach. Intel. 23(10), 2001.
[4] http://www.biometricaccess.com/