Beruflich Dokumente
Kultur Dokumente
Abstract-- Authentication is a fundamental issue to any trust- matching and Iris recognition. A biometric system is
oriented computing system and also a critical part in many essentially a pattern recognition [4] system which makes a
security protocols. In addition, authentication also serves as personal identification by determining the authenticity of a
the first step for many other security purposes, such as key specific physiological or behavioural characteristics possessed
management and secure group communication [5]. by the user. Depending on the context, a biometric system can
Passwords or smartcards have been the most widely used be either a verification (authentication) [8] system or an
authentication methods due to easy implementation and identification system. The current security model for
replacement; however, memorizing a password or verification of identity, protection of information and
carrying a smartcard, or managing multiple authentication to access data or services is based on using a
passwords/smartcards for different systems (one for each token or password, tied to and thereby representing an
system),is a significant overhead to users. In addition, they individual to either authenticate identity or allow access to
are artificially associated with users and cannot truly information [Annet al, 2007]. This token may be password or
identify individuals Performing authentication is notoriously shared secret (something you know), an identity card
difficult. Biometrics has been widely used and adopted as a (something you have) or biometric (something you are). In all
promising authentication [8] method due to its advantages over this cases, the details of the token are held by a third party
some existing methods, particularly, its resistance to losses whose functions is to authorizes and at times allow the
incurred by theft of passwords and smart cards. However, transaction to proceed if the details of an individual’s token
biometrics introduces its own challenges, Such as being match those stored in a database.
irreplaceable once compromised. Biometrics can be used to
By using biometrics it is possible to establish an identity
prevent unauthorized access to ATMs, cellular phones, smart
cards, desktop PCs, workstations, and computer networks. It can based on who you are, rather than by what you possess, such
be used during transactions conducted via telephone and internet as an ID card, or what you remember, such as a password.
(electronic commerce and electronic banking). In some applications, biometrics may be used to supplement
ID cards and passwords thereby imparting an additional level
Keywords: ARM7 (LPC2148), RFID, Fingerprint module, pc cam, of security. Such an arrangement is often called a dual-factor
keypad, buzzer, DC motor authentication scheme.
1. INTRODUCTION 1.1 EXISTING SYSTEM
Biometrics refers to the automatic identification of a person Present in existing system the person who ever wants to
based on his/her physiological or behavioural characteristics. access his things or take his amount from Bank Lockers or
This method of identification [1] is preferred over traditional ATM,s first of all he has to show his id card in front of the
methods involving passwords and PIN numbers for various card accessing machine. If the card is valid then he wants to
reasons: the person to be identified is required to be physically enter the password in a particular machine. If the password is
present at the point-of identification; identification based on correct then only the locker system will be opened otherwise
biometric techniques obviates the need to remember a it will not be opened, or he can draw the amount from
password or carry a token. With the increased use of particular machine. So likewise the person can access his
computers as vehicles of information technology, it is things from bank lockers.
necessary to restrict access to sensitive/personal data. By Not only in banking systems for suppose in military areas
replacing PINs, biometric techniques can potentially prevent also only authorized persons have to enter in that secure area
unauthorized access [8] to or fraudulent use of ATMs, cellular that means the area will be restricted. The authorized persons
phones, smart cards, desktop PCs, workstations, and computer those who wants enter in that restricted area first of all he
networks. PINs and passwords may be forgotten, and token wants to show his id card in front of the card accessing
based methods of identification like passports and driver's machine, if it is valid card then the person will have to enter
licenses may be forged, stolen, or lost. Thus biometric the password, if it is valid password then only the door will be
systems of identification are enjoying a renewed interest. opened otherwise it will not be opened.
Various types of biometric systems [1] are being used for real-
time identification; the most popular are based on fingerprint
170
Global Journal of Advanced Engineering Technologies, Vol1,Issue3-2012
Vol1,Issue3 ISSN : 2277-6370
1.2 DISADVANTAGES OF EXISTING SYSTEM pattern. The captured image is called a live scan. This live
• If the person’s ID card and the password are stolen by his scan is digitally processed to create a biometric template (a
colleagues or family members then the things will be stolen in collection of extracted features)) which is stored and used for
the existing system. matching.
By using authorized person’s identity card some other person
•By 4) Keys Section: With the help of these keys the users can
will enter in that particular authorized areas or restricted area enrol their Finger prints and they will
w enter the password.
in military. 5) PC Cam Section: This section is basically meant to capture
the IRIS of the persons and to transfer this captured IRIS for
2. PROPOSED SYSTEM STRUCTURE AND PROTOTYPE Processing.
DESIGN 6) IRIS: In this we are using the Iris recognition technique.
Iris recognition analyses the features that exist in the colored
tissue surrounding the pupil, which has 250 points used for
comparison, including rings, furrows, and freckles. Iris
recognition uses a regular video camera system and can be
done from further away than a retinal scan. It has the ability to
create an accurate enough measurement that can be used for
Identification purposes, not just verification.
7) Buzzer: This is the output device which we are using to
indicate the unauthorized person.
8) LOCKER SYSTEM: Here we are demonstrating demo a DC
motor as the Locker for the authorized persons in the Locker
system mode.
B. Building the Prototype System
Initially the users will enrol their fingerprints
finge and eye
images that will be saved in the data base. Figure1 shows the
block diagram of the project.
Step1: The he person who ever wants
want to access his things or take
his amount from Bank Lockers or ATM,s first of all he wants
to show his id card in front of the card accessing machine i.e
reader.. If it is a valid one then it goes to second step.
Figure 1:: Block Diagram of the Project Otherwise Buzzer will be on and it gives the error message
A. Analysis of hardware Structure display like invalid person again it displays to show your
RFID card.
1) ARM7TDMI: ARM architecture is based on Reduced Step2: In this step the user have to enter the correct password,
Instruction Set Computer (RISC) Principles. The RISC if the userr will entered the wrong password it will not moves
instruction set, and related decode mechanism are much the next step and the buzzer will be on, if the password
simpler than those of Complex Instruction Set Computer accessing is continuously failed for three times means then
(CISC) designs. This simplicity gives: process will move to the initial condition i.e. RFID tag
showing step. If the user will entered the correct password
• A high instruction throughput
then controller asks for a fingerprint access.
• An excellent real-time interrupt response
Step3: In this step the controller asks for a figure print access,
• A small, cost-effective,
effective, processor macro cell.
if the finger print accessing is failed then buzzer will be on
Microcontroller: A Micro controller consists of a powerful
and the process will move to the first step i.e. RFID tag
CPU tightly coupled with memory RAM, ROM or EPROM),
showing step. If fingerprint access is matched with stored
various I / O features such as Serial ports, Parallel Ports,
fingerprint or authorized person finger print
pr then it moves to
Timer/Counters, Interrupt Controller, Data Acquisition
next step (Iris recognition).
interfaces-Analog
Analog to Digital Converter (ADC), Digital to
Step4: In this step the person who ever want access that
Analog Converter (ADC), everything integrated onto a single
particular accessories or things first
firs he/she has to place his eye
Silicon Chip.
in front of the PC camera at that time it will capture the image
2) RFID reader Module: This is used to automatically identify of eye and comparing with previous eye image in that same
the products tagged within the communication range
r of the way we can access some others with matching or compare of
reader, which will be able to provide the accurate eye image and this whole process will done with wi the help of
consignments and real-time
time automatically manifest, and matlab code. If it matches the locker system will be opened,
improve movable asset management accuracy and efficiency. user will access that Particular accessories or things
thing and the
3) Finger Print Scanner: A fingerprint sensor is an electronic process goes on. If captured image does not matched with first
device used to capture a digital image of the fingerprint taken image then the controller gives a halt to the process
pr and
171
Global Journal of Advanced Engineering Technologies, Vol1,Issue3-2012
Vol1,Issue3 ISSN : 2277-6370
moves to the initial step1 at the same time buzzer will be on.
on
Figure2 shows the complete system operation flow
C. System operation flow
3. BIOMETRICS
Biometrics is a technology which uses physiological or
behavioural characteristics to identify or verify a person [1].
Typical characteristics used for authentication include
fingerprint, iris and face. A conventional biometric
authentication system consists of two phases: enrolment and
verification (Figure4).
172
Global Journal of Advanced Engineering Technologies, Vol1,Issue3-2012 ISSN : 2277-6370
• Privacy concern: Biometrics identifies individuals. To the LPC, MFCC, etc. According to the biometrics selected and its
best of our knowledge, conventional biometric authentication application the feature extraction technique can be applied.
system is primarily built upon a fully-trusted model; that is,
the central authentication entity (CA) is trusted to take full iv) Recognition Module
control of users’ biometric information and is assumed to not The feature vectors, generated in the Feature Extraction
misuse the information. This assumption of trustworthiness Module are used in this module to classify the biometric data.
about the CA is not sufficient in the current malicious There are the classifiers like hamming distance, Euclidian
environments, since handing over one’s biometric information distance, and Support vector machine classifier. The rules are
to other parties or loss/compromise of one’s biometric defined for recognition of a person with his /her biometrics [5].
template will cause serious user privacy [5] concern. According to the biometric applications, the suitable
classifiers can be used to get better performance of the system.
• Irreplaceability: biometric data is permanently bound to a The feature vectors are used to write the decision making
user, and it is almost impossible to generate a new set of rules. In this module user’s identity is established or a claimed
biometric features for a legitimate user. Thus compromised identity is accepted or rejected.
biometrics is not replaceable.
Many approaches [5], [8] addressing the security and privacy B. FINGER PRINT
issues of biometrics have been proposed in the literature. Among all the biometric techniques, fingerprint-based
These approaches avoid storage of plain biometric templates identification [4] is the oldest method which has been
by recording them in a “distorted” way. successfully used in numerous applications. Figure5 shows
fingerprint images. The finger prints of a person have been
A. Biometric Recognition System used as person identification from long time. The finger prints
The Biometric Recognition Systems are used to identify of the identical twins are different. Everyone is known to have
the person based on the feature vectors of any one of the unique, immutable fingerprints. A fingerprint is made of a
biometric that the person possesses [8]. These systems are series of ridges and furrows on the surface of the finger. The
person authorized systems hence offer more secure and uniqueness of a fingerprint can be determined by the pattern
convenient process of identification compared to alternative of ridges and furrows as well as the minutiae points [3].
methods of identification. Each person has to establish the Minutiae points are local ridge characteristics that occur at
identity ranging from drivers’ license to gaining entry into a either a ridge bifurcation or a ridge ending. Fingerprint
country to the passport. The biometric system uses the matching techniques can be placed into two categories:
individual’s physical characteristics like fingerprint, hand minutiae based and correlation based. Minutiae-based
geometry, face, voice or iris. A simple biometric system techniques first find minutiae points and then map their
consists of four modules: Image acquisition, Pre-processing, relative placement on the finger.
Feature extraction and Recognition. Fingerprint matching based on minutiae has problems in
matching different sized (unregistered) minutiae patterns.
i) Image Acquisition Module Local ridge structures cannot be completely characterized by
This is the first module to acquire the biometric input. The minutiae. Efforts are being on to try an alternate
input can be image according to the selection of biometrics. representation of fingerprints, which will capture more local
The sensors like high resolution CCD camera or recorder can information and yield a fixed length code for the fingerprint.
be used to capture the biometric image. The distance between The matching [12] will then hopefully become a relatively
the sensor and human should be constant, the lighting system simple task of calculating the Euclidean distance will between
as well as physical capture system should be constant to the two codes.
acquire standard biometric input. Finger Print Classification:
Fingerprint classification [4] is a technique to assign a
ii) Pre-processing Module fingerprint into one of the several pre-specified types already
Once the input is captured, the original input image or established in the literature, which can provide an indexing
voice signal is processed to remove the noise and blurring mechanism. Fingerprint classification can be viewed as a
effect. The image is localized to extract the region of interest. coarse level matching of the fingerprints. An input fingerprint
The voice signal is framed to extract the desired signal. Then is first matched at a coarse level to one of the pre-specified
this processed input is given to feature extraction module. types and then, at a finer level, it is compared to the subset of
the database containing that type of fingerprints only.
iii) Feature Extraction Module
In the feature extraction module, the pre-processed image Different algorithms [13] are developed to classify
is used to extract the features. The feature extraction fingerprints into five classes, namely, whorl, right loop, left
algorithms are applied to get feature vector of the biometric loop, arch, and tented arch. The algorithm separates the
image. There are various feature extraction techniques like number of ridges present in four directions (0 degree,
Independent Component Analysis, Linear discriminate 45degree, 90 degree, and 135 degree) by filtering the central
component, principal component analysis, wavelet transform, part of a fingerprint with a bank of Gabor filters.
173
Global Journal of Advanced Engineering Technologies, Vol1,Issue3-2012
Vol1,Issue3 ISSN : 2277-6370
174
Global Journal of Advanced Engineering Technologies, Vol1,Issue3-2012 ISSN : 2277-6370
175