Abstract

The security is an important aspect in our daily life

whichever the system we consider security plays vital role.
The biometric person identification technique based on the
pattern of the human fingerprint and speech is well suited
to be applied to access control and provides strong esecurity. Security systems having realized the value of
biometrics for two basic purposes: to verify or identify
users.The goal of this project is to provide different aspects
for security system by means of biometrics &investigate the
current techniques for biometric identification. This target
can be mainly decomposed into image preprocessing,
feature extraction and feature match. For each subtask,
some classical and uptodate methods in literatures are
analyzed. Based on the analysis, we are going to develop an
integrated solution for Biometric Security System using
Fingerprint and Speech.
.

INTRODUCTION
In an increasingly digital world, reliable personal
authentication has become an important human computer
interface activity. National security, ecommerce, and access to
computer networks are some examples where establishing a
persons identity is vital. Most existing security measures rely
on knowledge based approach like passwords or token based
approach such as swipe cards and passwords to control access
to physical and virtual spaces. However, all over the place, such
methods are not very secure. Token such as access cards may be
shared or stolen. Passwords and PIN numbers may be stolen
electronically. Further more, they cannot differentiate between
authorized user and a person having access to tokens or
knowledge. Biometrics such as fingerprint, face and voice print
offers reliable personal authentication that can address these
problems and is gaining citizen and government acceptance.
Among biometrics, fingerprint systems have been one of most
widely researched and deployed because of their easy access,
low price of fingerprint sensors, nonintrusive scanning, and
relatively good performance.There are a lot of attributes that
could be used for identification purposes. These attributes are
unique for each person. Of those attributes, the fingerprint was
the first one to be discovered and examined. Everyones finger
carries a unique pattern. This pattern consists of different loops,
spirals and curves and is absolutely unique.
Fingerprint-recognition-based IT security has reached great
importance as a mean of

admitting information and services. Other attributes, which

are unique for each human,
include face features, eye iris and retina features, palm and
hand geometry,ear shape, DNA odour and hand writing
feature. Some methods using these features are still under
development, but they require new devices and technologies
for detecting the deviations. The communication purposes
include speech recognition, speech generation, special input
devices and also character recognition (the OCR applications).
These make it easier to operate a machine due to the natural
way of the communication. The speech-based methods are not
common yet, but they are supposed to be very important as
soon as the reliable identification methods will be developed.
Advantages of the speech technology are an easiness of the
sample acquisition (there has to be only a single microphone to
get the needed data) and a willingness of the people to provide
the system with a speech sample.

There are seven basic criteria for biometric security system:

uniqueness, universality, permanence, collectability,

performance, acceptability and circumvention .As mentioned

above, uniqueness is considered as the priority one
requirement for biometric data. It will indicate how differently
and uniquely the biometric system will be able to recognize
each user among groups of users. For instance, the DNA of
each person is unique and it is impossible to replicate.
Universality is the secondary criteria for the biometric security.
This parameter indicates requirements for unique
characteristics of each person in the world, which cannot be
replicated. For example, retinal and iris are characteristics will
satisfy this requirement. Thirdly, a permanence parameter is
required for every single characteristic or trait which is
recorded in the database of the system and needs to be constant
for a certain period of time period. This parameter will mostly
be affected by the age of the user. Following the permanence
parameter is the collectability. The collectability parameter
requires the collection of each characteristic and trait by the
system in order to verify their identification. Then,
performance is the next parameter for the system which
outlines how well the security system works. The accuracy and
robustness are main factors for the biometric security system.
These factors will decide the performance of the biometric
security system. The acceptability parameter will choose fields
in which biometric technologies are acceptable. Finally,
circumvention will decide how easily each characteristic and
trait provided by the user can lead to failure during the
verification process.
All the implementation work will be done in MATLAB
using Image Processing & other related Toolbox.
Performance of the developed system will be evaluated on a

database with fingerprints&speech samples from different

people

Scope of project
Our project has scope in

SECURITY PURPOSE
Basically we are using neural networks & Hidden
Markov chain algorithms for fingerprint & Speech recognition
respectively using both of this algorithms the project aims at
identifying the authenticated person for security .Project aims
at giving 100% authentication using fingerprint impressions &
voice samples with less probability to fail in identification
using proposed algoriyhm.we would also try to implement the
same algorithms using iris and signature in future work.

1. SECURITY:
Biometric Identification Systems are widely used for
unique identification of humans
mainly for
verification and identification. Biometrics is used as a form
of identity access management and access control. So use
of biometrics in student attendance management system is
a secure approach. There are many types of biometric
systems like fingerprint recognition, face recognition,
voice recognition, iris recognition, palm recognition etc
Fingerscan provides an audit trail of the date and time a
user accessed the unit, the reason for access, and the result.
With a 0.0001% probability of a false acceptance fingerscan

provides a level of security which cannot be achieved by any

knowledge or token based system.

2.Network security:
The biggest problem for network security is the
authentication system. For most systems, they mainly use and
rely on passwords which is a combination of letters, characters
and/or numbers. However, passwords need to be renewed
within a certain period of time to maintain a high level of
security. Moreover, it might be copied and used by
unauthorized users. To fix that problem,biometrics security
system can be applied. The most use of biometrics security
system in network is the logical access controlmethod. It will
verify person's identification for secure workstation logon or
network logon to get access control to the system.

LITERATURE SURVEY
1.Multimodal Biometrics &Authentication System

Anil k Jain, Lin Hong,Yatin Kulkarni in which author says

that
They introduced a biometric system which integrates face
recognition, fingerprint verification and speaker verification
for making personal identification. This system takes
advantages of capabilities of each individual biometrics. It can
be used to overcome some of limitations of single biometrics
Preliminary experimental results that identity established by
such integrated systems is more reliable than identity
established by face recognition, fingerprint verification and
speaker verification. In this paper multiple fusion of biometric
techniques overcomes the drawback of individual
techniques[7].

2.Fingerprint

Identification System Based On

Neural Network
Mr. Lokhande S.K., Prof. Mrs. Dhongde V.S.
authors says that The purpose of this project is to
design and develop a pattern recognition system with using
Artificial Neural Network (ANN) that can recognize the type
of image based on the features extracted from the choose
image[2]. Also comparing any two methods of neural

network. This system which can fully recognizing the types of

the data had been add in the data storage or called as training
data. The Graphic User Interface in Neural Network toolbox
is used. This is the alternative way to change the common
usage of the MATLAB which are use the command insert at
command window.

3.A New Approach of Finger-Print Recognition

based on Neural Network
Behnaz Saropourian in which author says that this is
classic patterns of the finger-print recognition that they have
working on the single dots existing on the finger-print liked
ridge-ending and bifurcation[8]. This new observation is about
finger-print recognition that uses state of the single steak in the
finger-print image, because patterns of the veins in the fingerprint without notice of the finger-print about person, and can
be used for identified person. This algorithm can work very
fine on the binary images and also gray scanned photo.

4.Fingerprint based locker system using

microcontroller
Paper illustrates The main aim of the paper is to design and
implement the Fingerprint based bank locker system using
microcontroller. Biometrics studies commonly include
fingerprint, face, iris, voice, signature, and hand geometry
recognition and verification. Many other modalities are in

various stages of development and assessment. Among these

available biometric traits finger Print proves to be one of the
best traits providing good mismatch ratio and also reliable.
The present scenario to operate a bank locker is with locks
which are having keys. This does not provide good security to
our lockers. To provide perfect security to the bank lockers
and to make the work easier, this project is taking help of two
different technologies viz. EMBEDDED SYSTEMS and
BIOMETRICS[4].

5. Implementing Multimodal Biometric Solutions in

Embedded Systems
Jingyan Wang, Yongping Li, Ying Zhang and Yuefeng Huang Shanghai Institute of
Applied Physics, Chinese Academy of Science.

In which author illustrates that Embedded systems are

widely used in the areas of PIM (Personal Information
Management) and safety-critical mechanical
manipulation. With the increasing demands of privacy
protection and safety reliability, these systems confront
with all kinds of security concerns. To start with, they
are possibly operated in physically insecure
environment[10]. The small-size feature of the devices
such as cell phones and PDAs lends them easy to be lost
and stolen. Furthermore, increasing programmability and
networking function of these devices make them feeble to
secure against various hacker assaults. While recent advances
in embedded system security have addressed issues like secure

communication, secure information storage, and tamper

resistance (protection from physical and software attacks),
objectives such as user-device authentication have often been
overlooked, placing a hidden danger on the overall security of
the system.

6. Multimodal Biometric system Fusion Using

Fingerprint and Iris with Fuzzy Logic.
by Mohamad Abdolahi, Majid Mohamadi, Mehdi Jafari.
In this paper authors says that Single biometric systems have
a variety of problems such as noisy data, non-universality,
spoof attacks and unacceptable error rate[6]. These limitations
can be solved by deploying multimodal biometric systems.
Multimodal biometric systems utilize two or more individual
modalities, like face, iris, retina and fingerprint. Multimodal
biometric systems improve the recognition accuracy more than
uni-modal methods. In this paper, two uni-modal biometrics,
iris and fingerprint are used as multi-biometrics and show
using this biometrics has good result with high accuracy.
Decision level is used for fusion and each biometric result is
weighted for participate in final decision. Fuzzy logic is used
for the effect of each biometric result combination &
combining this 2 techniques error rate reduces significantly.

7. A Fingerprint Recognition Algorithm Combining

Phase- Based Image Matching and Feature-Based
Matching.
Koichi Ito, Ayumi Morita, Takafumi Aoki, Hiroshi
Nakajima,Koji Kobayashi, and Tatsuo Higuchi.
This paper proposes an efficient fingerprint
recognition algorithm combining phase-based image
matching and feature-based matching[1].The use of
Fourier phase information of fingerprint images makes
possible to achieve robust recognition for weakly
impressed, low-quality fingerprint images.
Experimental evaluations using two different types of
fingerprint image databases demonstrate efficient
recognition performance of the proposed algorithm
compared with a typical minutiae-based algorithm and
the conventional phase-based algorithm.

8.FINGERPRINT MATCHING USING NEURAL

NETWORK TRAINING
International Journal Of Engineering And Computer
Science
Kalpna Kashyap, Meenakshi Yadav

In this author says that says that Fingerprint is widely accepted

for personnel identification. In this paper LevenbergMarquardt back propagation (LMBP) algorithm is used for
training purpose because LMBP is fastest technique for
complex data sets and gives better performance in such
situation[5]. Input image is trained by trainlm function for
producing different result sets like performance plot,
regression values, simulation network of input image ,
histogram graph etc. Neural networks have many advantages
over other methods like adaptive learning, self organization,
real-time operation, fault tolerance. It has several applications
such as hand writing and type writing recognition, fraud
detection, criminal sentencing, optimization, pattern
recognition etc. Here, trainlm function is applied for training
network so that it can produce different result sets.

BLOCK DIAGRAM

FINGERPRINT SCANNER
Refers to automated method of
verifying match between human
fingerprints
One of the many forms to verify identity

MICROPHONE
Microphones take voice input from the
person and stores them in the database.
It converts speech signals into electrical
signals.

MAX232
Max232 is IC widely used in RS232 Communication systems
in which conversion of voltage
Level is required to make TTL devices to be compatible
with PC serial port and vice-versa.This chip contains charge
pumps which pumps the voltage to Desired level.It can be
powered by a single +5 volt power supply and its output can
reach +7.5 volts.MAX232 comes in 16 Pin Dip and many
other packages and it contains Dual Drivers.
MAX232 is compatible with RS-232 standard, and
consists of dual transceiver. Each receiver converts TIA/EIA232-E levels into 5V TTL/CMOS levels. Each driver converts
TTL/COMS levels into TIA/EIA-232-E levels. The MAX232
is characterized for operation from -40C to +85C for all
packages.MAX232 is purposed for application in highperformance information processing systems and control
devices of wide application. MAX232 is purposed for

application in high-performance information processing

systems and control devices of wide application.

PIC16F887

 The PIC16F887 has a 13-bit program

counter capable of addressing an 8K x 14
(0000h-1FFFh) program memory space.
This 8x14 memory space is broken into 4
pages of 2k x 14 each.
Page # Memory location within a page A12
A11 A10 A9 A8 A7 A6 A5 A4 A3 A2 A1 A0
Accessing a location above these boundaries
will cause a wrap-around within the first 8K x
14 space.
The Reset vector is at memory location
0000h and the interrupt vector is at memory
location 0004h.
The 16F887 provides various PORT I/O pins
These can be Used to interface to the
outside world. A total of 35 I/O pins are
provided by the 16F887 and are divided into
various PORTS.
PINS: The I/O pins can be individually
programmed to be either inputs or outputs.
Many of the I/O pins are shared with another
functionality. One needs to program the
16F887 for the desired functionality.

PORTS: A B C D E

D.C MOTOR

Electric drives
for
motor is used to
draw
electrical
energy
from the
mains and
supply the electrical energy to the motor at whatever voltage,
current and frequency necessary to achieve the desired
mechanical output.
Advantages of DC motor
Ease of control
Deliver high starting torque
Near-linear performance
Disadvantages:
High maintenance
Large and expensive (compared to induction motor)
Not suitable for high-speed operation due to commutator and
brushes
Not suitable in explosive or very clean environment
DC motor drives:

The drive is relatively simple and cheap (compared to

induction motor drives. But DC motor itself is more
expensive
Due to the numerous disadvantages of DC motor, it is getting
less popular.

PIEZOBUZZER

 The piezo buzzer produces sound based on

reverse of the piezoelectric effect. The
generation of pressure variation or strain by
the application of electric potential across a
piezoelectric material is the underlying
principle.
These buzzers can be used alert a user of an
event corresponding to a switching action,
counter signal or sensor input. They are also
used in alarm circuits.

POWER SUPPLY

A power supply is an electronic device that supplies electric

energy to an electrical load.. The primary function of a power
supply is to convert one form of electrical energy to another
and, as a result, power supplies are sometimes referred to
as electric power converters. Some power supplies are

discrete, stand-alone devices, whereas others are built into

larger devices along with their loads. Examples of the latter
include power supplies found in desktop
computers and consumer electronics devices.