Академический Документы
Профессиональный Документы
Культура Документы
System
PART I: REQUIREMENT ANALYSIS DOCUMENT (RAD)
CHAPTER ONE
1. Introduction
As the necessity for higher levels of security rises, technology is bound to swell to fulfill these
needs. Any new creation, enterprise, or development should be uncomplicated and acceptable for
end users in order to spread worldwide. This strong demand for user-friendly systems which can
secure our assets and protect our privacy without losing our identity in a sea of numbers, grabbed
the attention and studies of scientists toward whats called biometrics.
Biometrics is the emerging area of bioengineering; it is the automated method of recognizing
person based on a physiology. There exist several biometric systems such as finger prints, voice,
iris, retina, hand geometry, ear geometry, and face. Among these systems, face and fingerprint
recognition appears to be the most universal, collectable, and accessible systems.
Biometric face and fingerprint recognition are particularly attractive biometric approaches,
since both focuses on the same identifier that humans use primarily to distinguish one person
from another: their faces and fingerprint is also around in criminal investigation since late 19 th
century. One of the main goals of this system is to understand the complex human visual system
as well as to use the knowledge of distinguishing one persons fingerprint from others and how
humans represent faces in order to discriminate different identities with high accuracy with the
use
of
the
two
most
universally
accepted
biometric
mechanisms.
The face and fingerprint recognition problem can be divided into two main stages: face and
fingerprint detection (verification), and authentication based on the face and fingerprint detected
and verified.
1. The detection stage is the first stage; it includes locating a face and fingerprint as an
image file and verifying by cross matching.
2. The authentication stage is the second stage; in which authentication will take place.
The system will be developed with JAVA which makes it portable and platform independent.
There will be three systems namely Desktop application, web application, and mobile phones
(Android application) we will discuss these applications briefly throughout this documentation.
Haramaya University Department of Computer Science, Final Project I
Documentation
Page 1
1.1.
Background
Automated face recognition is a relatively new concept. Developed in the 1960s, the first semiautomated system for face recognition required the administrator to locate features ( such as
eyes, ears, nose, and mouth) on the photographs before it calculated distances and ratios to a
common reference point, which were then compared to reference data. In the 1970s, Goldstein,
Harmon, and Lesk used 21 specific subjective markers such as hair color and lip thickness to
automate the recognition.
In 1988, Kirby and Sirovich applied principle component analysis, a standard linear algebra
technique, to the face recognition problem. This was considered somewhat of a milestone as it
showed that less than one hundred values were required to accurately code a suitably aligned and
normalized face image.
Today, face recognition technology is being used to combat passport fraud, support law
enforcement, identify missing children, and minimize benefit/identity fraud. We have compared
the features of Face Recognition System and Fingerprint Recognition system. In the digital age,
both systems use the computer software application that can identify individual analyzing the
features of facial shape and fingerprint ridges.
Fingerprint Identification System: It is the oldest scientific method of personal identity
verification. Fingerprint Scanner authenticates the fingerprint applying digital technology. The
basic principle of fingerprint identification is based on the following features:
The fingerprints of any two people cannot be identical.
The fingerprint of a person remains the same throughout his life.
The pattern of the fingerprints can be expressed by algorithms.
Face Recognition: Modern technique of face recognition provides detailed analysis of face
image. There are certain prominent landmarks in each face. Peak and valleys of the face have
created these landmarks, which are known as nodal points. There are about 80 nodal points in
human face. The software analyzes mainly the following landmarks in face.
Width of the nose
1.3. Objectives
1.3.1 General objectives
Haramaya University Department of Computer Science, Final Project I
Documentation
Page 3
Examine the major biometric technologies of today including, iris, voice, signature,
fingerprint, face and hand.
Understand the key aspects of these major technologies, namely those relating to the
technological, application domain, social, environmental and performance aspects.
Develop a fully operational face and fingerprint recognition application using an object
oriented design approach with java.
Investigate the algorithmic structure of such a system and gain insight into how such an
application is structured and deployed.
Apply application interface standards to the application design and appreciate the need
for standardization in application development.
Understand and explain the need for biometric template file standards such as the
Common Biometrics Exchange File Format, (CBEFF).
1.4. Scope
We propose a simple and effective approach for Biometric fingerprint image enhancement and
minutiae extraction based on the frequency and orientation of the local ridges and thereby
extracting correct minutiae points.
The Face and Fingerprint Recognition System is designed to determine automatically whether
two sets of fingerprint ridge detail come from the same finger. The Fingerprint Recognition
System is used to identify fingerprints of an individual and verify their identity. Fingerprints as
one of many forms of special biometric characters are easy to identify individuals. The goal is to
run the Fingerprint Recognition System automatically and correctly. The future plan is to
improve the ability of this system to recognize low quality fingerprints images. This device can
be used in many different fields as mentioned below:
i.
Indentifying crime:
Private detectives
Keeping Federal records of criminals and suspected individual
Security
Fingerprint based identification has been one of the most successful biometric techniques used
for personal identification. Each individual has unique fingerprints. A fingerprint is the pattern of
ridges and valleys on the finger tip. A fingerprint is thus defined by the uniqueness of the local
ridge characteristics and their relationships. Small points are these local ridge characteristics that
occur either at a ridge ending or a ridge bifurcation. A ridge ending is defined as the point where
the ridge ends abruptly and the ridge bifurcation is the point where the ridge splits into two or
more branches.
Automatic minutiae detection becomes a difficult task in low quality fingerprint images where
noise and contrast deficiency result in pixel configurations similar to that of minutiae. This is an
important aspect that has been taken into consideration in this project for extraction of the
minutiae with a minimum error in a particular location. A complete minutiae extraction scheme
for automatic fingerprint recognition systems is presented. The proposed method uses improving
alternatives for the image enhancement process, leading consequently to an increase of the
reliability in the minutiae extraction task.
CHAPTER TWO
2. PROPOSED SYSTEM
There are many problems in the existing system, to solve those problems we are going to
develop a system that is well structured and computerized. And the goal of our project is to avoid
the problems faced in the existing system of the face and fingerprint recognition system and
develop fully functional one. To avoid these problems, we have to sort out the functional
requirements and non functional requirements of the proposed system.
2.1.1.
User requirements
Each record represents information about a person and contains an image of his/her face
and fingerprint.
Records will more or less consist of the following fields:
First name.
Last name.
Phone.
Address (city, state, country etc).
Face templates.
Fingerprint templates.
ID-number.
The system must be able to take face or fingerprint image as an input and search for a
match in the database, and then show the results.
The results should be viewed by showing the faces matches the input, and display the
most possible image first, in numerical order.
The user should be able to chose (click on) the result that he/she wants and view the full
records information of the person.
The system can do noisy filter on images.
2.1.2.
Various Software and Hardware that are required to do this project are discussed here.
1. Software:
The product requires the use of a PC running on JAVA runtime environment or java enabled
browser for the web application and an android system for mobile user.
1.1. For the client side (end user)
Running Window XP or later, UNIX, MAC operating system.
Java runtime environment.
Android 2.5 or later recommended Android 3.0
1.2. For the server Side
Running windows server 2003 or later, UNIX.
Java runtime environment
Oracle application server
Oracle mobile server.
2.
Hardware:
The other part of the external interface is hardware interface, this interface describe the hardware
part of the system.
Haramaya University Department of Computer Science, Final Project I
Documentation
Page 7
RAM 2GB recommended 6GB or more for big systems this is recommended because
image processing work need more memory.
Hard Disk: minimum of 15 GB recommended 40GB or more to store the biometric
data,we need bigger storage space for storing the image file properly.
Input device: Keyboard, Webcam (digital camera), and fingerprint reader.
Output device: computer monitor.
External firewall if the system needs to be secure.
2.2.1.
Security Requirements
Human face and fingerprint recognition is used for authentication and verification which raise
the need for big security. This is because it contains the identity of a person which if get in hand
1. Hardware Security
Using firewall hardwares.
Protecting the server room by putting it in secure place.
2. Software Security
Using different kind of firewall systems
Encrypting the database in high level of encryption.
Encrypting the network in high level encryption.
2.2.2.
Environmental Requirements
The system must be stored in a good place which is cold, which allows the server to perform in
its highest performance by allowing it not to get hot.
2.2.3.
Maintainability
The system shall be distributed with independent modules or classes for database interface for
the databases. This independency brings to easy testability, maintainability, flexibility and easy to
use. In general, after the system has been produced, change or improvement may be needed. This
could happen because design faults are identified after the system has been failed tested or
because functions need to be added.
2.2.4.
Accuracy
Human face and fingerprint recognition system need an accurate and correct data from the
system that he/she uses for the preparation of reports as well as to make relevant decisions.
We can easily imagine the consequences of any decision that made inaccurate and incorrect data
on their basis. We expect to address this major issue through implementing a number of validity
checks on the number validity on the person entering the data that is going to be entered to the
records of the system.
2.3.1.2 Actors
Actors are external entities that interact with the system. Use cases are initiated or triggered by
actors. An actor initiates system activities for the purpose of completing some task. An actor is a
Haramaya University Department of Computer Science, Final Project I
Documentation
Page 10
Use cases
Login
Capture photo
Capture fingerprint
Character identification
Display information (transaction)
Review (Update) analyses
Alert notice
Actors
Administrator
End users
1.
2.
3.
4.
5.
Login
Administrator, End User
The username and password to login for Administrator and User
Administrator and User must be authorized
Login is successfully
Basic course of Actions
Administrator and User want to Login
Fill the user name and password on the space provide
Administrator login as Admin and User login as standard user
Click Login button
Use case ends
Capture photo
Administrator, End user (embedded digital camera)
The photo area provides access to photo capturing process
Digital camera (Mobile Android) application successfully
launched
Photo displayed
Basic course of Actions
Capture fingerprint
Administrator, End user ( fingerprint scanner)
The capture fingerprints process provides a predefined capture
sequence
The administrator and user has chosen the capture biometrics
feature of Android application
The fingerprint capturing process is completed
Basic course of Actions
1. Fingerprint reader displays platen and active capture area of current presenter
finger tips
2. Administrator and User places requested print on scanner platen
3. Scanner captures the print image after it determines that the print image is
acceptable
4. The Application displays the fingerprint captured to the administrator and user
5. Repeat steps 1 to 3 until all required print images are captured
6. Use case ends
Alternate of courses of Action
Alternative course A: 3. If the scanner fails, application indicates the failure of the scanner and
the option to capture print is inactive
Alternate Course A : 6. Use case ends
Character identification
Administrator
Description
Precondition
Post condition
1.
2.
3.
4.
Display information
End User
Precondition
Post condition
1. The Android application resets the alert indication (i.e. all information displayed
chronologically)
2. The Android application displays to the user the information that match entries
in the Database
3. Use case ends
Alternate of courses of Action
Alternative course A: 2. If captured image does not match any entries in the database, access
the details of the information
Alternate Course A : 3. Use case ends
Review analyses
Administrator
The Administrator is able to look frame analyses or documents by
other user or their own
Frames must already be analyzed and documents must be
submitted in order for them to be reviewed later
Users can only make changes to their own frame analyses or
documents submitted
Basic course of Actions
1.
2.
3.
4.
Alert notice
End User
The system will continuously monitor the return responses and
indicate when there is a positive match response received
The system application must be launched with an active
connection
Matched transaction is indicated
Basic course of Actions
Sequence Diagram to Store Face and Fingerprint is shown in the figure below.
2.4. Interface
2.4.1.
Forms
The application more or less contains three or more forms for the desktop application and for
the android application there will be 3 or more forms. Here we tried to describe more about the
main three forms that will be available in all applications. The forms may change in some way
from the original (final application) but there function is the same.
As indicated in above figure, the login page contains the user ID, password and user clearance
level and the users should enter the User ID, password correctly and select his level of clearance
to get the home page or the main menu.
As indicated in above figure, the fingerprint read form (page) contains the operations performed
by the authorized person (administrator) to capture the new finger tips. This form is available
only if we logged in successfully.
Haramaya University Department of Computer Science, Final Project I
Documentation
Page 23
This page is used to search the information of record from the database. Select the criteria by
which you want to search by clicking one of the radio button and enter the selected on text box
Introduction
Purpose
System design focuses on decomposing the system into manageable parts. During system design,
we focus on the processes, data structures, and software and hardware components necessary to
implement it. The challenge of system design is that many conflicting criteria and constraints
need to be met when decomposing the system.
The purposes of objectoriented design document is to provide an overview as to how the
proposed system will be used to obtain the information needed to derive the actual
implementation of our system.
3.2
Design Goals
The objectives of Designing are to model a system with high quality and show what the system
will look like after the coding is done. Which allows the programmer to do his job as a
programmer and develop good and error-free system; these also give the developer, the ability to
develop easily maintainable system. These way maintenance programmers can make changes to
the system after it has been put into operation easily.
The field of structured design contains a number of guidelines that help designer determine
which modules, and which interconnections between the modules will best implement the
requirements specified in the system analysis /Requirement gathering phase.
The first step in designing process is to map the essential model of user requirements onto a
configuration of process. Then, within each process, the designer must decide how to allocate
processes and data to different tasks. Finally, we must organize the processes within each task
into a hierarchy of modules, using modeling tool.
The goal of system design is to manage complexity by dividing the system into smaller,
manageable pieces.
4.
CHAPTER FOUR
SYSTEM DESIGN MODEL
Enrollment: Capture and processing of user biometric data for use by system in subsequent
authentication operations. And it is workflow is illustrated in figure 12 below.
Figure 12: Enrollment
The following are the subsystems which the biometric system uses throughout every transaction/
process. We will describe each one as follows.
o Data Collection: Data Collection Module Biometric choice, presentation of biometric,
biometric data collection by sensor and its digitization is shown in Figure 15 below.
o Transmission: Transmission Module Compress and encrypt sensor digital data, reverse
process its workflow is shown in figure 16 below.
Decision
Confidence?
o Decision model: this stage will cheek if there is there enough similarity to the stored
information to declare a match with a certain confidence? If so it show the result. The
workflow is shown in figure 19 below.
Yes
Administrator
Add Record
registration
systemLog in to
levelGive clearance
Update record
Delete record
of biometricSearch record
Biometric
Add user
User
5.
CHAPTER FIVE
DETAILED DESIGN
5.1. Introduction
The Human Face And fingerprint recognition is a system to be developed to show the world wide
used Biometric system And to introduce this system to our countries forensic and other manual
systems. The system uploaded on a central server to be accessed by multiple users. It will have
user-friendly interfaces to interact with the users easily. User will type their user name and
password on the login form and the system will check the validity of the user in the database. If a
match is found the user will be allowed to access the system with the privilege level assigned to
him/her. If a match is not found in the database the system will display a message telling the user
to re-enter the User-ID and password or else service will be denied.
Response time. Refers to the time delay the user wait for accessing the application. It is
mainly depend on the connection type of the user internet and the speed of the computer
the user using.
Throughput. Refers to the number of tasks/operations that can be done at a time in our
case the system can handle multiple tasks at a time.
Memory: This is the required memory size, so as to run the application properly. The
proposed system will need minimum of 1GB of Memory for client machines and 4 GB
for server. And internet connection is the first step of processing. Offline users dont have
the opportunity to use the application properly.
The product requires also the use of a PC equipped with a mouth and standard keyboard. A
monitor with not less than 800x600 resolutions and with 256 color capability.
This product requires the use of a PC with Java runtime environment. This software should be
installed on a windows XP or later, UNIX/LINUX, Mac operating
The product should run on windows XP or later, UNIX/LINUX, Mac operating system.
For windows XP based systems, a Pentium class processor 3.0 GHZ or faster
Criteria
Haramaya University Department of Computer Science, Final Project I
Documentation
Page 37
Availability. It refers to the degree to which the system is found doing normal task. The
system works as long as connection is available.
Robustness. Ability to survive when users enter invalid input. It refers to the extent to which
the system works with invalid input. The system doesnt fail/ crash when the users enter an
invalid input. For instance the users enter the username and password to login into the system
until three times unless the system exits and the user enter an input in each form the system
check the appropriate type and give the type of error the user commit as an alert message .
Usability. The usage of the system must be sensitive. The graphical user interface is
designed in way that simple usage with good look and feel.
Fault Tolerance- ability to operate under erroneous conditions. The system back up data to
avoid loss of data when system crash or damage.
Usability: Easy adaptive for users after a short demonstration about the operation of the user
interface.
Utility: The system can support some additional information including pictures and movies
uploaded on the server and clients can read these posts.
Readability: It is simple to recognize what the system will perform by reading the source
code written using the specified JAVA code. The use of appropriate comments, descriptive
variable naming and indentation will help in this purpose.
Modifiability: The system can be used in any kind of biometric approach we can easily change
the biometric devices and data used.
Superimpose(place one thing over another, typically so that both are evident) a logical
structure upon the data on the basis of these relationships
Entity is a thing in real world with independent existence. Entity of the new system are listed below
List of entities along with their attributes are described in the table below.
Entity name
Person
PID
Fingerprint
Face image
Personal info
PID
Name
Birth date
Birth Place
Last Known Address
Sex
Data types
Primary key
Char(10)
BLOB
BLOB
Varchar2(50)
PID
Fingerprint
Face image
Char(10)
Varchar2(50)
Date and time
Varchar2(20)
Long Text
Char(1)
PID
User
User ID
User ID
Level
Name
Password
sex
Birth date
Job
Department
DEP-ID
Salary
Char(30)
INT
Char(30)
Char(30)
Varchar2(20)
Varchar2(20)
Varchar2(20)
Number(10,2)
Level
Level
Level
INT
Department Name
DEP-ID
Varchar2(20)
Char(30)
Department
Abbreviation
RAD: REQUIREMENT ANALYSIS DOCUMENT
CBEFF: Common Biometrics Exchange File Format
ACE/V- Analysis, Comparison, Evaluation, and Verification
PC: Personal Computer
MAC: Mackintosh
RAM: Random Access Memory
GB: Giga byte
SDD: System Design Document
PID: Person Identification Number
Definitions
Biometrics: An open-ended set of technologies based on the measurement of some unique
physical characteristics of an individual, for the purpose of identifying an individual (or
verifying) identity.
Bio-API: An industry standard Application Program Interface (framework) defined by The
Biometric Consortium.
References
1. Digital Image Processing An Algorithmic Introduction Using Java By Wilhelm Burger
And Mark J.Burge
2. Learn Java for Android Development By Jeff JavaJeff Friesen.
3. Oracle Database 11g Master SQL and PL/SQL in the Oracle Database By Jason Price
4. Oracle Database 11g DBA Handbook Administer a Scalable, Secure Oracle Enterprise
Database By Bob Bryla, Kevin Loney
5. http://www.google.com
6. http://www.ibm.com/developerworks/
7. NeuroTechnology Developers Guide Version: 4.3.0.0.Release date: 9/30/2012.