Professional Documents
Culture Documents
SYSTEM
(Facial Recognition System)
By
BACHELOR OF
SCIENCE IN
COMPUTER SCIENCE
1.1 Brief
Development began on similar systems in the 1960s, beginning as a form of computer
application. Since their inception, facial recognition systems have seen wider uses in recent times
on smartphones and in other forms of technology, such as robotics. Because computerized facial
recognition involves the measurement of a human's physiological characteristics, facial
recognition systems are categorized as biometrics. Although the accuracy of facial recognition
systems as a biometric technology is lower than iris recognition and fingerprint recognition, it is
widely adopted due to its contactless process.[3] Facial recognition systems have been deployed
in advanced human–computer interaction, video surveillance and automatic indexing of images.
1
Abbreviations
CNN Convolution Neural Network
ML Machine Learning
CV Computer Vision
HTML Hyper Text Markup Language
CSS Cascading Style Sheet
JS JavaScript
Ajax Asynchronous JavaScript And XML
2
Figure 1: Face scanning
Computer Vision model is used in my project to recognize the facial from photo and id card. I
have checked the accuracy by applying data of different user identities on Convolution Neural
Network (CNN) for image classification.
The Incremental model has been used in the construction of this project because in each phase
of the project, it is analyzed, designed, implemented, and further tested until the product is
finished. Many developmental cycles are possible, and these cycles are divided into very small
modules. Typically, software that works with the add-on model is produced during the first
module. Each subsequent module release can add function to the previous release. In a growing
model, the process continues until a complete system is achieved. Therefore, this model is much
more flexible compared to other models of System Development Life Cycle when conducting a
screening and treatment program. This is how it will be easier for every member to complete
their designated modules and is flexible to merge all the iterations. This methodology is more
useful in web applications and task-based companies.
3
Figure 2: Agile Model
4
Chapter 2
Problem Definition
5
2 Problem Definition
2.1 Problem statement
As we all know the world is moving faster towards online purchasing and selling platforms For
example Now a days Americans 70% purchase is from online platforms, The retailer also move
on those famous platforms like amazon , But the main problem is here for the profile verification
for new seller , the websites took more than a couple of weeks to verify their profile through
video call, Here we are going to develop a platform through which seller can verify their profile
from live video using deep learning in minutes instead of days.
We have created a website named as Digital Trading System. The website has:
6
Chapter 3
Requirement Analysis
7
3 Requirement Analysis
3.1 Use Case Diagram
The table below indicates a comprehensive use case template filled in with an example
drawn from the Seller profile verification.
8
3.2 Use Case Diagram
The table below indicates a comprehensive use case template filled in with an example
drawn from the Order placement flow.
9
3.3 Use Case Diagram
The table below indicates a comprehensive use case template filled in with an example
drawn from the Database Storage.
10
3.4 Use Case Diagram
The table below indicates a comprehensive use case template filled in with an example
drawn from the Give prescription.
11
3.5 Use Case Diagram
The table below indicates a comprehensive use case template filled in with an example
drawn from the view User record.
Table 5: Manage User use case
12
3.6 Use Case Diagram
The table below indicates a comprehensive use case template filled in with an example
drawn from the manage users.
Table 6: Manage Seller use case
13
3.7 Functional Requirements
This system has following functional requirements:
Admin
Seller/Trader
User/Buyer
Facial Verification
Order placement
Product Recommendation
Comparison
3.7.1 Admin
Admin management module provides human resource management. It refreshes the job
description of employees, revives the structure of the Club, keeps track of employment records.
3.7.2 Seller
It can be used to register them, view the data of the Placed Orders, update status of orders, and
check the orders history and their profile ranks.
3.7.3 Buyer
It can be used to register them, view the data of the Placed Orders, update status of orders, and
check the orders history, search and get recommendation for products.
14
3.8.2 Reliability
Reliability is the level to which the software system reliably performs the specified functions
without failure. The system is reliable in that it performs the decision with confirmation of the
test.
3.8.3 Safety
The database may get crashed at any certain time due to virus or operating system failure.
Therefore, it is required to take the database backup.
3.8.4 Security
This system allows only authorized members to do administrative tasks. The system wouldn’t
allow unauthorized users to enter the system; this action will maintain and improve the
system's security level. This system had strong security to protect itself from any external
threats.
3.8.5 Portability
Portability is the ease with which a computer software program system can be transported
from its current hardware or software environment to another environment. This system works
on different platforms with full portability.
3.8.6 Performance
This system performs all the tasks very correctly and provides the results quickly and
accurately.
15
Chapter 4
Design and Architecture
16
4 Design and Architecture
4.1 System Architecture:
The structure of the system explains the working of the system and describes the components of the
project, their relationships, and how they interact with each other, with this architecture.
17
4.3 Process Flow/Representation:
18
4.4 ER Diagram:
19
4.5 Design Models:
SDLC model used:
The Incremental model has been used in the construction of this project because in each
phase of the project, it is analyzed, designed, implemented, and further tested until the
product is finished. Many developmental cycles are possible, and these cycles are divided
into very small modules. Typically, software that works with the add-on model is produced
during the first module. Each subsequent module release can add function to the previous
release. In a growing model, the process continues until a complete system is achieved.
Therefore, this model is much more flexible compared to other models of System
Development Life Cycle when conducting a screening and treatment program. This is how it
will be easier for every member to complete their designated modules and is flexible to
merge all the iterations. This methodology is more useful in web applications and task-based
companies.
20
Chapter 5
Implementation
21
5 Implementation
Implementation is done through website platform. Front end is in HTML, CSS, Bootstrap and
CNN Computer Vision Model is used, and all is connected with PHP AJAX,
python(Backend).
5.1 Algorithm:
Signup/Login or go to home page.
Can access image data, profiles, live well or contact us pages.
22
Chapter 6
Testing and Evaluation
23
6 Testing and Evaluation
6.1 System Testing:
Once the system has been successfully developed, testing has to be performed to ensure that the
system working as intended. This is also to check that the system meets the requirements stated
earlier. Besides that, system testing will help in finding the errors that may be hidden from the user.
There are few types of testing which includes the unit testing, functional testing and integration
testing. The testing must be completed before it is being deploy for user to use.
24
Unit Testing 3: Upload image
Objective: To ensure that the correct page with the correct navigation bar is loaded.
25
correct tab. for the specific
buttons
3 Verify that “facial Upload image tab is Pass
recognition” takes to loaded.
upload image page.
26
Chapter 7
Conclusion and Future Work
27
7 Conclusion and Future Work
7.1 Conclusion:
At the end of this research project, we will get a system that will be a more efficient and time saving
product for people. We will get an efficient working methodology for using modern technological
concepts in building a Digital Trading System. We hope that at the end of the project users will easily
search our platform according to their choice. The findings from this system inspire motivations to
carry out further research to develop an enhanced version of the proposed system .
28
Reference
29
Appendix
1) A book of Computer Vision: Algorithms and Applications Richard Szeliski (September
3, 2010)
2) Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception
architecture for computer vision. In: IEEE CVPR 2016: Computer Vision and Pattern
Recognition (2016)
30