Software Requirements Specification: Silicon Institute of Technology

Software Requirements
Specification
for
FACE RECOGNISATION
Prepared by Rajashree Rashmita
Silicon Institute Of Technology
25-01-2019
Software Requirements Specification for Face Recognisation System

Page ii
Table of Contents
Table of Contents...........................................................................................................................ii
1. Abstract...................................................................................................................................iii
2. INTRODUCTION..................................................................................................................iv
3. SYSTEM ARCHITECTURE................................................................................................iv
Input Unit................................................................................................................................................v
Processing Unit.......................................................................................................................................v
3.1 Enrollment Module.....................................................................................................................v
3.2 Authentication Module..............................................................................................................vi
3.3 Application Module...................................................................................................................vi
SYSTEM IMPLEMENTATION................................................................................................vii
Implementation of Door Lock Access by using Face Recognition.......................................................vii
Implementation of Person Detection along with Auto Alert Sending..................................................viii
4. SYSTEM DESCRRIPTION..................................................................................................ix
Internal Module:....................................................................................................................................ix
4.1 Software and Techniques for Face Recognition:.......................................................................ix
External Door module:............................................................................................................................x
5. SYSTEM ANALYSIS..............................................................................................................x
5.1 Texting Procedure......................................................................................................................x
The Proposed System Works As Follows :........................................................................................xi
6. CONCLUSION.....................................................................................................................xiv
7. REFERENCES......................................................................................................................xiv

Page iii
1. Abstract
Authentication is one of the significant issuesin the era of the information system. Among other
things, human face recognition (HFR) is one of the known techniques which can be used for
user authentication. As an important branch of biometric verification, HFR has been widely used
in many applications, such as video monitoring/surveillance system, human-computer
interaction. This project proposes a method for automatic door access system using face
recognition technique by using python programming and from OpenCV library Haar cascade
method. Object Detection using Haar feature-based cascade classifiers is an effective object
detection method proposed by Paul Viola and Michael Jones. This is the standalone security
device has been developed by using Raspberry Pi electronic development board and operated on
Battery power supply, wireless internet connectivity by using USB modem. Automatic e-mail
notification has been achieved by sending security alert mail to the user e-mail id. This proposed
is more effective, reliable, and this system consumes very less data and power compared to the
other existing systems.

Page iv
2. INTRODUCTION
In today’s world of connectivity and smart devices there is an urgent need to modify our existing
day to day objects and make them smart, also it is not the era when we can blindly trust the old
and conventional securitymeasures, specifically speaking is our door locks. To change and
modernize any object we need to eliminate its existing drawbacks and add extra functionality.
Face detection is more challenging because of some unstable characteristics, for example, glasses
and beard will impact the detecting effectiveness.
Moreover, different kinds and angles of lighting will make detecting face generate uneven
brightness ontheface, which will have an influence on the detection process. An intensive study of
OpenCV platform and its inbuilt libraries has been conducted to generate a code, which does
correct and reliable facial recognition with new and efficient use of hardware. This proposed
system also acts as a home security system for both Person detection and provide security for door
access control by using facial recognition for the home environment.
The human body is identified as an intruder within a home environment achieved by

capturing livevideo from web camera and processing will be done on captured video frames. The
web camera to capture the series of images as soon as the person press switch. The advantage of
this system is for accessing the door is that face detection and recognition are performed by using
face detection technique and the entire face recognition is completed by pressing single and tiny
push button switch. Facerecognition includes feature extraction from the facial image, recognition
or classification and feature reduction. As the world is progressing people are scared about the
safety of their possessions, information and themselves. With the model of Smart Door, a
profound impact is expected in the security industry and it is somewhat anticipated as the
timehascome to make all daily life objects interconnected and interactive. This model will be a
major contribution to the field of Home Security.
3. SYSTEM ARCHITECTURE
The Architecture of the proposed system is the design diagram which depicts the scope of the
project with the whole system design. In architecture diagram, it highlights the modules with its
various functions as a process. It aims to convey the internal design of the proposed system the
following Fig-2.1 shows the entire architecture of the proposed system.

Page v
Processing Unit
Enrollment
Module
Input
From Database
Authentication
Camera
Module
Application
Module
Fig2.1: System Architecture
Input Unit
In input unit, the Facial images for Face Recognition and Video frames for person detection are
captured from camera input devices respectively i.e. from Raspberry Pi Camera or Web camera.
Processing Unit
The data which is collected from Input unit that is captured Image and Video frames input is fed
into the processing unit in which the processing or calculations are performed onthe proposed
person detection and door lock system module, Here the processing unit is nothing but a
Raspberry Piboard, along with code scripts of the implemented modules.
3.1 Enrollment Module
In this enrollment module, the data which collected from input camera means person face image
is stored in the database. Before storing the image it will use feature extraction means it is
converted in Haar Feature-based Cascade Classifiers.
Enrollment
Feature
Image
Extraction
Fig2.2.1(a): Enrollment Module

Page vi
3.2 Authentication Module
In this module, we recognize and detect the input images. This module is connected to the outer
side of the door, where the captured image converted into Haar Feature- based Cascade
Classifiers. And matching this feature extraction image with the database.
Image Feature
Extraction
Result Matching
Fig2.2.1(b): Authentication Module
3.3 Application Module
The Application specific unit which consists of Door lock circuitry, it is associated with Door
lock system module of authentication module and it starts functioning according to results of
the module to perform door lock open/close operation based on Face Recognition.
Relay Lock
Circui System
Fig2.3: Application Module

Page vii
SYSTEM IMPLEMENTATION
There are two parts in this section. The first is the implementation of Door lock access by using
Face Recognition and the second is the implementation of person detection along with auto
alert sending.
Implementation of Door Lock Access by using Face Recognition
This project work proposes an idea of for face reorganization concept for accessing the
door lock system and it implemented with the help of OpenCV, which is a popular computer
vision library. Face recognition is an important application of image processing owing to its use
in many fields.
An effective face recognition system based on OpenCV is developed in the project. Face
recognition has been the best choice for the problem of biometrics and it has avarious type of
applications in our present life. An efficient face recognition system can be of great help in
forensic sciences, identification for law enforcement, authentication for banking and security
system, and giving preferential access to authorized users i.e. access control for secured areas
etc. A real-time door lock access system by face recognition system.
The algorithm used here is Local Binary Patterns Histograms (LBPH), based on Haar
Feature-based Cascade Classifiers is presented in the project. The technique used here we will
work with face detection. Initially, the algorithm needs a lot of positive images (images of faces)
and negative images (images without faces) to train the classifier. Then we need to extract
features from it. For this, Haar features shown in the below Fig-3.1 are used. They are just like
our convolution kernel. Each feature is a singlevalueobtained by subtracting the sum of pixels
under the white rectanglefrom the sum of pixels under the black rectangle.
Fig3.1: Haar Features

Page viii
Implementation of Person Detection along with Auto Alert Sending.
The proposed home security system is a machine learning based approach where a
cascade function is trained from a lot of positive and negative images. It is then used to detect
objects in other images. A procedural view of how this person detection works is shown in
below flowchart.
In the above Figure, we see the procedural view person detection process. In this system
first in authentication module is having small switch button, when the person presses the switch
button then the implemented code is the call. Then by using the camera the system capture the
image sequence and compare this images with the database. If the image is a match then in
application module get the signal to unlock the door. After unlocking the door the SMTP is to
send alert to an authorized personnel.

Page ix
4. SYSTEM DESCRRIPTION
4.1 Internal Module:
The following block diagram shows the internal module of door unlocking system. Which is have the
Raspberry Pi board, motor driving circuit, motor & camera.
Fig4.1: Internal Module
Raspberry Pi 3 Model B are used in it. The commands are sent to a driver circuit for processing the required
actionand the motor is being driven in either clockwise or anticlockwise as per requirement for locking or
unlocking the door.
4.2 Software and Techniques for Face Recognition:
This System is used Python 3.5+ software and python programming. With OpenCV (Open
Source Computer Vision) is a library of programming functions mainly aimed at real- time
computer vision.
• Haar Cascade Classifier
Object Detection using Haar feature-based cascadeclassifiers is an effective object

detection method proposed by Paul Viola and Michael Jones in their paper, "Rapid Object
Detection using a Boosted Cascade of Simple Features" in 2001. It is a machine learning based
approach where a cascade function is trained from a lot of positive and negative images. It is
then used to detect objects in other images.
• Local Binary Patterns Histograms Technique
The Local Binary Patterns methodology has its roots in 2D texture analysis. The basic
idea of Local Binary Patterns is to summarize the local structure in an image by comparing
each pixel with its neighborhood. Take a pixel as center and threshold its neighbors against. If
the intensity of the center pixel is greater-equal its neighbor, then denote it with 1 and 0 if not.
You’ll end up with a binary number for each pixel, just like 11001111. So with 8 surrounding

Page x
pixels, you’ll end up with 2^8 possible combinations, called Local Binary Patterns or
sometimes referred to as LBP codes. Thefirst LBP operator described in literature actually used
a fixed 3 x 3 neighborhood just like this.
External Door module:
The following block diagram shows the external module of door unlocking system.
Which is have the switch, Led by indication & camera. In this module whenthepersonpresses
the switch, then the code will run from the virtual environment of the raspberry pi board. Then
the camera is started, and from camera capture, the images and it will process in raspberry pi.
After matching and verifying the images the Led will glow it means the door is open.
Fig4.2: External Module
5. SYSTEM ANALYSIS
5.1 Texting Procedure
Install OpenCV and Python
1. Write the code for detecting and recognition of image through the camera.
2. Then start the training code, and the camera will open up, Accuracy depends on the number of
data sets as well as the quality and lighting conditions.
3.Take pictures of the person for face recognition after running create_database.py script. It
automatically creates Train folder in Database folder containing the face to be recognized. You

Page xi
can change the name from Train to the person’s name. The result in the creation of the real-time
database is recorded. The real-time database is created by using python. While executing it 100
images of each subject. Likewise, databases should be created a dictionary and it creates each
image size of variable pixels of height and width. While creating the database, the face images
must have different expressions, which is whya 0.38-second delay is given in the code for
creating the dataset. In this example, we take about 45 pictures/images and extract the face,
convert it into greyscale and save it to the database folder with its name.
4. Afterprogram execution, the database is created and then run face recognition program. And
the database is accessed by the program and it will match the live stream video image with it.
The Proposed System Works As Follows :
• Interface
the camera to capture live face images.
• Create a database of an authorized person by using Graphical user interface shown in below
image.
•Write name in the blank block in GUI model to store the person image on their name in the
database. And then click on start.

Page xii
•After click on start one video frame window will open. It captures the images and creates the
database.
• After competing capturing the images click on Train.
(Above two process images are following shown respectively.)


Page xiii

After click on start one video frame window will open. It captures the images and creates the
database.

Page xiv
• When the face is recognized then by using Simple Mail Transfer Protocol(SMTP) to send alert
to an authorized person while unlocking the locked door in the form of an email.

Page xv
6. CONCLUSION
In this proposed system door access system by using face recognition and along with the
e-Mail alert system has been presented. This system has been used with home door lock access
control based on face recognition method byverifying enrolled facial images. Concern persons
will be informed successfully about the person detection via e-mail alert generations along with
details attached. Face recognition is one of the several techniques for recognizing people. There
are several methods that can be used for that purpose. Some of the most common are using PCA
or eigenfaces. Though there are other new techniques more simple to understand the use and
implement but also with very good performance. The Haar Cascades algorithm is one of those
algorithms. As we show Haar Cascades has very good performance and is very accurate.
7. REFERENCES
[1] Hteik Htar Lwin, Aung Soe Khaing, Hla Myo Tun, “Automatic Door Access System Using
Face Recognition”, International Journal of Scientific & Technology Research Volume 4, Issue
06, June 2015.
[2]Samuel Lukas, Aditya Rama Mitra, Ririn Ikana Desanti, Dion Krisnadi "Student Attendance
System in Classroom Using Face Recognition Technique" IEEE 2016.
[3] RatnawatiIbrahim, "Study of Automated Face Recognition System for Office Door Access
Control Application", IEEE 2011
[4]Lerato Masupha, Tranos Zuva, Seleman Ngwira, Omobayo Esan, "Face Recognition
Techniques, their Advantages, Disadvantages and Performance Evaluation", IEEE 2015
Paul Viola, Michael J. Jones, "Robust Real-Time Face Detection", International Journal of
[5]
Computer Vision 57(2), 2004.
Ayushi Gupta, Ekta Sharma, NehaSachan, and Neha Tiwari, "Door Lock System through Face
Recognition Using MATLAB",

Software Requirements Specification: Silicon Institute of Technology

Uploaded by

Copyright:

Available Formats

Software Requirements Specification: Silicon Institute of Technology

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Software Requirements Specification: Silicon Institute of Technology

Uploaded by

Copyright:

Available Formats

What is the proposed system about?

What are the main steps of the proposed system?

Software Requirements

Prepared by Rajashree Rashmita

Silicon Institute Of Technology

The human body is identified as an intruder within a home environment achieved by

• Haar Cascade Classifier

Object Detection using Haar feature-based cascadeclassifiers is an effective object

• Local Binary Patterns Histograms Technique

Install OpenCV and Python

The Proposed System Works As Follows :

• After competing capturing the images click on Train.

(Above two process images are following shown respectively.)

You might also like