Design and Construction of Face

Recognition Door Lock System Using

Raspberry Pi

SUBMITTED BY SUPERVISED BY
Md. Uzzal Mia Sree Krishna Das
Reg. No: WUB 09/16/60/3397 Lecturer
Mohammad Ashikuzzaman Ashik Department of Electrical & Electronic Engineering
Reg. No: WUB 09/16/60/3398

World University of Bangladesh (WUB)

 Background
The most important feature of any home security system is to detect the people who
enter or leave the house. Instead of monitoring that through passwords or pins unique
faces can be made use of as they are one’s biometric trait. These are innate and cannot
be modified or stolen easily. The level of security can be raised by using face detection.
The proposed face recognition door lock security system has been developed to prevent
robbery in highly secure areas like home environment with lesser power consumption
and more reliable standalone security device for both intruder detection and for door
security. This system is powered by raspberry pi circuit. Raspberry pi electronic board
is operated on battery power supply, wireless internet connectivity by using USB
modem, it includes pi camera, PIR motion sensor and a door. Whenever the person
comes in front of the door, it recognizes the face and if it is registered then it unlocks
the door, if the face is not registered it will raise an alarm.
1
 Introduction

In today 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 security measures, specifically speaking is our
door locks. To change and modernize any object we need to eliminate its existing
drawbacks and add extra functionality. The major drawbacks in a common door lock are
that anyone can open a conventional door lock by duplicating or stealing the key and its
simply impossible if we want our friends and family to enter our house, without being
actually present over there. Thus why not just eliminate these problems. So, to simply
convert this normal door lock into a smart lock, which can open the door whenever we
turn up in front of the gate or when we want it to open up for someone else without being
physically present, we need to modify the door.
2
 Introduction (Continued)

So an era has come where devices can interact with its users and at the same time
ensure of their safety and keep improvising themselves. Users could operate on a
touchscreen to select entering the house by recognizing the face or motors and/or
adding a digital number pad to take inputs from the user or adding infra-red or
Bluetooth modules to operate these devices. For face recognition, an image will be
capture by a pi camera and pre-processed by raspberry pi like converting, re-sizing
and cropping. Then face detection and recognition are perform. Once the face is
recognized by the classifier based on a presorted image library, the image will be sent
to a remote console waiting for house owner’s decision. For the passcode part, users
could enter or reset passcode through a keypad.

3
 Objectives

• To design and construct of face authenticated real time security

system.
• To capture the image and verify the captured image with the
database, if matching found then the access to locking device is
allowed.

4
 Methodology
• Creating an idea for face recognition door lock system using the
raspberry pi.
• Designing a block diagram to know which components are needed
to construct it.
• Designing a schematic for creating the circuit board.

• Programming for the raspberry pi to control the video camera for

capturing the images.
• Setting all the components in with raspberry pi on board.

• Turn on the device for the experimental.

• And finally run the device.

5
 Flow Chart

Fig. 1: Flow chart of face recognition door lock system using raspberry pi.
7
 Block Diagram

Fig. 2: Block diagram of face recognition door lock system using raspberry pi.

6
 Schematic Diagram

Fig. 3: Schematic diagram of face recognition door lock system using raspberry pi
7
 Working Principle
In the above figures, showing the basic schematic diagram of the raspberry pi based face
recognition system for door unlocking. Our project system can be operated in two
different sections, for instance, one for capturing and creating a database and the other
section is to capture the image and which is used for identifying or comparing the images
in the database. In this system, a single-board computer called “raspberry pi” is used to
execute all the system where it recognizes faces. Whenever someone stands in front of
the PIR motion sensor then it detects the person and gives an output signal to the GPIO
pin of the raspberry pi. After detecting the person camera module captures the photo of
that person & compare the photo with the stored photos in the directory. If the photo is
the same as the directory photo then the door is unlocked otherwise the buzzer will give
you an alarm. This procedure is secured for any place where unauthorized access is
restricted.
8
 Required Components

 Raspberry Pi 3 B
 Camera Module

 Door Lock Solenoid

 Buzzer

 PIR (Passive Infrared) Motion Sensor

9
 Physical Diagram of Raspberry Pi
Raspberry pi is the central core part of
the whole system. It is used to get
command from either the android
tablet or PC and according to the
command, control the appliances
connected to it on the output port. It is
connected to an android tablet or
phone via a router by using wi-fi or
Fig. 4: Physical diagram of raspberry pi
ethernet cable. It is also used as a
webserver to store in the database and
provides it to the webpage to display
the webpage. 10
Schematic Diagram of Raspberry Pi

Fig. 5: Schematic diagram of raspberry pi

11
 Pi Camera

Camera module is interfaced to the

raspberry pi module. It is used to
capture images and send the clicked
images to the raspberry pi module.
Camera contains LEDs and flashes to
handle light conditions that are not
explicitly supplied by the environment
and these light conditions are known as
ambient light conditions.

Fig. 6: Physical diagram of Pi camera

12
Schematic Diagram of Pi Camera

Fig: 8: Schematic diagram of Pi camera

13
 PIR Motion Sensor

PIR (passive infrared) motion sensor

detects body heat (infrared energy).
Passive infrared sensors are the most
widely used motion in home security
systems. When your system is armed,
your motion sensors are activated.
Once the sensor warms up, it can
detect heat and movement in the
Fig. 9: Physical diagram of PIR motion sensor surrounding areas, creating a
protective “grid.”

14
PIR Motion Sensor (Continued)

Fig. 10: Schematic diagram of PIR motion sensor

15
 List of Components With Price
Table 1: Estimate of the cost our project
Total
Sl. Unit Price
Name of Items Quantity Price in
No. in BDT
BDT

01 Raspberry Pi 1 3600 3600

02 Camera module 1 1300 1300

03 Solenoid valve 1 700 700

04 PIR motion sensor 1 100 100

04 Buzzer 1 80 80

05 Pi power supply 1 500 500

06 Buck converter 1 100 100

07 Others 100 100

Total 6,480
16
Physical Model of Our Project

Fig. 11: Physical Model of Our Project

17
 Applications

 It can be used in any residential area.

 It can be used in government office & highly secured zone.

 It can be used where unauthorized person entry is restricted.

18
 Advantages

High accuracy allows avoiding false identification.

More secure due to face detection.

19
 Discussion
The experimental results shows two different cases like if it is an
authenticated person then the door will be opened automatically and in
the case of unauthenticated person the door will remain closed. The
snap shot of the authenticated person is taken. The captured image is
compared with the image in the database. With these features the
image is decided to be an authenticated one. Once the image is
declared to be an authenticated one, then the door of the system will
be opening automatically. Sometimes unknown person may also enter,
this cannot be avoided but at all times everyone will not be aware of
the intruder. For this type of situation this model proposes a solution.
If the captured image is an unauthenticated person and the door will
remain closed itself. Face recognition system has been developed in
order to study the potential application for automated door access
control system.
20
 Conclusion
We successfully finished a face recognition door lock system as
we planned. The passcode and face recognition works well. There
is high accuracy in recognizing house owner faces and it could
realize sending the matched face image to another Raspberry Pi in
time and give a good output. And it takes a little bit time to
recognize. At all, we all are satisfied to build it.

21
 Future work

 Our project can be implemented real time video monitoring

security system.
 It can be implemented in wireless attendance system of
university, school and college etc.

22
Thank
You