You are on page 1of 8

1

SMART IoT VISUALISED


DOOR LOCKING SYSTEM
PROBLEM STATEMENT 2
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 security measures,
specifically speaking is our door locks.
The major drawbacks in a common door lock are that
anyone can open a conventional door lock by stealing the
key and its simply impossible if we want our friends and
family to enter our house, without being actually present
over there.
KEY 3
We propose 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. So an era has come where devices can
interact with its users, operate the door and at the
same time ensure of their safety and keep improvising
themselves.
COMPONENTS 4
•RASPBERRY Pi 3 B+
•PI CAMERA
•MOTION SENSOR
HARDWARE •SERVO MOTOR

•AWS DATABASE
•ANDROID
SOFTWARE
BLOCK DIAGRAM 5
PI
CAMERA

MOTION Raspberry SERVO


SENSOR Pi MOTOR

CLOUD
DATABASE
SCHEMA 6
WORKING PRINCIPLE 7
Let us consider a house with 3 family members. The facial recognition of each family member is
scanned and uploaded on the AWS cloud server. As many as 3-4 trails are carried out, so that there
wont be any hitch during recognition. The data is uploaded on the server and is trained by machine
learning methodology.
Putting the smart device into use, the family member has to show up at the door, which will be sensed
by the PIR motion sensor, which causes the raspberry pi to come out of hibernate state and turns on
the pi camera, the hibernate state is used to conserve power and increase the efficiency of it.
Scenario 1
When an authorized person tries to enter the house, the pi camera scans the image of the person with
the help of digital image processing and will try to match with the data present in database, if the
image scanned by the pi camera matches with the one stored in the database, the door will get
unlocked and will allow the user to get in.
Scenario 2
Considering a situation where un authorized person is present at the door and tries to unlock the door,
the motion sensor and pi camera come into act, where the pi camera captures the image of the
person and compares with that stored in the database, if the captured image doesn’t match with the
ones stored in the database, then the image of the unauthorized person will be sent to one authorized
person through android app connecting the cloud server. The authorized person gets the notification
immediately where he has an option to either allow the person in or reject him.
CONCLUSION
We successfully completed the proposal of a face
recognition door locking system as we planned. The
passcode response is quick and face recognition is precise.
There is high accuracy in recognizing authorized persons and
in case of unauthorized person it’s quick enough to send the
information to the authorized person so that he could either
allow the person in or reject him. It takes minimum time to
recognize. This way we can increase the security of our
houses. This is a great platform for us to build such cool
things, and we are glad to be a part of it.

You might also like