RASPBERRY PI BASED FACE RECOGNITION

SYSTEM FOR DOOR UNLOCKING

Akshay N. Patil 1, Rohit B. Ranavare2,
Dayasagar V. Ballal3,Asst. Prof. P. P. Kotekar4
123
Student, 4Assistant Professor, Department of Electronics & Telecommunication,
DMGOI, Kolhapur (India)

ABSTRACT
This paper deals with the design and implementation of Secure locking Automation using Raspberry Pi for Door
unlocking to provide essential security to our homes, bank lockers and associated control operations and send
security alert through the GSM module. Raspberry Pi operates and controls the video camera for capturing it
for turning ON a relay for door unlock. The module contains a secured face recognizer for automatic door
opening.

Keywords: Raspberry pi B+ model, Pi camera, PCA, SIM 300.

I.INTRODUCTION

A Face Recognition System is a system which automatically identifies and/or verifies the identity of a person
from digital images or a video frame from a video source. We use OPEN CV library that can be formulated as
given images of a scene identify or verify one or more persons in the scene using a stored database of faces. The
basic flow of the face recognition system is the image is captured by camera. The PCA algorithm detects the
face and extracts its features. After the extraction, system matches the captured images with data base images. In
the decision box the result of the matching is decide which is face match or the no face match.
After that SIM300 GSM module sends an security alert to the authorised person which is entry successful or
unauthorised person trying to unlock. Tools used are normal and widely applied for current applications and
python as the main programming language & Linux based operating system, one can use C, JAVA or Perl also.
On being successful, with further optimizations and improvements, the system may be implemented in real time
systems requiring user authentication such as attendance systems, ATM security, Network security, In Bank
locker, Home automation.

II. PROPPSED WORK

The aim of our project is to provide a high security system using face recognition on Raspberry Pi board and
send an alert to the authorised person via GSM module, this will increase the security of our project. The
proposed work is as follows:
1) Interfacing of camera module to capture live Face image.
2) Create a database of authorized person

1091 | P a g e
 3) Capture current face, save it and compare with data base image.
4) Interface GSM module to send security alert to Authorized person while unlocking the locked door.
5) Interface relay as an output module.

III.METHODOLOGY

Fig 1: Block diagram of “Raspberry pi based face recognition system for door unlocking”.

IV.WORKING

In above figure 1 show the basic block diagram of the Raspberry pi based face recognition system for door
unlocking. Our project system can be operated in two different sections, i.e. one for capturing and creating a
data base and the other section is to capture the image and which is used for identifying or comparing the
images in the database. Here in the second section we use Eigen faces methodology of face recognition for
finding the matches.
Camera module: Camera module is Pi camera interfacing to the raspberry pi module. It is used for captures an
image and send captured image to the Raspberry pi module.
Raspberry pi module: Raspberry pi B+ module is small computer board. When image taken by the raspberry pi
it is compared with Eigen face image. At the first time when we capture the image to create a data base
raspberry pi module capture six types of the images to create a data base in the system and this data base is
compared with the live captured image. After comparing two images output is positive/negative then it gives
commands to GSM module.
GSM module: GSM module is used to sending a message to the authorities after comparison output is positive
or negative. If output is positive then "Person Identified!! DOOR OPENS!!" message send to the authority
person otherwise send “unknown person is trying to unlock the door”.

1092 | P a g e
 Fig 2: Flowchart of Image capturing and database comparison
Figure 2 shows the basic flow of the system to Image capturing and database comparison.

V.CONCLUSION
The design of the face recognition system using Raspberry pi can make the smaller, lighter and with lower
power consumption, so it is more convenient than the PC-based face recognition system. Because of the open
source code, it is freer to do software development on Linux. We use Principle component analysis algorithm
for the face recognition and detection process. Also send a security alert message to the authorized person
utilities. The developed scheme is cheap, fast, highly reliable and provides enough flexibility to suit the
requirements of different systems

VI. FUTURE SCOPE

Using raspberry pi the current project can be modified by an Infrared camera interfacing it can be used in Smart
Surveillance Monitoring security system which any type of public security is using Living body detection or
spying, Also it can be used in Attendance system of the class, Also some profound applications can be
implemented using interfacing of Raspberry pi and Arduino UNO board like sensor application of smartcard
swapping, finger detection, alcohol detection, agriculture humidity sensing, Temperature sensing using web
server, and many more.

VII. ACKNOWLEDGEMENT

First and foremost we want to thank our guide Asst. Prof. P. P. Kotekar for constant encouragement and noble
guidance. With great pleasure and gratefulness, we extend our deep sense of gratitude to Prof. J. K. Ravan,
HOD, E&TC Engg. Dept. of for giving us an opportunity to accomplish our paper and to increase our
knowledge. Lastly we wish each and every person involved in making our dissertation successful. Thank you.

1093 | P a g e
REFERENCES
[1] K.Gopalakrishnan, V.Sathish Kumar “embedded image capturing system using raspberry pi system”
international Journal of Emerging Trends & Technology in Computer Science (IJETTCS) Volume 3,Issue2,
March–April 2014.WebSite: www.ijettcs.org.
[2] Anoop Mishra “Embedded Image Capturing & Digital Converting Process using Raspberry pi System
interfacing and Comparison of Generation 2 verses Generation 1 models in Raspberry pi” et al, /(IJCSIT)
International Journal of Computer Science and Information Technologies, Vol. 6 (2), 2015, 1798-1801.
[3] Sanjana Prasad, P. Mahalakshmi, A. John Clement Sunder R. Swathi “Smart Surveillance Monitoring
System Using Raspberry PI and PIR Sensor” International Journal of Computer Science and Information
Technologies (IJCSIT) ISSN 0975-9646 Vol.5 (6), 2014, 7107-7109
[4] Raspberry Pi Face Recognition Treasure Box Created by Tony Di Cola.
[5] An Introduction to Face Recognition Technology, Shang-Hung Lin, Ph.D. IC Media Corporation,
[email protected].
[6] Facial Recognition Technology A Survey of Policy and Implementation Issues Lucas D. Introna Lancaster
University, UK.
[7]Keun-Chang Kwak and W. Pedrycz,“Face recognition using an enhanced independent component analysis
approach inNeural Networks, IEEE Transactions on, vol.18, no.2, pp.530–541, 2007.
[8] Medak Teena Ravali, Prof. Rangasai Komaragiri “Image processing platform on raspberry pi for face
recognition” Global Journal of Advanced Engineering Technologies, ISSN 2277-6370 Vol3, Issue4- 2014.
[9] Paola Campadelli and Raffaella Lanzarotti, “A face recognition system based on local feature
characterization” in Advanced Studies in Biometrics.
[10] Kuldeep Soni, Indian Institute of Technology Kanpur,June 22, 2014,[email protected]
[11] Raspberry Official site - http://www.raspberrypi.org

1094 | P a g e