DOMAIN DESCRIPTION

• A security domain is the list of objects a subject is allowed to access.

More broadly defined, domains are groups of subjects and objects with
similar security requirements.
• The security domain operates using numerous practices, such as
concentric and layered protection, redundancy, crime prevention
through environmental design, and psychological deterrence.
• All concepts share a common purpose: keep the adversary away from
the target. 
 ALGORITHMS

• IMAGE PROCESSING:

Image processing algorithms that typically need to be performed for

complete image capture can be categorized into low-level methods, such as color
enhancement and noise removal, medium-level methods such as compression and
binarization, and higher-level methods involving segmentation, detection, and
recognition algorithms extract semantic information from the captured data. 
• MACHINE LEARNING:

Machine learning (ML) is the scientific study of algorithms

and statistical models that computer systems use to perform a specific
task without using explicit instructions, relying on patterns and
inference instead. It is seen as a subset of artificial intelligence. Machine
learning algorithms build a mathematical model based on sample data,
known as "training data", in order to make predictions or decisions
without being explicitly programmed to perform the task.
 ABSTRACT
• The purpose of this project is to reinforce security of the conventional
ATM model. We have posited a new concept that enhances the
overall experience, usability and convenience of the transaction at the
ATM.
• Features like face recognition and mobile app conformation are used
for the enhancement of security of accounts and privacy of users.
• Face recognition technology helps the machine to identify each and
every user uniquely thus making face as a key.
• This completely eliminates the chances of fraud due to theft and
duplicity of the ATM cards. Moreover, the mobile Application control
helps the user to provide the user to allow permission to access the
ATM card by their friends.
 EXISTING SYSTEM
• In existing system RFID card is used as ATM card, IR sensor in order
to sense the presence of the card holders and to turn on Fan and Light,
if ATM is tampered then SMS is sent to two main stations via GSM.
Based on WI fall detection get security, that network access is not that
much secured.
PROPOSED SYSTEM
• The study is focused on Design and Implementation of Face Detection based ATM
Security System using Embedded Linux Platform.
• The system is implemented on the credit card size with extended capability of
open source Computer Vision (OpenCV) software which is used for Image
processing operation.
• High level security mechanism is provided by the consecutive actions such as
initially system captures the human face and check whether the human face is
detected properly or not.
• If the face is not detected properly, then there will be a alert in a mobile
application for further process. If the user press yes the process will continue. If
the user press no then the process will be terminated
 BLOCK DIAGRAM
ATM SECURITY SYSTEM
Dataset

Capturing Face Detection

yes
image ATM process
no
Mobile
application of
account holder yes
no

Process
Terminated
 MODULE DESCRIPTION
Module 1:
Facial recognition using OpenCV and capturing the image, Comparing with
the datasets and displaying the result as MATCHED if the faces are same.
Module 2:
If the faces are mismatched then there will be a alert in mobile application
of account holder. The user of account will be given two buttons YES and
NO in app.
Module 3:
If user press YES then the ATM process will continue ,Whereas if user press
NO then the process will be terminated.
 MODULE 1
• ATM’s camera and its computer will automatically initiate a face
recognition procedure, whenever the computer detects a human face in
camera obtains a picture of your face, the computer compares the image
of your face to the images of registered customers in its dataset .
• If your face (as seen by the ATMs camera) matches the picture of the in
the data base you are automatically recognized by the machine.
• An Image may be defined as a two dimensional function f(x,y) where x
and y are spatial(plane) coordinates x, y is called intensity or gray level
of the image at that point. When x, y and the amplitude values of f are all
finite, discrete quantities.
 REFERENCE
• Hossain Reza Babaei, “Face Recognition application for Automatic
Teller Machines(ATM)”, 2012 International Conference on
Information and Knowledge management, IACSIT press, Singapore.
• Mohsin Karovaliya,Saifali Karedia, Sharad Oza, Dr.D.R.Kalbande,
“Enhanced security for ATM machine with otp and Facial recognition
freatures”, International conference on advanced computing
Technologies and application(ICACTA-2015).
• Dr.G.Ranjitham, Senthamilarasu monoharan, “Face recognition and
Fingerprint Based New Generation ATM”, International Journal of
Innovative Science and Reserch Technology, March-2018.
 CONCLUSION
• The combination of Biometrics will always result in high security. The
FACE ID, MESSAGE ALERT and PIN as combined, they result in a
hard-secure authentication.