AN ATM WITH AN EYE

1. INTRODUCTION
The rise of technology in India has brought into force many types of equipment that
aim at more customer satisfaction. ATM is one such machine which made money
transactions easy for customers to bank. The other side of this improvement is the
enhancement of the culprits probability to get his unauthentic share. Traditionally,
security is handled by requiring the combination of a physical access card and a PIN
or other password in order to access a customers account. This model invites
fraudulent attempts through stolen cards, badly-chosen or automatically assigned
PINs, cards with little or no encryption schemes, employees with access to nonencrypted customer account information and other points of failure.
Our paper proposes an automatic teller machine security model that would
combine a physical access card, a PIN, and electronic facial recognition. By forcing
the ATM to match a live image of a customers face with an image stored in a bank
database that is associated with the account number, the damage to be caused by
stolen cards and PINs is effectively neutralized. Only when the PIN matches the
account and the live image and stored image match would a user be considered fully
verified. A system can examine just the eyes, or the eyes nose and mouth, or ears,
nose, mouth and eyebrows, and so on.
In this paper , we will also look into an automatic teller
machine security model providing the customers a cordless,
password-free way to get their money out of an ATM. Just step up to
the camera while your eye is scanned. The iris -- the colored part of
the eye the camera will be checking -- is unique to every person,
more so than fingerprints.

(BRIG ECE)

AN ATM WITH AN EYE

2. ATM SYSTEMS
Our ATM system would only attempt to match two (and later, a
few) discrete images, searching through a large database of
possible matching candidates would be unnecessary. The process
would effectively become an exercise in pattern matching, which
would not require a great deal of time. With appropriate lighting and
robust learning software, slight variations could be accounted for in
most cases. Further, a positive visual match would cause the live
image to be stored in the database so that future transactions would
have a broader base from which to compare if the original account
image fails to provide a match thereby decreasing false negatives.
When a match is made with the PIN but not the images, the
bank could limit transactions in a manner agreed upon by the
customer when the account was opened, and could store the image
of the user for later examination by bank officials. In regards to bank
employees gaining access to customer PINs for use in fraudulent
transactions, this system would likewise reduce that threat to
exposure to the low limit imposed by the bank and agreed to by the
customer on visually unverifiable transactions.
In the case of credit card use at ATMs, such a verification
system would not currently be feasible without creating an overhaul
for the entire credit card issuing industry, but it is possible that
positive results (read: significant fraud reduction) achieved by this
system might motivate such an overhaul.
The last consideration is that consumers may be wary of the privacy
concerns raised by maintaining images of customers in a bank
database, encrypted or otherwise, due to possible hacking attempts
or employee misuse. However, one could argue that having the
image compromised by a third party would have far less dire
consequences than the account information itself. Furthermore,
since nearly all ATMs videotape customers engaging in transactions,
it is no broad leap to realize that banks already build an archive of
their customer images, even if they are not necessarily grouped
with account information itself.

(BRIG ECE)

AN ATM WITH AN EYE

3. HARDWARE AND SOFTWAR

ATMs contain secure cryptoprocessors, generally within an IBM PC compatible
host computer in a secure enclosure. The security of the machine relies mostly on the
integrity of the secure cryptoprocessor: the host software often runs on a commodity
operating
system.In-store ATMs typically connect directly to their ATM Transaction Processor
via a modem over a dedicated telephone line, although the move towards Internet
connections is under way.
In addition, ATMs are moving away from custom circuit boards (most of
which are based on Intel 8086 architecture) and into full-fledged PCs with commodity
operating systems such as Windows 2000 and Linux. An example of this is Banrisul,
the largest bank in the South of Brazil, which has replaced the MS-DOS operating
systems in its automatic teller machines with Linux. Other platforms include RMX
86, OS/2 and Windows 98 bundled with Java. The newest ATMs use Windows XP or
Windows XP embedded.
Block Diagram of ATM

CPU
Magnetic or chip card Reader
Pin pad
Secure Crypto processors
Function key and buttons
Display
Record Printer

(BRIG ECE)

AN ATM WITH AN EYE

4. FACIAL RECOGNITION
The main issues faced in developing such a model are keeping
the time elapsed in the verification process to a negligible amount,
allowing for an appropriate level of variation in a customers face
when compared to the database image, and that credit cards which
can be used at ATMs to withdraw funds are generally issued by
institutions that do not have in-person contact with the customer,
and hence no opportunity to acquire a photo.
Because the system would only attempt to match two (and
later, a few) discrete images, searching through a large database of
possible matching candidates would be unnecessary. The process
would effectively become an exercise in pattern matching, which
would not require a great deal of time. With appropriate lighting and
robust learning software, slight variations could be accounted for in
most cases. Further, a positive visual match would cause the live
image to be stored in the database so that future transactions would
have a broader base from which to compare if the original account
image fails to provide a match thereby decreasing false negatives.
When a match is made with the PIN but not the images, the
bank could limit transactions in a manner agreed upon by the
customer when the account was opened, and could store the image
of the user for later examination by bank officials. In regards to bank
employees gaining access to customer PINs for use in fraudulent
transactions, this system would likewise reduce that threat to
exposure to the low limit imposed by the bank and agreed to by the
customer on visually unverifiable transactions.
In the case of credit card use at ATMs, such a verification
system would not currently be feasible without creating an overhaul
for the entire credit card issuing industry, but it is possible that

(BRIG ECE)

AN ATM WITH AN EYE

positive results (read: significant fraud reduction) achieved by this
system might motivate such an overhaul.
The last consideration is that consumers may be wary of the
privacy concerns raised by maintaining images of customers in a
bank database, encrypted or otherwise, due to possible hacking
attempts or employee misuse. However, one could argue that
having the image compromised by a third party would have far less
dire consequences than the account information itself. Furthermore,
since nearly all ATMs videotape customers engaging in transactions,
it is no broad leap to realize that banks already build an archive of
their customer images, even if they are not necessarily grouped
with account information.
SOFTWARE SPECIFICATION
For most of the past ten years, the majority of ATMs used
worldwide ran under IBMs now-defunct OS/2. However, IBM hasnt
issued a major update to the operating system in over six years.
Movement in the banking world is now going in two directions:
Windows and Linux. NCR, a leading world-wide ATM manufacturer,
recently announced an agreement to use Windows XP Embedded in
its next generation of personalized ATMs (crmdaily.com.) Windows
XP Embedded allows OEMs to pick and choose from the thousands
of components that make up Windows XP Professional, including
integrated multimedia, networking and database management
functionality. This makes the use of off-the-shelf facial recognition
code more desirable because it could easily be compiled for the
Windows XP environment and the networking and database tools
will already be in place.
Many financial institutions are relying on Windows NT,
because of its stability and maturity as a platform.The ATMs send
database requests to bank servers which do the bulk of transaction
processing (linux.org.) This model would also work well for the
proposed system if the ATMs processors were not powerful enough
to quickly perform the facial recognition algorithms.
FACIAL RECOGNITION TECHNIQUE
There are hundreds of proposed and actual implementations
of facial recognition technology from all manner of vendors for all
manner of uses. However, for the model proposed in this paper, we
are interested only in the process of facial verification matching a
live image to a predefined image to verify a claim of identity not in
the process of facial evaluation matching a live image to any
image in a database. Further, the environmental conditions under
which the verification takes place the lighting, the imaging system,
the image profile, and the processing environment would all be
controlled within certain narrow limits, making hugely robust

(BRIG ECE)

AN ATM WITH AN EYE

software unnecessary .One leading facial recognition algorithm class
is called image template based. This method attempts to capture
global features of facial images into facial templates. What must be
taken into account, though, are certain key factors that may change
across live images: illumination, expression, and pose (profile.)

The natural conclusion to draw, then, is to take a frontal image

for the bank database, and to provide a prompt to the user, verbal
or otherwise, to face the camera directly when the ATM verification
process is to begin, so as to avoid the need to account for profile
changes. With this and other accommodations, recognition rates for
verification can rise above 90%. A system can examine just the
eyes, or the
eyes
nose
and mouth, or
ears,
nose,
mouth
and
eyebrows,
and so on
The conclusion
to be drawn
for this project,
then, is that
facial
verification
software
is
currently up
to the task of
providing
high
match
rates for use
in
ATM
transactions.
What remains is
to find an
appropriate
open-source
local
feature
analysis
facial
verification
program that can be used on a variety of platforms, including
embedded processors, and to determine behavior protocols for the
match / non-match cases.

(BRIG ECE)

AN ATM WITH AN EYE

5. OUR METHODLOGY
The first and most important step of this project will be to
locate a powerful open-source facial recognition program that uses
local feature analysis and that is targeted at facial verification. This
program should be compilable on multiple systems, including Linux
and Windows variants, and should be customizable to the extent of
allowing for variations in processing power of the machines onto
which it would be deployed.We will then need to familiarize
ourselves with the internal workings of the program so that we can
(BRIG ECE)

AN ATM WITH AN EYE

learn its strengths and limitations. Simple testing of this program
will also need to occur so that we could evaluate its effectiveness.
Several sample images will be taken of several individuals to be
used as test cases one each for account images, and several
each for live images, each of which would vary pose, lighting
conditions, and expressions.
Once a final program is chosen, we will develop a simple ATM
black box program. This program will server as the theoretical ATM
with which the facial recognition software will interact. It will take in
a name and password, and then look in a folder for an image that is
associated with that name. It will then take in an image from a
separate folder of live images and use the facial recognition
program to generate a match level between the two. Finally it will
use the match level to decide whether or not to allow access, at
which point it will terminate. All of this will be necessary, of course,
because we will not have access to an actual ATM or its software.
Both pieces of software will be compiled and run on a
Windows XP and a Linux system. Once they are both functioning
properly, they will be tweaked as much as possible to increase
performance (decreasing the time spent matching) and to decrease
memory footprint.
Following that, the black boxes will be broken into two
components a server and a client to be used in a two-machine
network. The client code will act as a user interface, passing all
input data to the server code, which will handle the calls to the
facial recognition software, further reducing the memory footprint
and processor load required on the client end. In this sense, the thin
client architecture of many ATMs will be emulated.
We will then investigate the process of using the black box
program to control a USB camera attached to the computer to avoid
the use of the folder of live images. Lastly, it may be possible to
add some sort of DES encryption to the client end to encrypt the
input data and decrypt the output data from the server knowing
that this will increase the processor load, but better allowing us to
gauge the time it takes to process.

6. IRIS RECOGNITION
Inspite of all these security features, a new technology has
been developed. Bank United of Texas became the first in the United
States to offer iris recognition technology at automatic teller
(BRIG ECE)

AN ATM WITH AN EYE

machines, providing the customers a cardless, password-free way to
get their money out of an ATM. There's no card to show, there's no
fingers to ink, no customer inconvenience or discomfort. It's just a
photograph of a Bank United customer's eyes. Just step up to the
camera while your eye is scanned.

(BRIG ECE)

AN ATM WITH AN EYE

(BRIG ECE)

10

AN ATM WITH AN EYE

The iris -- the colored part of the eye the camera will be
checking -- is unique to every person, more so than fingerprints.
And, for the customers who can't remember their personal
identification number or password and scratch it on the back of their
cards or somewhere that a potential thief can find, no more fear of
having an account cleaned out if the card is lost or stolen.

(BRIG ECE)

11

AN ATM WITH AN EYE

7. HOW THE SYSTEM WORK

When a customer puts in a bankcard, a stereo camera locates
the face, finds the eye and takes a digital image of the iris at a
distance of up to three feet. The resulting computerized "iris code"
is compared with one the customer will initially provide the bank.
The ATM won't work if the two codes don't match. The entire process
takes less than two seconds.
The system works equally well with customers wearing
glasses or contact lenses and at night. No special lighting is needed.
The camera also does not use any kind of beam. Instead, a special
lens has been developed that will not only blow up the image of the
iris, but provide more detail when it does. Iris scans are much more
accurate than other high-tech ID systems available that scan voices,
faces and fingerprints.
Scientists have identified 250 features unique to each
person's iris -- compared with about 40 for fingerprints -- and it
remains constant through a person's life, unlike a voice or a face.
Fingerprint and hand patterns can be changed through alteration or
injury. The iris is the best part of the eye to use as a identifier
because there are no known diseases of the iris and eye surgery is
not performed on the iris. Iris identification is the most secure,
robust and stable form of identification known to man. It is far safer,
faster, more secure and accurate than DNA testing. Even identical
twins do not have identical irises. The iris remains the same from 18
months after birth until five minutes after death.
When the system is fully operational, a bank customer will
have an iris record made for comparison when an account is
opened. The bank will have the option of identifying either the left or
right eye or both. It requires no intervention by the customer. They
will simply get a letter telling them they no longer have to use the
PIN number. And, scam artists beware, a picture of the card holder
won't pass muster.

(BRIG ECE)

12

AN ATM WITH AN EYE

The first thing the camera will check is whether the eye is
pulsating. If we don't see blood flowing through your eye, you're
either dead or it's a picture

(BRIG ECE)

13

AN ATM WITH AN EYE

(BRIG ECE)

14

AN ATM WITH AN EYE

8. APPLICATIONS
Reliability
ATMs are generally reliable, but if they do go wrong customers will
be left without cash until the following morning or whenever they
can get to the bank during opening hours. Of course, not all errors
are to the detriment of customers; there have been cases of
machines giving out money without debiting the account, or giving
out higher value notes as a result of incorrect denomination of
banknote being loaded in the money cassettes. Errors that can
occur may be mechanical (such as card transport mechanisms;
keypads; hard disk failures); software (such as operating system;
device driver; application); communications; or purely down to
operator error.

SECURITY
such as malls, grocery stores, and restaurants. The other side of this
improvement is the enhancement of the culprits probability to get
his unauthentic share. ATMs are
Early ATM security focused
on making the ATMs invulnerable to physical attack; they were
effectively safes with dispenser mechanisms. ATMs are placed not
only near banks, but also in locations a quick and convenient way to
get cash. They are also public and visible, so it pays to be careful
when you're making transactions. Follow these general tips for your
personal safety.
Stay alert.
If an ATM is housed in an enclosed area, shut the entry door
completely behind you. If you drive up to an ATM, keep your car
doors locked and an eye on your surroundings. If you feel uneasy or
sense something may be wrong while you're at an ATM, particularly
at night or when you're alone, leave the area.
Keep you PIN confidential.
Memorize your Personal Identification Number (PIN); don't write it on
your card or leave it in your wallet or purse. Keep your number to
yourself. Never provide your PIN over the telephone, even if a caller
identifies himself as a bank employee or police officer. Neither
person would call you to obtain your number.
Conduct transactions in private.
Stay squarely in front of the ATM when completing your transaction
so people waiting behind you won't have an opportunity to see your
PIN being entered or to view any account information. Similarly, fill
out your deposit/withdrawal slips privately.
Dont flash your cash.
(BRIG ECE)

15

AN ATM WITH AN EYE

If you must count your money, do it at the ATM, and place your cash
into your wallet or purse before stepping away. Avoid making
excessively large withdrawals. If you think you're being followed as
you leave the ATM, go to a public area near other people and, if
necessary, ask for help.
Save receipt.
Your ATM receipts provide a record of your transactions that you
can later reconcile with your monthly bank statement. If you notice
any discrepancies on your statement, contact your bank as soon as
possible. Leaving receipts at an ATM can also let others know how
much money you've withdrawn and how much you have in your
account.
Guard your card.
Don't lend your card or provide your PIN to others, or discuss your
bank account with friendly strangers. If your card is lost or stolen,
contact your bank immediately.
Immediately report any crime to the police.
Contact the Department Of Public Security or your local police
station for more personal safety information.

(BRIG ECE)

16

AN ATM WITH AN EYE

9.ADVANTAGES AND DISADVANTAGES

ADVANTAGES
1. The entire process will takes time less than 2 seconds as facial recognition
code more desirable because it could easily be compiled for the windows xp
environment and the networking and database tools will already be in place.
2. The system works equally well with customers wearing glasses or contact
lenses and at night no special lighting is needed. The camera also does not use
any kind of beam.
3. The iris is the best part of the eyes to use as a identifier because there are no
know diseases of the iris and eye surgery is not performed on the iris.
4. It is far safer, faster, more secure and accurate than DNA testing. Even
identical twins do not have identical irises. The iris remains the same from 18
months after birth until five minutes after death.
DISADVANTAGES
1. Iris scanners are significantly more expensive than some other forms of
biometrics, password or proxy card security system.
2. Iris recognition is very difficult to perform at a distance larger than a few
meters and if the person to be identified is not cooperating by holding the head
still and looking into the camera.

(BRIG ECE)

17

AN ATM WITH AN EYE

10.CONCLUSION
We thus develop an ATM model that is more reliable in
providing security by using facial recognition software. By keeping
the time elapsed in the verification process to a negligible amount
we even try to maintain the efficiency of this ATM system to a
greater degree. One could argue that having the image
compromised by a third party would have far less dire consequences
than the account information itself. Furthermore, since nearly all
ATMs videotape customers engaging in transactions, it is no broad
leap to realize that banks already build an archive of their customer
images, even if they are not necessarily grouped with account
information.

(BRIG ECE)

18

AN ATM WITH AN EYE

(BRIG ECE)

19

AN ATM WITH AN EYE

REFERENCES
1. All , anne Triple DES dare you. ATM marketplace.com.
2. Bone, mike, wayman,dr.james L., and Blackburn, duane, Evaluating facial
recognition technology for during control applications.
3. Work shop on empirical evaluation methods in computer vision.

(BRIG ECE)

20