Hi I Am subrata maji. I'm from west Bengal
Posts: 14,118
Threads: 61
Joined: Oct 2014
There is an urgent need to improve security in the banking region. With the advent of ATM although banking became much easier it even became very vulnerable. The potential for misuse of this widespread "unsafe" baby product is manifold due to the exponential growth of "smart" criminals every day. At present, ATM systems use only one access card and one PIN for identity verification.
This situation is unfortunate since enormous progress has been made in biometric identification techniques, including digital printing, retinal scanning and facial recognition. This article proposes the development of a system that integrates facial recognition technology in the identity verification process used at ATMs. The development of such a system would serve to protect both consumers and financial institutions from fraud and other breaches of security.
An ATM with one eye proposes a security model for ATMs that would combine a physical access card, PIN and electronic face recognition. By forcing the ATM to match a live image of a customer's face with an image stored in a bank database associated with the account number, the damage caused by stolen cards and PIN is effectively neutralized. Only when the PIN matches the account and the live image and the stored image match would a user be considered completely verified.
The main problems faced in the development of this type of ATM with an eye model are keeping the time spent in the verification process at an insignificant amount, allowing an adequate level of variation in the face of a client compared With the database image, can be used at ATMs to withdraw funds are generally issued by institutions that do not have in-person contact with the customer, and therefore no opportunity to acquire a photo. Because the system would only try to match two (and later, a few) Discreet, searching through a large database of possible matching candidates would be unnecessary.
The process would effectively become an exercise in model matching, which would not require much time. With proper lighting and robust learning software, slight variations could be explained in most cases.
In addition, a positive visual match would make the live image stored in the database so that future transactions would have a broader base from which to compare if the original account image does not provide a match - thus decreasing the False negatives. Made with PIN but not with images, the bank could limit transactions in a manner agreed upon by the customer when the account was opened, and could store the user's image for further examination by bank officials.
With respect to bank employees accessing customer PINs for use in fraudulent transactions, this system would also reduce that threat to exposure to the minimum limit imposed by the bank and agreed by the customer in transactions not visually Verifiable.