AMRITA VISHWA VIDYAPEETHAM,

ETTIMADAI

VEIN RECOGNITION FOR  SECURITY IN ATM

ABSTRACT

This work presents a security system in ATM based on the vein recognition in hand. Vein recognition biometric approach is the verification of a person's identity by recognizing the pattern of blood veins in the palm (number of veins, their position and the points at which they cross). Other biometric applications like finger prints and iris patterns can be more prone to copying by a third person. Veins in hand are not directly visible to a third person, which makes them more suitable for security use. Veins and other subcutaneous features present large, robust, stable and largely hidden patterns. In the ATM cell, camera takes the digital picture of the ATM user (back side of his hand) using near-infrared light. The haemoglobin in the blood absorbs the light, so veins appear black in the picture. Vein pattern IR. Grey-scale images are binarized, compressed and stored within a relational database of 2D vein images. This is taken as a reference template and is compared with the database which stores vein structure of the account holders of the bank. Subjects are verified against a reference template in under 200ms providing fast, robust biometric authentication. If the pattern and the pin number matches, the ATM machine allows the users to do transactions in a secured way.

HOW IT WORKS

                           The process begins with scanning the back of the hand of each account users and vein pattern is processed and then stored in a database of the bank. When the account users use the ATM system for doing transaction, the back of the user’s hand will be scanned. Vein scanners use near-infrared light to reveal the patterns in a person’s veins. The digital picture is taken and is fed in to the image processing unit. The hemoglobin in your blood absorbs the light, so veins appear black in the picture. As with all the other biometric types, the software creates a reference template based on the shape and location of the vein structure. This template that is generated is compared with the existing templates that are already stored in the database. If both the templates match the transaction can be done by the user.  From this the account holders can carry out the transactions in a secured way.

ARCHITECTURE

 ENROLLMENT PHASE

VERIFICATION PHASE

INTRODUCTION

           Fraudsters are growing increasingly sophisticated in their efforts to beat identification systems. The best solution to provide a secured way is going for biometric approaches. Biometrics is the science of recognition of a person based on physiological or behavioral characteristics. Biometrics is used in security applications such as ATM machines, ballot systems, airports and so on. There are two biometric traits: open view and closed view. Open view biometric traits i.e. traits that can be easily recorded or photographed are left on every item we touch are likely to come under increasing criminal attack as biometric usage becomes more widespread. Open view biometric traits can be covertly captured and worked on by criminal elements until satisfactory facsimiles are produced to fool or spoof the biometric system. Closed view biometric traits i.e. hidden or internal biometric parameters and certain behavioral traits are more difficult to illicitly capture or reproduce.

               Vein recognition is one of the emerging closed view biometric approaches. Vein biometric systems record subcutaneous Infra Red (IR) absorption patterns to produce unique and private identification templates for users. The technology is a vascular "bar" code reader for people.

               Here we propose a system that uses vein recognition-biometric approach to authenticate all the ATM users of a bank. ATM has some problems related to security like misusing the card. So, the entry of the four-digit personal identification number (PIN) on the keypad should still be obscured from observation, which can be done by positioning your hand and body in such a way that the PIN entry cannot be recorded by store cameras or store employees. The biometrics system identifies a person from the enrolled population by searching a database for a match. Then the system uses vein recognition method to authenticate a person's claimed identity based on his/her previously enrolled pattern.

Vein recognition has the following advantages:

             The human vascular structure is a unique & private feature of an individual. Infra Red absorption patterns are easily compared via optical and DSP techniques. Identical twins have different and distinct IR absorption patterns. Veins provide large, robust, stable and hidden biometric features. Vein patterns are not easily observed, damaged, obscured or changed. Vein patterns require only low resolution IR. Imaging allied to simple image processing. Vein pattern stability and repeatability requires only simple algorithms for auto identification.

 RESULTS

 CONCLUSION

      Thus vein recognition system, its large, robust, stable and hidden biometric features which require only low resolution IR. Imaging allied to simple image processing and small data requirements make a popular choice for those in need of verification system.  Biometrics is at last attracting some interest from the world’s major electronic and computer companies. This heralds a move to enhanced biometric interfaces for vehicles, computer networks, and security access and payment systems. Biometric authentication will be used to secure future transactions between humans and intelligent machines. Biometrics will provide the key enablers to the generation of private keys in public key cryptography, securing the digital frontier for commerce. in the future we can expect many civilized biometric technologies. Technologies that delight rather than blight humanity.

        SUBMITTED BY

Ananda Ramya A (0110304103)

Gokila .M (0110304117)

Sandhiya U.S. (0110304139)

Sarannya V (0110304140)