AN EMBEDDED REAL TIME FINGER VEIN RECOGNITION SYSTEM FOR ATM SECURITY SHANMATHY D, SRINIVASAN J ME-CSE, ARUNAI COLLEGE OF ENGINEERING TIRUVANNAMALAI TAMILNADU INDIA Abstract -Nowadays ATMs are used by many people for money transaction. So security in ATM system must be increased, for this purpose I introducing Finger Vein (FV) technology. A real time finger vein recognition system for authentication on ATM devices. The system is implemented on an embedded platform and equipped with a novel finger vein recognition algorithm. The proposed system consists of three hardware modules: image acquisition module, embedded main board, and human machine communication module. At first the RF get received and then in MATLAB finger vein image is given and it gets compared with the database image if it get authorized transaction page will be opened or else it get unauthorized two SMS will be generated to crime branch and the owner. Keywords: Finger Vein, One Time Password, Radio Frequency Identification I. INTRODUCTION The private information is traditionally provided by using passwords or Personal Identification Numbers (PINs), which are easy to implement but it is vulnerable to the risk of exposure and being forgotten. Biometrics, which uses human physiological or behavioral features for personal identification, has attracted more and more attention and is becoming one of the most popular and promising alternatives to the traditional password or PIN based authentication techniques. There is a long list of available biometric patterns, and many such systems have been developed and implemented, including those for the face, iris, fingerprint, palm print, hand shape, voice, signature, and gait. Not with standing this great and increasing variety biometrics patterns, no biometric has yet been developed that is perfectly reliable or secure [14]. For example, fingerprints and palm prints are usually frayed;voice,signature,handshapes and iris images are easily forged; face reorganization can be made difficult by occlusions or face-lifts are susceptible to spoofing attacks, that is the biometric identifiers can be copied and used to create artifacts that can device many currently available biometric devices. The finger vein is a promising biometric pattern for personal identification in terms of its security and convenience. The vein is hidden the body and is mostly invisible to human eyes, so it is difficult to forge or steal. The non-invasive and contactless capture of finger veins ensures both convenience and hygiene for the user, and is more acceptable [1].The finger vein pattern can only be taken from live body therefore it is natural and convincing proof that the subject whose finger vein is successfully captured is alive. The Smart Card Security System. In the scheme the remote user does not need to use smart cards. It is convenient for the users to use a common storage device such as a universal serial bus memory. The scheme is easy to implement. However, this authentication scheme is vulnerable to impersonation attacks and middle man attacks. An attacker could impersonate legitimate users to login and access the remote server. In addition, we analyze the security of scheme [2]. The scheme suffers from replay attacks and impersonation attacks.lamport proposed a password authentication scheme to provide authentication between the users and the remote server. Since then, many password-based remote user 94
authentication schemes have been proposed. In a smart card based password authentication scheme, the smart card takes the password from the users as input, computes the login message and sends the login message to the server [6]. The server checks the validity of the user s login message. In the mutual authentication situation, not only the server can verify the user but also a user can verify the server. To enhance and strengthen our system, we store public elements used in our scheme on a smart card and each user can gain access to his own smart card by verifying himself using his fingerprint. Accordingly, each user can participate in our scheme using only his own Smart card and fingerprint. Our fingerprint verification method is based on minutia extraction and matching.whenever a fingerprint is input, a different map of minutia is made, so we can generate a one-time random number far the ElGamal public key cryptosystem using that map. As described our scheme requires a system to authenticate each user by each user's knowledge, possession and biometrics, and this feature makes our scheme more reliable. II. THE OVER ALL DESIGN OF THE SYSTEM ATMs are a major convenience in our lives and most people now rely on them to transfer money, withdraw cash or pay bills and even to apply for new services such as internet banking and direct debit. However, with the rising use of ATMs, ATM fraud has also risen. To help protect you from scams and thieves, Bangkok Bank has prepared twelve tips and a guide to ATM skimming to improve your ATM security [8]. By following these simple precautions you can protect your savings and enjoy the security of knowing that your money is safe. The host is mainly owned by the bank. It can also be owned by an ISP. If the host is owned by the bank only machines that work for that particular bank will be supported[11]. As told earlier, there are mainly two input devices and four output devices for an ATM. The input devices are Card Reader This is a part of the identification of your particular account number. For this the magnetic stripe on the back of the ATM card is either swiped or pressed on the card reader so that it captures your account information. To understand the account information of the user, the data from the card is passed on to the host processor. The host processor thus uses this data to get the information from the card holder s bank. Keypad After the card is recognized, the machine asks further details like the type of withdrawal you prefer, your balance enquiry, and your personal identification number (PIN) and so on. Since each card has a unique PIN number, there is very little chance for someone else to withdraw money from your account. There are also separate laws to protect the PIN code while sending it to the host processor. So, the PIN number is mostly sent in encrypted form. If your pin number is correct the ATM makes the necessary transactions for the required amount. For this transaction, there are mainly four outputs. They are Speaker When a particular key is pressed, the speaker provides the feedback as audio. Display Screen The questions asked by the ATM machine regarding the transaction and the input from the user is all displayed on the display screen. Each step of withdrawal is shown by the display screen. A CRT screen or even an LCD screen is commonly used as an LCD screen. Receipt printer All the details regarding your withdrawal like the date and time and the amount withdrawn and also the balance amount in the bank is also shown in the receipt. Thus a paper receipt of the current transaction is obtained by the user. Cash dispenser This is the central system of the ATM machine. This is from where the required money is obtained. From this portion the person can collect the money. A) ATM Networking When a transaction is made, the details are inputted by the card holder. This information is passed on to the host processor by the ATM machine. The host processor checks these details with the authorized bank. If the details are correct, the requested cash by the card holder is taken with the help of an electronic fund from the customer s bank 95
account to the host processor s account. After this function is carried out, the processor sends an approval code to the ATM machine so that the cash can be transferred. B) ATM Security An ATM card is secured as long as the PIN number is kept as a secret. There is no way to get the PIN number from your card as it is encrypted by strong software s like Triple Data Encryption Standard. To keep your PIN number secure, there are a number of ways. Select your own PIN number. Select a PIN number which is easy to remember. It should not be anything that is associated to your birth date, phone number or anything personal. Do not write down the PIN number on the back of your ATM card. Here are some tips on how to keep your ATM card safely. The Finger vein recognition is a method of biometric authentication. The uses pattern recognition techniques based on images of human vein patterns beneath the skin surface. B) ONE TIME PASSWORD GENERATION One-time password (OTP) is a passw ord that is valid for only one transaction. OTPs avoid a number of shortcomings that are associated with traditional passwords. OTPs are difficult for human beings to memorize. C) RFID TAGS Radio frequency identification (RFID) refers to the use of radio frequency wave to identify and track the tag implanted into an object or a living thing. It is a wireless mean of communication that use electromagnetic and electrostatic coupling in radio frequency portion of the spectrum to communicate between reader and tag through a variety of modulation refers to the variation in the amplitude, frequency or phase of a high frequency carrier signal to convey information from one to another. Fig : RFID Tag System Fig 1 System Architecture RFID system usually consists of RFID reader and III LIST OF THE HARDWARE MODULES tag. It is very useful because it can uniquely identify a person or a product based on the tag incorporated. It A) FINGER VEIN can be done quickly and this usually takes less than a second. A prototype of the system has been designed and fabricated. The RFID reader used in the system is 96
passive type which has maximum range of detection of around 5cm above the reader. The browser any one input image, that is already to stored in a finger vein database, to pick on input image. D. SKIMMER TECHNIQUES A method used by criminals to capture data from the magnetic stripe on the back of an ATM card. Devices used are smaller than a deck of cards and are often fastened in close proximity to, or over the top of the ATM s factory-installed card reader. Where to spot a device on an ATM? Check these areas for any suspicious tampering: a. Light diffuser area. b. Speaker area. c. ATM side fascia. d. Card reader entry slot. e. ATM keyboard area. 1) OPEN GUI PAGE 3) DATABASE MATCH To check 4 recognition methods, that is an resize, histogram equation, feature, database, now process are completed, if it is correct means the process are authenticationed otherwise To run on the graphical user interface, the page will be open that is an finger vein authentication page. It is consist of 4 recognition methods that are resize, histogram equation, feature, database. 2) BROWSE 97
unauthenticated. ISSN 2394-3777 (Print) 5) CODE VERIFICATION 4) 3FACTOR AUTHENTICATION The finger vein image is compared to the database image, if it is authorized transaction means the page will be open, that time to give your own card number. To check the card number correct means the OTP(One Time Password) generate to our mobile number otherwise unauthorised transaction means two SMS will be generate to the crime branch and the owner. 6) LOGIN PAGE Finally to open the login page.it is mainly used for secure money transaction. 98
IV. CONCLUSION The authentication scheme is only based on the common storage device. However, we show that this authentication scheme is vulnerable to impersonation attacks and middle man attacks. We also show that even if Fan-Chan-Zhang s scheme uses smart card, it still suffers from replay attacks and impersonation attacks. As shown here, although it is convenient for the users to use a common storage device such as a USB in the based password authentication schemes, designing such authentication schemes will be more difficult. How to design a secure authentication scheme using memory devices is still an challenging task. REFERENCES [1] Y. Ding, D. Zhuang, and K. Wang, A study of hand vein recognition method, in Proc. IEEE Int. Conf. Mechatronics & Automation, Niagara Falls, Canada, Jul. 2005, pp. 2106 2110. [2] K. Wang, Y. Zhang, Z. Yuan, and D. Zhuang, Hand vein recognition based on multi supplemental features of multi-classifier fusion decision, in Proc. IEEE Intl. Conf. Mechatronics Automation, Luoyang, China, Jun. 2006, pp. 1790 1795. [3] L.Wang and G. Leedham, Near- and far-infrared imaging for vein pattern biometrics, in Proc. IEEE Int. Conf. Video Signal Based Surveillance, Sydney, Nov. 2006, pp. 52 57. [4] D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, Handbook of Fingerprint Recognition. New York: Springer, 2003. [5] S. Fantini and M. A. Franceschini, Handbook of Optical Biomedical Diagnostics. Bellingham, WA: SPIE, 2002. [6] Handbook of Biometrics, A. K. Jain, P. Flynn, and A. Ross, Eds. New York: Springer, 2007. [7] C. Oden, A. Ercil, and B. Buke, Combining implicit polynomials and geometric features for hand recognition, Pattern Recognit. Lett., vol. 24, pp. 2145 2152, 2003. [8] A. Kumar and D. Zhang, Personal recognition using hand-shape and texture, IEEE Trans. Image Process., vol. 15, no. 8, pp. 2454 2461, Aug. 2006. [9] G. Bebis, T. Deaconu, and M. Georgiopoulos, Fingerprint identification using Delaunay triangulation, in Proc. Int. Conf. Information Intelligence and Systems, 1999, pp. 452 459. [10] L. Wang, G. Leedham, and S.-Y. Cho, Minutiae feature analysis for infrared hand vein pattern biometrics, Pattern Recognit., vol. 41, no.3, pp. 920 929, 2008. [11] P. Buddaharaju, I. Pavlidis, P. Tsiamyrtzis, and M. Bazakos, Physiology- based face recognition in the thermal infrared spectrum, IEEE.Tran. Pattern Anal. Mach. Intell., vol. 29, no. 4, pp. 613 626, Apr.2007. [12] W. Norman, The Anatomy Lesson [Online]. Available: http://home. comcast.net/~wnor [13] O. A. Carretero, Vascular remodeling and the kallikrein-kinin system, J. Clin. Invest., vol. 115, pp. 588 591, Mar. 2005. [14] P. Carmeliet and R. K. Jain, Angiogenesis in cancer and other diseases, Nature, vol. 407, pp. 249 257, 2000. [15] http://www.fujitsu.com/global/about/rd/200506 palmvein.html [16] [Online]Available: http://www.bionicsk.co.jp/english/product/va200.html 99