05-04-2011, 12:17 PM
[attachment=11735]
ABSTRACT
This paper encloses the information regarding the ‘IMAGE PROCESSING’. And discussed one of the major application of image processing ‘BIOMETRICS’. Biometrics technology allows determination and verification of ones identity through physical characteristics. To put it simply, it turns your body in to your password. We discussed various biometric techniques like finger scan, retina scan, facial scan, hand scan etc. Two algorithms have been proposed by taking biometric techniques to authenticate an ATM account holder , enabling a secure ATM by image processing. Biometrics is now applied in various public and private sectors. No doubt, biometrics is going to be next generation’s powerful security tool…!
What is Digital Image Processing?
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, we call the image a digital image.
Interest in digital image areas: improvement of pictorial information for human interpretation: and representation for autonomous machine perception.
The entire process of Image Processing and starting from the receiving of visual information to the giving out of description of the scene, may be divided into three major stages which are also considered as major sub areas, and are given below
(i) Discretization and representation: Converting visual information into a discrete form: suitable for computer processing: approximating visual information to save storage space as well as time requirement in subsequent processing.
(ii) Processing :Improving image quality by filtering etc ; compressing data to save storage and channel capacity during transmission.
(iii) Analysis: Extracting image features; qualifying shapes, registration and recognition.
We concentrated on human interpretation application and developed two algorithms which can make the ATM secure by image processing.
1.OVERVIEW
With the increasing necessity of e-mail accessing and Internet resources and the convenience it offers serious security concerns also arise. Internet is vulnerable to intruders who are always snooping to find open computers in the network to steal personal files, information or cause any damage. The loss of these records, emails or customer files can be devastating.
1.1Draw back of passwords-need for Biometrics
No more problems if forgotten passwords and id codes, biometrics is the technology taking care of it which turns your body into your password. Typically, the more rigorous you make your password selection and construction rules the more difficulty users will have in remembering their passwords. Unfortunately, strict password rules are necessary to stop simple hacker attacks on the network.
The fundamental problem with password is two fold. First, they are transferable they can be written down on paper, they can be transferred to some one who should not have them. Second, and just as important, they can be forgotten. Recent research suggests that a forgotten password can cost as much as US$ 340 per event! This is n’t too surprising. Clearly, the risk and costs of compromised passwords are a significant facto to consider in developing any sure system. The critical need for additional level of security has given rise to the field of “BIOMETRICS”
2.Introduction
The present generation security issue is considered the basic TCP/IP encryptions and other factors that are provided by the network. But there was lack of consistent identification of individuals, then the newly developed technology Biometrics, came in to picture. Biometrics can be defined as recognizing and identifying a person based on physiological or behavioral characteristics. Biometrics technologies are applied in the following sectors: Public services, law enforcement, banking, physical access control and control and computer networks. These include fingerprints, facial features, retina shape, speech, handwriting, etc.
Biometrics can be used to prevent unauthorized access to ATM’s, smart cards, desktop PC’s workstations, cellular phones, home security systems, door locks, etc. The advanced Biometrics solution uses a more sophisticated method called “identification”. The design of an advanced solution enables the product to search a very large database and pick the individual from the crowd. Biometric is the most secure and convenient authentication tool. It can’t be borrowed. Stolen, or forgotten, and forging one is practically impossible.
2. Classification of biometrics:
The two categories of biometric techniques are:
The physiological based techniques, which measure the physiological characteristics of a person. These include fingerprint verification, iris analysis, facial analysis, hand geometry-vein patterns, ear recognition, odor detection and DNA pattern analysis.
The behavioral based techniques, which measure the behavior of a person. These include hand written signature verification and speech analysis. These techniques involve two major steps. These are the Authentication & the verification.
Authentication is a process of one-to one comparison, rather than a mass searching process. Identification is a process of checking for a particular identity in the database available.
The setting of the error tolerance of these systems is critical to their performance. Both errors (False Rejection and False Acceptance).
Should be low and they should both are quoted by the manufacturers.
3.How biometric technology works
Process involved in using a biometric system for security is:
During enrollment:
1) Capture the biometrics, which has to be stored in the database;
2) Process the biometric, extract and enroll the biometric template;
3) Store the template in a local repository, a central repository, or a portable token such as a smart card.
During access to database:
4) Live-scan the biometric feature;
5) Process the biometric and extract the biometric template;
6) Match the scanned biometric against stored templates;
7) Incase of successful verification; provide a matching score to business application;
8) Record a secure audit trail with respect to system use
Biometric applications depend on comparing as new measure against previously captured information. In biometric applications, some aspect of a person is measured; the measure is processed; and the resulting data is stored; At a subsequent time, the same aspect of a person is measured and compared against the stored data .If it is being used for authentication, the new data is compared against the data, already in storage for that person. If it is being used for identification, the entire database is searched, in order to locate one or more individuals that are a close fit to the new data. Most biometrics technologies do not seek exact equality between the new and the stored measures. Instead they have a pre-set tolerance range within which the two are deemed to be sufficiently close. In order to reduce transmission time, costs and to require less storage space, compression algorithms are used. To provide better transfer rate of data during identification & authentication ‘hashing’ is used. Hashing is a process of detecting the perfect match of a particular input record from a large database using a hashing function.
