Because ID theft occurs in 1 out of 20 individuals with an estimated 54 billion in fraud, biometrics is the future for security that should be implemented by businesses and the government to reduce Identity fraud. Biometrics addresses the recognition of people grounded on their genetic or behavioral traits. It has recently been getting noticed in the popular mass communication industry. It is usually assumed that biometric will become a considerable component of the identification technology as the values of biometrics sensor keeps on failing, the fundamental technology becomes more mature and the public becomes cognizant of the forces and limitations of biometric (Pankanti, Anil, and Ruud,1999, p1).
Introduction
The purpose of the biometric system is the identification or authentication of human beings based on some physical or behavioral traits that are essentially distinctive from each other. Currently, biometric systems are basic components of highly developed security architectures. The functions of biometrics range from access control, military, and surveillance to banking and multimedia copyright protection (Boulgouris, 2009, P.vii).
Of late, biometric information has started to become an important element in government-issued confirmation and travel papers. The large-scale use of biometric sensors in a range of electronic devices, such as mobile phones, laptops, and personal digital assistants (PDA), has increased the pace at which the demand for biometric technologies has been on the increase. The vast interest in the theory, technology, applications, and social implications of biometric systems has created an urgent need for the systematic learning of the use of biometrics in security and surveillance infrastructures.
Definition of Biometric
Biometric is the science of proving the distinct personality of an individual based on the physical, chemical, or behavioral qualities of the person. The application of biometrics in present society has been reinforced by the need for comprehensive identity management systems whose functionality relies on the correct determination of an individual’s identity in the framework of some different applications.
The proliferation of e-banking services like online banking and the improvement of decentralized customer service centers have further underlined the need for consistent identity management systems that can put up with a large number of individuals.
The central or dominant task in an identity management system is the determination or proof of an individual’s identity or declared identity. Such an action may be required for a variety of reasons but the most important intention, in most applications, is to stop frauds from accessing secluded resources. Traditional methods of proving a person’s identity include knowledge-based passwords and token-based ID cards mechanisms, but these substitute representations of identity can easily be lost, shared, manipulated, or stolen thus compromising the planned security.
Biometric proffers a natural and consistent solution to definite aspects of identity management by using fully automated or semi-automated systems to identify individuals based on their biological characteristics.
In some applications, biometrics may be used to supplement ID cards and passwords thereby imparting an extra level of security. This arrangement is often called a dual-factor authentication system.
The efficiency of an authenticator (biometric or non-biometric) is grounded on its importance to a particular application in addition to its heftiness to different types of deliberately harmful attacks. There is lists of many attacks that can be set up against authentication systems based on passwords and tokens: a) client attack like guessing a password, stealing tokens, b) host attack like accessing plain text file containing passwords c) eavesdropping e) Trojan horse attacks such as the installation of the bogus log-in screen to steal passwords and f) denial of service like disabling the system by intentionally supplying a wrong password severally. While several of these attacks can be avoided by integrating suitable defense mechanisms, it is impossible to handle all the problems linked with the use of passwords and tokens.
Biometric proffers definite improvements such as unenthusiastic recognition and non-repudiation that cannot be provided by tokens and passwords. Negative identification is the method by which a system verifies that a person is, without doubt, enrolled in the system even though the individual might deny it. This is particularly critical in applications such as welfare payment where fraud may endeavor to claim several benefits under different names. Non-repudiation is a way to certify that an individual who accesses a certain facility cannot deny using it. Like accessing a computer resource and later claiming that an imposter must have used it under inaccurate credentials.
Biometric systems use a range of physical or behavioral characteristics, as well as fingerprints, face, hand/finger geometry, iris, resins, signature, gait, palm print, voice pattern, ear, hand vein, odor, or the DNA information of an individual to prove identity. In the biometric literature, these features are referred to as traits, indicators, identifiers, or modalities.
Operation of a biometric system
A biometric system is a prototype recognition system that obtains biometric data from an individual, removes the most important feature set from the date, compares these feature sets stored in the database, and performs an action established on the result of the comparison. A generic biometric system can be analyzed as having four most important modules, a sensor module; a quality assessment and feature extraction module; a matching module; and a database module. Each of these modules is described below:
Sensor Module
This is an appropriate biometric reader or scanner which is essential in the acquisition of the original biometric data of an individual. To take fingerprint images, an ophthalmic fingerprint sensor may be used to copy the friction convexity structure of the fingertip. The sensor module ascertains the human-machine boundary hence critical to the presentation of the biometric system. A scantily designed boundary can result in a high failure to acquire rate and consequently, low user acceptability.
Since most biometric modalities are acquired as images except voice and odor, the quality of the raw data is also impacted by the characteristics of the camera technology that is used.
Quality assessment and feature extraction module
The character of the biometric information obtained by the sensor is first gauged to verify its quality for further processing. Normally, the obtained data is submitted to a signal enhancement algorithm to improve its quality. However, in some cases, the quality of the data may be so underprivileged that the user is requested to present the biometric data again. The biometric data is then processed and a deposit of relevant unfair features is reduced to represent the underlying trait.
Matching and decision-making module
The extorted features are examined against the stored templates to give match scores. In a fingerprint-based biometric system, the number of identical details between the amount and the template feature sets is determined and a match score is reported. The match score may be controlled by the quality of the presented biometric data. The matcher module also summarizes a decision-making module, in which the match score is used to either authenticate an asserted identity or provide a ranking of the enrolled identities to identify an individual.
System database module
The database performs as the depository of biometric information. During the staffing process, the feature set extracted from the raw biometric sample is stored in the database together with some biographic information such as Personal Identification Number, characterizing the user.
The data retrieved in the registration method is likely to be controlled by an individual relying on the submission. For example, a user trying to create a new computer account in her biometric-enabled workstation may proceed to enroll her biometrics without any supervision, a person desiring to use a biometric-enabled ATM, on the other hand, will have to enroll her biometrics in the presence of a bank officer after presenting her non-biometric credentials (Arun, Anil, and Patrick, 2008, p 5).
Applications of biometrics
Ascertaining the uniqueness of a person with high confidence is becoming essential in several functions in our widely consistent society. Methods of consistent authentication have dramatically enhanced security, and fast developments in global connection, the activity of conveying information. Thus, biometrics is being progressively more integrated into several different applications. These applications can be categorized into the following groups.
- Commercial applications such as computer network login, electronic data security, e-commerce, internet access, ATM, or credit card use.
- Government applications such as national ID card, managing inmates in a correctional facility, driver’s license, social security, welfare-disbursement, border control, and passport control
- Forensic applications such as corpse identification, criminal investigation, and parenthood determination and parenthood determination
(Arun, Anil, and Patrick, 2008, p. 12).
Overview of Biometric Technology
No distinct biometrics is supposed to effectively gratify the needs of all identification or authentication appliances. A number of biometrics has been recommend, explored, and evaluated for identification applications. Biometric has its potency and restrictions, and for that reason they please or stimulate a given detection. A summary of the existing and burgeoning biometric technologies is described below:
- Signature: The manner in which a person signs their name is known to be a trait of that specific person only (Aviczer, Lee, and Berger, 1996; Nalwa, 1997). Signatures entail close interaction with pen and an attempt by the user.
- Fingerprints: for many years, fingerprints have been used by humans for personal identification. The corresponding exactness using fingerprints has been shown to be very high. Even the fingerprints of matching twins are different hence each person has their own distinctive prints.
- Face: Face identification is a non-intrusive technique, and facial qualities are perhaps the most familiar biometric characteristics used by individuals to identify one another. The use of facial identification ranges from an inactive, controlled confirmation to dynamic, unrestrained face recognition in a mixed-up background. The most accepted Ideas or actions intended to deal face recognition are grounded on either the position or form of facial quality, like the eyes, eyebrows, nose, lips, and chin and their spatial relationships.
- Palm print: The palms of an individual have perceptual structure of natural elevation and depression same as the print made by an impression of the ridges in the skin of a finger; frequently used for biometric detection in criminal investigations. The area of the palm is much larger than the area of a finger and consequently, palm prints are likely to be even more distinct than the fingerprints (Wong, Zhang, Kong, and You, 2003). Palm print scanners need to capture a large area, so they are larger and more costly than the finger print sensors. However, all the marks of the hand such as geometry, ridge and valley features, principal lines and wrinkles may be joined to put up a correct biometric system.
- Hand geometry: The detection methods of hand geometry are established on the assessments of the human hand, including all the features and its components. Commercial hand geometry-based verification systems have been set up in lots of locations worldwide. The system is uncomplicated, quite easy to use and economical.
- Voice: Voice can be classified as an individual communicative biometric feature (Campbell, 1997). The difficulty of voice based identification is that speech features are responsive to a number of features such as back-ground noise. Speaker identification is most suitable in telephone-based applications but the voice signal is characteristically graded in quality by the communication means.
- Gait: Gait refers to the way in which human being walks, and is one of the few biometric features that can be used to identify people separately. Therefore, this feature is very suitable in inspection scenarios where the characteristics of an individual can be furtively established. Most gait recognition algorithms try to remove the human shape to develop the spatio-temporal traits of a moving individual.
In conclusion, fast developments in the field of communications, computer networking and transportation, couples with sensitive concerns about identity fraud and national security, has resulted in a well-defined need for consistent and competent identity management schemes in a countless of application. The method of identity management entails the creation, maintenance and destruction of identities while ensuring that an impostor does not deceitfully gain advantage linked with a legally enrolled person. Traditional verification techniques based on passwords and tokens are imperfect in their ability to tackle matters such as negative identification and non-repudiation. Apart from hi-tech solutions to deal with privacy concerns, government regulations are also required in the prevention of wrong transmission, swap and processing of biometric data.
Reference List
Arun, A. R., Anil, K. J., and Patrick, J. F. (2008). Handbook of biometrics. New York, NY: Springer.
Aviczer, E., Lee, L., and Berger, T. (1996). Reliable On-line Human Signature Verification Systems. IEEE Transactions on Patern Analysis and Machine Intelligence, 18(6): 643-647.
Boulgouris, N. V. (2009). Biometrics: Theory, Methods, and Applications. New Jersey, NJ: Wiley-IEEE.
Campbell, J. P. (1997). Speaker Recognition: a Tutorial. Proceedings of the IEEE, 85(9): 1437-1462.
Nalwa, V.S. (1997). Automatic On-line Signature Verification. Proceedings of the IEEE, 85(2): 215-239.
Pankanti, S., Anil K. J., and Ruud, B. (1999). Biometrics: personal identification in networked society. New York, NY: Springer.
Wong, M., Zhang, D., Kong, A.W.K., and You, J. (2003). Online Palmprint Identification. IEEE Transactions on pattern Analysis and Machine Intelligence, 25(9): 1041-1050.