First of all the term Biometrics should be defined to have an understanding of the subject. Both terms Biometrics and Biometry have been used since early in the 20th century to refer to the field of development of statistical and mathematical methods applicable to data analysis problems in the biological sciences. The following are some examples which fall under the umbrella of Biometrics as the term has been historically used:
1. Statistical methods for the analysis of data from agricultural field experiments to compare the yields of different varieties of wheat.
2. The analysis of data from human clinical trials evaluating the relative effectiveness of competing therapies for disease.
3. The analysis of data from environmental studies on the effects of air or water pollution on the appearance of human disease in a region or country.
Recently the term Biometrics has also been used to refer to the emerging technology which is devoted to identify an individual on the basis of their biological traits, such as fingerprints, hand geometry, face, iris, retina, voice and hand written signatures. Each one has its strengths and weaknesses. Depending upon the application, suitable biometric system can be selected.
The use of biometric systems for personal authentication is a response to the rising issue of authentication and security. The most widely used method of biometric authentication is fingerprint recognition. Generally, a fingerprint is known to be unique for each person and for that reason is considered a secure method for authentication. It is most widely used and less expensive. A Finger print is made of a series of ridges and furrows on the surface of the finger. Every one is known to have unique, immutable finger prints. Even the finger prints of the identical twins are different. This has 1/1000 misidentification rate means relatively high accuracy rate and is used in medium security facilities. It is affordable to scan the finger prints of a person and can be used in computer for number of applications and it gives more accuracy for currently available Fingerprint Recognition Systems for authentication. The fingerprint biometric system easy to capture the data, hence it is most popular. These are used to secure entry devices for building door locks and computer network access. These are used in banks for authorization at ATMs, credit cards. More recent application includes use of fingerprints for administering drugs and controlled substances to patients. The finger print biometric system has the following features:
1. Fairly small storage space is required for the biometric template, reducing the size of the databases required.
2. It is one of the most developed biometrics, with more history, research and design.
3. Each and every finger print including all the fingers are unique, even identical twins have different fingerprints.
4. Relatively inexpensive and offers very high levels of accuracy.Some examples of the use of fingerprint systems in civil areas are:
5. For fighting the abuse of civil services like social security.
6. For permitting logins based on fingerprints.
7. For fighting against illegal immigration.
This fingerprint recognition system is becoming affordable in a large number of applications like Banking, Passport,|Law enforcement, Civil Government, Enterprise Security, Medical and Financial transactions etc. Figure 1(a) shows a sample finger print image of a person.
This biometric approach uses the geometric form of the hand for confirming an individual’s identity. Specific features of a hand must be combined to assure dynamic verification, since human hands are not unique. Characteristics such as finger curves, thickness and length, the height and width of the back of the hand, the distances between joints and the overall bone structure, are usually extracted. Those characteristics are pretty much persistent and mostly do not change in a range of years. The first hand scanners were used more than 20 years ago and therefore it was one of the first biometric recognition systems. For scanning the hand a CCD (Charge-Coupled Device) camera is necessary. The camera takes two binary photos, one from above and one from beside the hand. Over 90 measurements are combined to form a template. A template is a binary file created from distinctive information from a biometric sample. Registration of a new user depends on the system but normally lasts less than 1 minute. The camera takes 3 times 2 shots and the system calculates the averages and stores the user with a special ID with his hand geometry code. The verification process requires the user to enter an ID in order to verify the claimed identity. After the user ID has been entered and the photos have been captured, the calculation of the feature set representing the biometric trait and the verification process lasts no longer than a second. Hand scan applications have proven their practical use which is shown by the 30-60% market share of biometric identification applications. The misidentification rate is 1/700 and it is used in low security buildings. The following listing should give some examples in real world areas where hand scan identification was used:
1. Personnel at the Olympic Games 1996 were identified with hand scans.
2. In a lot of cases access to military plants is granted upon successful hand scan identification.
3. Airport personnel at the San Francisco Airport are identified by hand scans.
The hand geometry recognition systems are based on a number of measurements taken from the human hand, including its shape, size of palm, length and width of the fingers. This method is very simple and easy to use. As there is no effect of environment factors such as dry weather or dry skin, this does not appear to have dry negative effects on the authentication accuracy. Also hand geometry information may not be invariant during the growth period of the children. Hand Geometry Biometric Recognition System uses the geometric shape of the hand to identify the person. This system also uses finger length, thickness, and curvature for the purpose of verification. The hand geometry is not distinctive but it is the ideal choice. The hand geometry data collection is easier and hand geometry can be combined with other biometrics like finger print. The recent applications of the hand geometry biometric systems include child day care centers use to verify the identity parents, payroll accuracy and access control, the fast gate pilot program to track border crossings for frequent travelers, United States military using for access control and majority of nuclear power plants in US use hand geometry for access control. The hand geometry is used in biometric systems as it has the following features:
1. Very small template size, easy to maintain and store large database.
2. High reliability and accuracy.
3. Robust, user friendly and easy to integrate into existing and third party systems.
4. Ideal for rough outdoor environments like construction industry and can handle high throughput of people.
5. Relatively inexpensive offers excellent return on investment.
6. The hand geometry is scanned as shown in figure 1(b) and used for identification and recognition of a person.
The face is the commonly used biometric characteristics for person recognition. The most popular approaches to face recognition are based on shape of facial attributes, such as eyes, eyebrows, nose, lips, chin and the relationships of these attributes. All these attributes of the face image are shown in figure 1 (c). As this technique involves many facial elements; these systems have difficulty in matching face images . The face recognition systems which are used currently impose a number of restrictions on how facial images are obtained. This face recognition system automatically detects the correct face image and is able to recognize the person. Human face detection plays an important role in applications such as video surveillance, human computer interfaces, face recognition, and face image databases . To enable this biometric technology it requires having at least a video camera, PC camera or a single-image camera. Face recognition biometric systems uses facial characteristics of a person. It measures the overall facial structure, distance between eyes, nose, mouth, and jaw edges. These features are extracted and used for identification of a person . Face recognition systems are used successfully in verification systems like Document control of passport, driver’s licenses, transactional authentication, credit cards, ATMs, physical access accuracy, time and attendance, entry and exit verification. Misidentification rate is 1/100 and it can be used at low security facilities. Face recognition biometric systems are strongly recommended as it has following features:
1. Facial photographs do not disclose the personal information.
2. The facial image is already socially and culturally accepted internationally.
3. It is already collected and verified to produce passports.
4. People are aware of its capture and use for identity as well as verification purpose.
5. It is non-intrusive.
6. Many states have legacy database of facial images.
7. Human verification of the biometric against the photograph/person is relatively simple and a familiar process for border control authorities.