Biometrics, as a New Technology
Identifying oneself by using unique human charateristics
By Lim Dong-hun
What is biometrics?
Biometrics is an old greek word for a very new concept. "Bio," meaning life, and "Metric," the measure of, so Biometrics is in essence, the measure of life. Biometrics is an emerging technology for automatically identifying individuals using their distinct physical or behavioral characteristics. Types of Biometrics can be any unique human characteristics, such as fingerprint, voice, face, iris, retina, palm, signature, wrist vein, and hand geometry. Biometrics provides a better solution for the increased security requirements of our information society than current identification methods (passwords, PIN numbers and magnetic strip cards with a PIN number) for various reasons: the person to be identified must be physically present at the point of identification; identification based on biometric techniques obviates the need to remember a password (or write it on a yellow sticky note), PIN or carry a token. Using biometric systems to identify the user of a computer, ATM, cellular phones and even credit card purchases will reduce fraud and unauthorized access. This could save the economy billions of dollars. There are issues that must be defined when designing a practical system. Two initial issues are determining how the person is going to be identified, verification or identification. Verification involves confirming or denying a person's claimed identity. In verification, the biometric system will verify whether or not an individual's biometric sample matches a previously enrolled data. Identification establishes a person's identity. In identification, a biometric sample is compared against a database of stored users. Both approaches have complexities and could probably be solved best by a certain biometric system.
Fingerprint identification
Fingerprint identification is the most commonly recognized and most widely applied form of Biometric technology. Fingerprint ID is based upon the fact that a person's fingerprint is completely unique to the individual. A fingerprint is made of a series of ridges and furrows on the surface of the finger. The uniqueness of a fingerprint can be determined by the pattern of ridges and furrows as well as the minutiae points. In the past, fingerprints were recorded by the application of ink to the finger which was then pressed to paper to give an impession. More recently, it has become possible to scan a person's fingerprint into virtual storage in a computer with the aid of laser technology. In order to prove identification, a person's fingerprint will be scanned again in the future by a similar device, and a match of print to name is verified through information systems. Techniques such as this are even currently being used in applications as commonplace as automatic teller machines and security locks. Look for fingerprinting to become a primary means of identification verification in the near future!
Hand geometry
Hand geometry is even older than digital fingerprinting; it was first used for security purposes on Wall Street more than 20 years ago. We're already conditioned to offer a hand in friendship or th seal an agreement, which may be why hand scanners have gained wide acceptance in office buildings, factories, and other corporate environments.
Hand geometry is based on the fact that virtually every person a hand is shaped differently and that the shape of a person's hand (after a certain age) does not significantly change. When the user places a hand on the hand reader, a three-dimensional image of the hand is captured. Then, the shape and length of the fingers and knuckles are measured. Depending on the data used to identify a person, hand reading technologies generally fall into one of three categories - application to the palm, the pattern of veins in the hand and the geometrical analysis of fingers.
Eye scanning
Biometrics which analyze the complex and unique characteristics of the eye can be divided into two different fields: iris biometrics and retina biometrics. The iris is the colored band of tissue that surrounds the pupil of the eye. An iris recognition system uses a video camera to capture the sample while the software compares the resulting data against stored templates.
The retina is the layer of blood vessels at the back of the eye. Retina scans are performed by directing a low-intensity infrared light to capture the unique retina characteristics. An area known as the face, situated at the center of the retina, is scanned and the unique pattern of the blood vessels is captured. Retina biometrics is considered to be the best biometric performers. However, despite is accuracy, this technique is often thought to be inconvenient and intrusive. And so, it is difficult to gain general acceptance by the end user. The retinal scanner requires an individual to stand still while it is reading the retinal information. Eye and retinal scanner are ineffectual with the blind and those who have cataracts.
Face recognition
Face recognition systems identifies an individual by analyzing the unique shape, pattern and positioning of facial features. There are essentially two methods of processing the data: video and thermal imaging. Standard video techniques are based on the facial image captured by a video camera. Thermal imaging techniques analyze the heat-generated pattern of blood vessels underneath the skin.
The attraction of this biometric system is that it is able to operate 'hands=free', limiting the amount of man-machine interaction. However, this system is highly unreliable and expensive. For example, it will not distinguish twins or triplets, not recognize the user after a haircut, and not recognize a person who changes from wearing and not wearing glasses.
As concerns face recognition many approaches have been proposed in the literature, and several researchers are studying this problem. Principal component analysis, elastic graph matching, neural networks, and distorsion-tolerant template matching are only few of the proposed techniques.
Voice verification
Voice verification is the science of verifying a person's identity on the basis of their voice characteristics. Unique features of a person's voice are digitized and compared with the individual's pre-recorded "voiceprint" sample stored in the database for identity verification. It is different from speech recognition because the technology does not recognize the spoken word itself. Rather, it recognizes the speaker of the words by analyzing unique speech characteristics, such as the frequency between phonetics.
Speaker recognition technology makes it possible for a speaker's voice to control access to restricted services, for example, phone access to banking, database services, shopping or voice mail, and access to secure equipment.
While speaker recognition is convenient, it is not as reliable due to the risks of impersonation, remote access and bad accuracy. A person with a cold or laryngitis may have problems using a speaker recognition system due to false rejection.
Signature recognition
The user sings his signature on a digitized graphics tablet. Signature dynamics, such as speed, relative speed, stroke order, stroke count and pressure are analyzed. The key in signature dynamics is to differentiate between the parts of the signature that are habitual and those that vary with almost every signing.
The use of a signature itself has been widely accepted, from the Declaration of Independence to credit cards. Still, problems with signature recognition lie in the means of obtaining the measurements used in the recognition process and the repeatability of the signature. The DSV(Dynamic Signature Verification) system is engineered in a way to adapt to variances. Nevertheless, without lowering the acceptance rate, it cannot consistently measure the dynamics of a signature.
Keystroke dynamics
Keystroke dynamics analyze the way one types. It is a very new technology to the biometrics arena. Users enroll by typing the same word or words a number of times. Verification is based on the concept that the rhythm with which one types is distinctive.
DNA
The term "DNA" is actually short for Dioxyribo Nucleic Acid. DNA is found in every cell of every creature, and it contains the information for carrying out the activities of the cell. Since every person's DNA structure is completely unique, DNA analysis is a very accurate way of proving identification. Due to the extensive testing and advanced technology required, it is not the most cost efficient Biometric science, but when a positive identification is needed it is the most reliable.
Future applications
Biometrics is a rapidly evolving technology which is being widely used in forensics such as criminal identification and prison security, and has the potential to be used in a large range of civilian application areas. Biometrics can be used to prevent unauthorized access to ATMs, cellular phones, smart cards, desktop PCs, workstations, and computer networks. It can be used during transactions conducted via telephone and internet (electronic commerce and electronic banking). In automobiles, biometrics can replace keys with key-less entry devices.
