Biometric Technology

49

2

A Review of the Present and

Future Biometric Technologies

THE BIOMETRIC TECHNOLOGIES OF

TODAY: PHYSICAL AND BEHAVIORAL

Chapter 2 will now take a part of Chapter 1 and explore it in much more

exhaustive detail, that is, biometric technologies that are available today.

Each biometric technology that was presented in Chapter 1 will now be

further expanded upon and reviewed.

Before we move onto our detailed discussion and analyses of the bio-

metric technologies that are available on the market place today, it is very

important to turn back to the topic of physical biometrics and behavioral

biometrics. As was mentioned in Chapter 1, physical biometrics involves

taking a biological or physiological snapshot of a part of our body and

behavioral biometrics involves taking a picture of our unique manner-

isms that make us different from everybody else.

However, we need to provide much more precise, scientic deni-

tions to these two terms. Physical biometrics can be dened as “acquir-

ing physical biometric samples which involves taking a measurement

from subjects. This does not require any specic action by the subject. A

physical biometric is based primarily upon an anatomical or physiological

characteristic rather than a learned behavior” (Certied Biometrics Learning

System, Module 2, Biometrics Standards, © 2010 IEEE, p. 2–1).

Behavioral biometrics can be dened as “Acquiring behavioral bio-

metric samples requires subjects to be active. They must perform a specic

BIOMETRIC TECHNOLOGY

50

activity in the presence of a sensor. A behavioral trait is learned and

acquired over time rather than based upon biology” (Certied Biometrics

Learning System, Module 2, Biometrics Standards, © 2010 IEEE, p. 2–1).

DIFFERENCES BETWEEN PHYSICAL BIOMETRICS

AND BEHAVIORAL BIOMETRICS

As one can see, based upon these two denitions, some very subtle dif-

ferences between physical biometrics and behavioral biometrics can be

observed. Probably the biggest difference to be noted is the amount of

activity required by the end user. With physical biometrics, no active part

is needed on the part of the individual in order to collect that individual’s

physiological and biological unique features (whether it be the hand, the

nger, the iris or retina, or even the vein patterns present from under-

neath the palm or the ngerprint). The end user must be cooperative in

order for an effective sample to be captured (this is true for all biometric

technologies).

In other words, physical biometrics can be more or less considered

as garbage in–garbage out. The image is captured, unique features are

extracted, and the individual is either veried or not. However, with

behavioral biometrics, a specic function, or an active part, must be car-

ried out (such as typing on a keyboard or signing your name), which is

learned over time.

As a result, because of this learned behavior, deviations or changes

in the behavioral-based biometric templates that are collected can drasti-

cally occur over time, at a level much more so than physical-based bio-

metric templates. Hence, research and development is already underway

in which a behavioral-based biometric system can literally learn and take

into account such changes in the behavior and mannerisms that can occur

over the lifetime of an individual.

A perfect example of this would be the use of neural network technol-

ogy. With this type of technology, computer-based learning and reason-

ing takes place in an attempt to closely follow the actions and patterns of

the human brain.

Another difference between physical biometrics and behavioral

biometrics that is evident from the above denitions is the number of

measurements taken to extract the unique features. In both types of tech-

nologies, multiple images or multiple samples are collected. However, in

physical biometrics, only one composite image is utilized from which to