The Identification Technology of Biometrics

The recent advances of information technologies and the

increasing requirements for security proposed have led to a

rapid development of automatic personal identification

systems based on biometrics. Biometrics refers to identify an

individual based on his or her distinctive physiological (e.g.,

fingerprints, face, retina, iris) or behavioral (e.g., gait,

signature) characteristics accurately [1]. It is inherently more

reliable and more capable than traditional token-based or

knowledge-based methods in distinguishing between an

authorized person and a fraudulent impostor. Among all

biometrics, fingerprint recognition is one of the most reliable

and promising personal identification technologies.

Biometrics authentication is highly reliable, because

physical human characteristics are much more difficult to

forge the security codes, passwords, hardware keys sensors,

fast processing equipment and substantial memory capacity,

so the system are costly. Biometric-based authentication

occupied by varying applications such as, workstation and

network access, single sign-on, application log on, data

protection, remote access to resources, transaction security,

and Web security. Moreover, a promise of e-commerce and egovernment

can be achieved through the utilization of strong

personal authentication procedures.

Secure electronic banking, investment and other financial

transactions, retail sales, law enforcement, health and social

services are already benefiting from these technologies.

Biometric technologies are expected to play a key role in

personal authentication for large-scale enterprise network

authentication environments, Point-of-Sale and the protection

of applications. Utilized alone or integrated with...

... middle of paper ...

...d recently [4, 5].

Cancellable biometrics uses transformed or intentionally

distorted biometric data instead of the original biometric data

for identifying person. When a set of biometric data is found to

be compromised, they can be discarded, and a new set of

biometric data can be regenerated. Several keys issues in

generating cancellable biometrics can be defined as

changeability (how dissimilar the transformed data are

compared to the original data), non-invertibility (transformed

biometric data should not be easily converted back to the

original biometric data even if the transformation method is

known and the transformed data are given), reproducibility (we

should be able to generate many different cancellable templates

from the original data), performance degradation (the

performance when using transformed templates should not be

degraded much).