Professional Documents
Culture Documents
Area of Research: Biometrics Recognition: Access Control Surveillance
Area of Research: Biometrics Recognition: Access Control Surveillance
Most often, the two types are combined, as in voice or signature recognition. Most of
these biometrics are seen as "behavioral", but some are linked to the physiology, e.g. of
the vocal tract, or of the hand.
Ways to identify a person could be to take a fingerprint of every person; another one
could be to let the person sign a document. The data could then be put into a form that
a machine can read. At the border, people could again take the fingerprint or the
signature, and compare it to the version stored in the passport.
When selecting features, we must also look at social acceptance. Taking a fingerprint
may be ok, taking a blood test may not be. Some biometric data is also easier to fake,
e.g. signatures.
Also, when voice samples are taken, these may be distorted, because only a telephone
line is available. Telephone lines cut off some bandwidth from the signal.
Other than for passports, biometric methods are also used in some banks.
More traditional means of access control include token-based identification systems,
such as a driver's license or passport, and knowledge-based identification systems,
such as a password or personal identification number. Since biometric identifiers are
unique to individuals, they are more reliable in verifying identity than token and
knowledge-based methods; however, the collection of biometric identifiers raises
privacy concerns about the ultimate use of this information.
According to a CSO article, the biometrics market was worth US $13.8 billion in 2015.
-Siddharth
yadav
B.tech cse 4th
sem
Section-B; grp-2
A51405214007