False acceptance rate (FAR)
False match rate (FMR):
False rejection rate (FRR)
False non-match rate (FNMR)
Equal error rate (EER)
Crossover error rate (CER):
Failure to enroll rate (FTE)
Failure to capture rate (FTC)

Template capacity

Biometric verification is any means by which a person can be uniquely
identified by evaluating one or more distinguishing biological traits. Unique
identifiers include fingerprints, hand geometry, earlobe geometry, retina and
iris patterns, voice waves, DNA, and signatures. The oldest form of biometric
verification is fingerprinting. Historians have found examples of thumbprints
being used as a means of unique identification on clay seals in ancient China.
Biometric verification has advanced considerably with the advent of
computerized databases and the digitization of analog
Iris-pattern and retina-pattern authentication methods are already employed
in some bank automatic teller machines. Voice waveform recognition, a method of
verification that has been used for many years with tape recordings in
telephone wiretaps, is now being used for access to proprietary databanks in
research facilities. Facial-recognition technology has been used by law
enforcement to pick out individuals in large crowds with considerable
reliability. Hand geometry is being used in industry to provide physical access
to buildings. Earlobe geometry has been used to disprove the identity of
individuals who claim to be someone they are not (identity theft). Signature comparison
is not as reliable, all by itself, as the other biometric verification methods
but offers an extra layer of verification when used in conjunction with one or
more other methods.
No matter what biometric methodology is used, the identification verification
process remains the same. A record of a person's unique characteristic is
captured and kept in a database.
Later on, when identification verification is required, a new record is
captured and compared with the previous record in the database. If the data in
the new record matches that in the database record, the person's identity is
confirmed.

* False accept rate or false match rate (FAR or FMR): the probability that the
system incorrectly matches the input pattern to a non-matching template in the
database. It measures the percent of invalid inputs which are incorrectly accepted.
* False reject rate or false non-match rate (FRR or FNMR): the probability that the
system fails to detect a match between the input pattern and a matching template in
the database. It measures the percent of valid inputs which are incorrectly
rejected.
* Receiver Operating Characteristic or relative operating characteristic (ROC): The
ROC plot is a visual characterization of the trade-off between the FAR and the FRR.
In general, the matching algorithm performs a decision based on a threshold which
determines how close to a template the input needs to be for it to be considered a
match. If the threshold is reduced, there will be less false non-matches but more
false accepts. Correspondingly, a higher threshold will reduce the FAR but increase
the FRR. A common variation is the Detection error trade-off (DET), which is
obtained using normal deviate scales on both axes. This more linear graph
illuminates the differences for higher performances (rarer errors).
* Equal error rate or crossover error rate (EER or CER): the rate at which both
accept and reject errors are equal. The value of the EER can be easily obtained
from the ROC curve. The EER is a quick way to compare the accuracy of devices with
different ROC curves. In general, the device with the lowest EER is most accurate.
* Failure to enroll rate (FTE or FER): the rate at which attempts to create a
template from an input is unsuccessful. This is most commonly caused by low quality
inputs.
* Failure to capture rate (FTC): Within automatic systems, the probability that the
system fails to detect a biometric input when presented correctly.
* Template capacity: the maximum number of sets of data which can be stored in the
system.