|
| Templets |
As the data representing the enrollee’s biometric, the biometric device creates templets. The device uses a proprietary algorithm to extract “features” appropriate to that biometric from the enrollee’s samples. Templets are only a record of distinguishing characters, of a person’s biometric features. For example, templates are not an image of the person’s  fingerprint or voice. Generally, templets are numerical representations of key points taken from a person’s body.
The template usually takes a little of computer memory, and this allows for quick processing, which is a symbol of biometric authentication. The template must be stored somewhere so that the templates, created when a user tries to access the system using a sensor, can be compared. Some biometric experts claim it is impossible to reverse-engineer, or recreate, a person’s print or image from the biometric template.
Matching
Matching is the compare of two templets: the first made in the process of enrollment (or at previous sessions) with the second produced “on the spot” when user try to gain access by providing a biometric using sensor. There are three ways a match can fail:
• failure to enroll
• false match
• false nonmatch
Failure to log in (or acquire) is the failure of the technology to extract distinctive features fitting to that technology. For example, a small percentage of employees fail to enroll in fingerprint-based biometric authentication systems. Two reasons are responsible for this failure: the individual’s fingerprints are not distinctive enough to be approved by the system, or the distinguishing characteristics of the individual’s fingerprints are altered because of the individual’s age or occupation, e.g., an elderly bricklayer.
The probability of a False Match or a False Nonmatch exists. These two terms are frequently miscalled “false acceptance” and “false rejection,” but these terms are application-dependent in meaning. FM and FNM are application-neutral terms that describe the matching process between a live sample and a biometric template. A false match happens when a sample is falsely matched to a template in the database. An incorrect non-match occurs when a sample is falsely not matched to a truly template in the database.
Rates for FM and FNM are calculated and used to compromise between security and convenience. For example, a heavy security emphasis errs on the side of denying legitimate matches and does not permit acceptance of cheaters. A heavy emphasis on user convenience results in little tolerance for denying legitimate matches but will allow some acceptance of imposters.
|
|
