Publication details
Accelerating Biometric Identification
| Authors | |
|---|---|
| Year of publication | 2012 |
| Type | Article in Proceedings |
| Conference | Santacrypt 2012: Proceedings |
| MU Faculty or unit | |
| Citation | |
| Field | Informatics |
| Keywords | biometrics; statistics; authentication |
| Attached files | |
| Description | By opposition to biometric matching, biometric identification is a relatively costly process. Let B = (b1, ..., bn) be a database of n biometric templates and let b be a given individual biometric acquisition. The biometric identification problem consists in finding the most likely bi corresponding to b. This paper assumes the existence of an oracle A taking as b and bi, and responding with true or false. Considering A as an atomic operation, any system-level optimization must necessarily minimize the number of calls to A per identification session. This is the parameter that we optimize in this paper. |
| Related projects: |