Biometric identification and verification
First Claim
1. A method implemented on a computing device in a biometric system for one or more of biometric enabled access control, fingerprint search, facial recognition and iris identification to improve efficiency in match/no match decisions comprising:
- accessing a first biometric probe sample and a first gallery sample from storage;
determining a first match score between the first biometric probe sample and the first gallery sample;
determining a plurality of gallery match scores between the first gallery sample and a plurality of other samples in the gallery;
determining a number of the plurality of gallery match scores that are greater than the determined first match score;
determining a plurality of probe match scores between the first probe sample and the plurality of other samples in the gallery;
determining a number of the plurality of probe match scores that are greater than the determined first match score; and
,with one or more of the determined numbers one or more of;
determining a false match probability for assessing a reliability of a match result, the match result indicating whether the first probe sample matches with the first gallery sample, in the one or more of biometric enabled access control, fingerprint search, facial recognition and iris identification, and/oradjusting the first match score or determining a match threshold for the first match score, such that a tendency to match of the first gallery sample and/or of the first probe sample is used for a decision as to whether the first probe sample matches with the first gallery sample.
0 Assignments
0 Petitions
Accused Products
Abstract
In real biometric systems, false match rates and false non-match rates of 0% do not exist. There is always some probability that a purported match is false, and that a genuine match is not identified. The performance of biometric systems is often expressed in part in terms of their false match rate and false non-match rate, with the equal error rate being when the two are equal. There is a tradeoff between the FMR and FNMR in biometric systems which can be adjusted by changing a matching threshold. This matching threshold can be automatically, dynamically and/or user adjusted so that a biometric system of interest can achieve a desired FMR and FNMR.
90 Citations
21 Claims
-
1. A method implemented on a computing device in a biometric system for one or more of biometric enabled access control, fingerprint search, facial recognition and iris identification to improve efficiency in match/no match decisions comprising:
-
accessing a first biometric probe sample and a first gallery sample from storage; determining a first match score between the first biometric probe sample and the first gallery sample; determining a plurality of gallery match scores between the first gallery sample and a plurality of other samples in the gallery; determining a number of the plurality of gallery match scores that are greater than the determined first match score; determining a plurality of probe match scores between the first probe sample and the plurality of other samples in the gallery; determining a number of the plurality of probe match scores that are greater than the determined first match score; and
,with one or more of the determined numbers one or more of; determining a false match probability for assessing a reliability of a match result, the match result indicating whether the first probe sample matches with the first gallery sample, in the one or more of biometric enabled access control, fingerprint search, facial recognition and iris identification, and/or adjusting the first match score or determining a match threshold for the first match score, such that a tendency to match of the first gallery sample and/or of the first probe sample is used for a decision as to whether the first probe sample matches with the first gallery sample. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A system configured to use false match behavior of biometric gallery samples to add a false match probability score to a match score to improve efficiency in match/no match decisions comprising:
-
a connected match score module, memory and processor that are in communication and; access a first biometric probe sample and a first gallery sample from storage; determine a first match score between a first biometric probe sample and a first gallery sample; determine a plurality of gallery match scores between the first gallery sample and a plurality of other samples in the gallery; determine a number of the plurality of gallery match scores that are greater than the determined first match score; determine a plurality of probe match scores between the probe sample and the plurality of other samples in the gallery; and determine a number of the plurality of probe match scores that are greater than the determined first match score; wherein the system;
one or more of determines a false match probability for assessing a reliability of a match result with one or more of the determined numbers, the match result indicating whether the first probe sample matches with the first gallery sample, and adjust the first match score or to determine a match threshold for the first match score with one or more of the determined numbers, such that a tendency to match of the first gallery sample and/or the first probe sample is used for a decision whether the first probe sample matches with the first gallery sample. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19, 20, 21)
-
Specification