Biometric identification and verification
First Claim
1. A method of using impostor match behavior of biometric gallery samples to add a false match probability score to a match score to assist with match/no match decisions to identify an individual comprising:
- determining, using an interconnected processor and memory;
a first match score between a biometric probe sample and a gallery sample;
as the false match probability score, a plurality of gallery match scores between the gallery sample and a plurality of other samples;
a number of the plurality of gallery match scores that are greater than the determined first match score;
a plurality of probe match scores between the probe sample and the plurality of other samples;
a number of the plurality of probe match scores that are greater than the determined first match score; and
automatically performing an analysis to attempt to identify the individual by using information from the above determining steps to improve match/no match decisions for one or more of biometric enabled access control, fingerprint search, facial recognition and iris identification.
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.
-
Citations
22 Claims
-
1. A method of using impostor match behavior of biometric gallery samples to add a false match probability score to a match score to assist with match/no match decisions to identify an individual comprising:
-
determining, using an interconnected processor and memory; a first match score between a biometric probe sample and a gallery sample; as the false match probability score, a plurality of gallery match scores between the gallery sample and a plurality of other samples; a number of the plurality of gallery match scores that are greater than the determined first match score; a plurality of probe match scores between the probe sample and the plurality of other samples; a number of the plurality of probe match scores that are greater than the determined first match score; and automatically performing an analysis to attempt to identify the individual by using information from the above determining steps to improve match/no match decisions for one or more of biometric enabled access control, fingerprint search, facial recognition and iris identification. - View Dependent Claims (7, 8, 9, 10)
-
-
2. A method of using impostor match behavior of biometric gallery samples to add a false match probability score to a match score to assist with match/no match decisions when there is a multi-sample probe comprising:
-
determining, using a processor and memory; a first match score between a first probe sample and a first gallery sample; as the false match probability score, a plurality of gallery match scores between the first gallery sample and a plurality of other samples; a number of the plurality of gallery match scores that are greater than the determined first match score; a plurality of probe match scores between the first probe sample and the plurality of other samples; a number of the plurality of probe match scores that are greater than the determined first match score; a second match score of a second probe sample and a second gallery sample; a plurality of gallery match scores between the second gallery sample and the plurality of other samples; a number of the plurality of gallery match scores that are greater than the determined second match score; a plurality of probe match scores between the second probe sample and the plurality of other samples; a number of the plurality of probe match scores that are greater than the determined second match score; combining, using the processor and the memory, information from the first probe sample and the second probe sample to determine a false match probability level; and automatically performing an analysis to attempt to identify an individual by using information from the above steps to improve the match/no match decisions for one or more of biometric-enabled access control, fingerprint search, facial recognition and iris identification. - View Dependent Claims (11, 12)
-
-
3. A method of using impostor match behavior of biometric gallery samples to add a false match probability score to a match score to assist with match/no match decisions in a multi-modal environment comprising:
-
determining, using a processor and memory; a first match score of a first probe sample corresponding to a mode and a first gallery sample; as the false match probability score, a plurality of gallery match scores between the first gallery sample and a plurality of other samples; a number of the plurality of gallery match scores that are greater than the determined first match score; a plurality of probe match scores between the first probe sample and a plurality of other samples; a number of the plurality of probe match scores that are greater than the determined first match score; a second match score of a second probe sample corresponding to a second mode and a second gallery sample; a plurality of gallery match scores between the second gallery sample and a plurality of other samples; a number of the plurality of gallery match scores that are greater than the determined second match score; a plurality of probe match scores between the second probe sample and a plurality of other samples; a number of the plurality of probe match scores that are greater than the determined second match score; combining, using the processor and the memory information from the first probe sample and the second probe sample to determine a false match probability level; and automatically performing an analysis to attempt to identify an individual by using information from the above steps to improve the match/no match decisions for one or more of biometric-enabled access control, fingerprint search, facial recognition and iris identification. - View Dependent Claims (13, 14)
-
-
4. A system that uses impostor match behavior of biometric gallery samples to add a false match probability score to a match score to assist with match/no match decisions comprising:
-
a match score module, a processor and memory configured to; determine a first match score between a biometric probe sample from an access control system or a fingerprint scanner and a gallery sample; determine, as the false match probability score, a plurality of gallery match scores between the gallery sample and a plurality of other samples; 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; determine a number of the plurality of probe match scores that are greater than the determined first match score; and automatically performing an analysis to attempt to identify an individual by using information from the above determining steps to improve the match/no match decisions for one or more of biometric-enabled access control, fingerprint search, facial recognition and iris identification. - View Dependent Claims (15, 16, 17, 18)
-
-
5. A system that uses impostor match behavior of biometric gallery samples to add a false match probability score to a match score to assist with match/no match decisions when there is a multi-sample probe comprising:
-
a match score module, a processor and memory configured to; determine a first match score between a first probe sample from an access control system or a fingerprint scanner and a first gallery sample; determine, as the false match probability score, a plurality of gallery match scores between the first gallery sample and a plurality of other samples; 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 first probe sample and the plurality of other samples; determine a number of the plurality of probe match scores that are greater than the determined first match score; determine a second match score of a second probe sample and a second gallery sample; determine a plurality of gallery match scores between the second gallery sample and the plurality of other samples; determine a number of the plurality of gallery match scores that are greater than the determined second match score; determine a plurality of probe match scores between the second probe sample and the plurality of other samples; determine a number of the plurality of probe match scores that are greater than the determined second match score; combine, by the processor, information from the first probe sample and the second probe sample to determine a false match probability level; and automatically perform an analysis to attempt to identify an individual by using information from the above steps to improve the match/no match decisions for one or more of biometric-enabled access control, fingerprint search, facial recognition and iris identification. - View Dependent Claims (19, 20)
-
-
6. A system that uses impostor match behavior of biometric gallery samples to add a false match probability score to a match score to assist with match/no match decisions in a multi-modal environment comprising:
-
a match score module, a processor and memory configured to; determine a first match score of a first probe sample from an access control system or a fingerprint scanner corresponding to a mode and a first gallery sample; determine, as the false match probability score, a plurality of gallery match scores between the first gallery sample and a plurality of other samples; 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 first probe sample and a plurality of other samples; determine a number of the plurality of probe match scores that are greater than the determined first match score; determine a second match score of a second probe sample corresponding to a second mode and a second gallery sample; determine a plurality of gallery match scores between the second gallery sample and a plurality of other samples; determine a number of the plurality of gallery match scores that are greater than the determined second match score; determine a plurality of probe match scores between the second probe sample and a plurality of other samples; determine a number of the plurality of probe match scores that are greater than the determined second match score; and combine, using the processor, information from the first probe sample and the second probe sample to determine a false match probability level; and automatically performing an analysis to attempt to identify an individual by using information from the above steps to improve the match/no match decisions for one or more of biometric-enabled access control, fingerprint search, facial recognition and iris identification. - View Dependent Claims (21, 22)
-
Specification