Biometric identification and verification

• US 10,438,054 B2
• Filed: 04/03/2018
• Issued: 10/08/2019
• Est. Priority Date: 04/25/2008
• Status: Active Grant

• Current Assignee: Aware Incorporated (Crowley Holdings Preferred LLC)
• Original Assignee: Aware Incorporated (Crowley Holdings Preferred LLC)
• Inventors: Benini, David
• Primary Examiner(s): Kholdebarin, Iman K
• Application Number:
  US15/944,547
• Publication Number:
  US 20180225533A1
• Time in Patent Office: 553 Days
• Field of Search: None
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/1365 Matching; Classification
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/40 Spoof detection, e.g. liveness detection
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities

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.

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.

2. The method of claim 1, wherein the method is for a one-to-many search.

3. The method of claim 1, wherein a single probe sample P1 is compared against a gallery G1 of samples G(x).

4. The method of claim 1, further comprising indicating, when compared to probe sample P1, that three gallery samples G(a), G(b), and G(c) yield match scores equal to or greater than an operating match threshold.

5. The method of claim 4, wherein for each of the three probe/gallery sample pairs P1:

G(a), P1;

G(b), and P1;

G(c), the following is counted;

a) within the corpus of false match score data yielded from the comparison between the probe sample P1 and all gallery G(x) samples, the observed number of occurrences of the false match score being greater than the match score result between the probe P1 and gallery samples G(a), G(b), and G(c);

b) within the corpus of false match score data yielded from the comparison between gallery samples G(a), G(b), and G(c) and the rest of the gallery G1, the observed number of occurrences of false match scores above the match score result of the pair; and

c) a probability of a false match resulting from either P1 or G(X).

6. The method of claim 1, wherein the method further comprises:

determining a second match score of a second probe sample and a second gallery sample;

determining a plurality of gallery match scores between the second gallery sample and the plurality of other samples;

determining a number of the plurality of gallery match scores that are greater than the determined second match score;

determining a plurality of probe match scores between the second probe sample and the plurality of other samples;

determining a number of the plurality of probe match scores that are greater than the determined second match score; and

combining the determined information from the first and second sample to determine a false match probability level.

7. The method of claim 6, wherein the first probe sample is a right sample.

8. The method of claim 6, wherein the second probe sample is a left sample.

9. The method of claim 1, wherein the method is used in a multi-modal environment, wherein the first probe sample corresponds to a mode and a second probe sample corresponds to a second mode.

10. The method of claim 9, wherein the mode is a fingerprint.

11. The method of claim 9, wherein the second mode is a face.

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.

13. The system of claim 12, wherein the system for a one-to-many search.

14. The system of claim 12, wherein a single probe sample P1 is comparable against a gallery G1 of samples G(x).

15. The system of claim 12, further comprising an alert module that indicates, when compared to probe sample P1, that three gallery samples G(a), G(b), and G(c) yield match scores equal to or greater than an operating match threshold.

16. The system of claim 15, wherein for each of the three probe/gallery sample pairs P1:

G(a), P1;

G(b), and P1;

G(c), the following is countable;

a) within the corpus of false match score data yielded from the comparison between the probe sample P1 and all gallery G(x) samples, the observed number of occurrences of the false match score being greater than the match score result between the probe P1 and gallery samples G(a), G(b), and G(c);

b) within the corpus of false match score data yielded from the comparison between gallery samples G(a), G(b), and G(c) and the rest of the gallery G1, the observed number of occurrences of false match scores above the match score result of the pair; and

c) a probability of a false match resulting from either P1 or G(x).

17. The system of claim 12, usable with a multi-sample probe comprising:

a match score module that;

determines a plurality of gallery match scores between the second gallery sample and the plurality of other samples in the gallery;

determines a number of the plurality of gallery match scores that are greater than the determined second match score;

determines a plurality of probe match scores between the second probe sample and the plurality of other samples in the gallery;

determines a number of the plurality of probe match scores that are greater than the determined second match score; and

combines the determined information from the first and second sample to determine a false match probability level.

18. The system of claim 12, wherein the first probe sample is a right sample.

19. The system of claim 12, wherein the second probe sample is a left sample.

20. The system of claim 12, usable for a multimodal environment, wherein a first probe sample corresponds to a mode and a second probe sample corresponds to a second mode.

21. The system of claim 12, wherein the mode is a fingerprint and/or the second mode is a face.