Biometric identification and verification

• US 8,559,681 B2
• Filed: 04/27/2009
• Issued: 10/15/2013
• 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): Patel, Jayesh A
• Assistant Examiner(s): Kholdebarin, Iman K
• Application Number:
  US12/988,056
• Publication Number:
  US 20120087549A1
• Time in Patent Office: 1,632 Days
• Field of Search: 382/115, 235/382
• US Class Current: 382/115
• 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 for setting a threshold in a biometric system by using imposter match score data to derive a match threshold score that results in a desired false match rate comprising:

creating a database of match scores between all unique impostor biometric sample pairs;

creating, using a processor, a cumulative histogram data table that records, for each possible match score outcome, a number of match scores observed greater than the threshold divided by the total number of samples;

using the cumulative histogram data table to determine the threshold;

selecting the desired false match rate and determining the threshold that will result in the desired false match rate; and

determining a false match probability level.

2. A method for setting a threshold in a biometric system using genuine match score data to automate derivation of a match threshold score that results in a desired false non-match rate comprising:

creating a database of match scores between all unique genuine biometric sample pairs;

creating, using a processor, a cumulative histogram data table that records, for each possible match score outcome, a number of match scores observed greater than the threshold divided by the total number of samples;

using the cumulative histogram data table to determine a threshold;

selecting the desired false non-match rate and determining the threshold that will result in the desired false non-match rate; and

determining a false match probability level.

3. A method of using previous genuine and impostor biometric match score data to automate derivation of an individualized verification match threshold score comprising:

for each individual enrolled in a biometric system;

generating a database of match scores observed between all genuine and all impostor samples, and

creating, using a processor, a first cumulative histogram data table that records a number of the impostor match scores that are greater than that score divided by the total number of samples; and

for each individual enrolled in the biometric system;

generating a database of match scores observed between all the genuine samples, and

creating a second cumulative histogram data table that records a value for each possible match score less than that score divided by the total number of samples;

utilizing a match threshold that results in a false match rate that matches performance within a targeted range, wherein the match threshold is derived from the first cumulative histogram data table; and

determining a false match probability level.

4. A method of using previous genuine and impostor biometric match score data to automate derivation of an individualized verification match threshold score comprising:

for each individual enrolled in a biometric system;

generating a database of match scores observed between all genuine and all impostor samples,

creating, using a processor, a first cumulative histogram data table that records the number of these impostor match scores that are greater than that score divided by the total number of samples; and

for each individual enrolled in the biometric system;

generating a database of match scores observed between all genuine samples,

creating a second cumulative histogram data table that records a value for each possible match score less than that score divided by the total number of samples;

utilizing a match threshold that results in a false non-match rate that matches performance within a targeted range, wherein the match threshold is derived from the second cumulative histogram data table; and

determining a false match probability level.

5. A computer-based system for setting a threshold in a biometric system using imposter match score data to derive a match threshold score that results in a desired false match rate comprising:

a match score module that creates a database of match scores between all unique impostor biometric sample pairs;

a histogram module that creates a cumulative histogram data table that records for each possible match score outcome a number of match scores observed greater than the threshold divided by the total number of samples;

a threshold module and a processor that select the desired false match rate and determines the threshold that will result in the desired false match rate, wherein the cumulative histogram data table is used to determine the threshold; and

a confidence level module that determines a false match probability level.

6. A computer-based system for setting a threshold in a biometric system using genuine match score data to automate derivation of a match threshold score that results in a desired false non-match rate comprising:

a match score module that creates a database of match scores between all unique genuine biometric sample pairs;

a histogram module that creates a cumulative histogram data table that records for each possible match score outcome a number of match scores observed greater than the threshold divided by the total number of samples;

a threshold module and a processor that select the desired false non-match rate and determines the threshold that will result in the desired false non-match rate, wherein the cumulative histogram data table is used to determine the threshold; and

a confidence level module that determines a false match probability level.

7. A computer-based system of using previous genuine and impostor biometric match score data to automate derivation of an individualized verification match threshold score comprising:

for each individual enrolled in a biometric system;

a match score module that generates a database of match scores observed between all genuine and all impostor samples, and

a histogram module that creates a first cumulative histogram data table that records a number of the impostor match scores that are greater than that score divided by the total number of samples; and

for each individual enrolled in the biometric system;

the match score module generates a database of match scores observed between all the genuine samples, and

a histogram module creates a second cumulative histogram data table that records a value for each possible match score less than that score divided by the total number of samples;

a threshold module and a processor that utilize a match threshold that results in a false match rate that matches performance within a targeted range, wherein the first cumulative histogram data table is used to determine the match threshold; and

a confidence level module that determines a false match probability level.

8. A computer-based system of using previous genuine and impostor biometric match score data to automate derivation of an individualized verification match threshold score comprising:

for each individual enrolled in a biometric system;

a match score module that generates a database of match scores observed between all genuine and all impostor samples,

a histogram module that creates a first cumulative histogram data table that records the number of these impostor match scores that are greater than that score divided by the total number of samples; and

for each individual enrolled in the biometric system;

the match score module generates a database of match scores observed between all genuine samples,

the match score module creates a second cumulative histogram data table that records a value for each possible match score less than that score divided by the total number of samples; and

a threshold module and a processor that utilize a match threshold that results in a false non-match rate that matches performance within a targeted range, wherein the second cumulative histogram data table is used to determine the match threshold; and

a confidence level module that determines a false match probability level.