SYSTEMS AND METHODS OF IDENTIFICATION BASED ON BIOMETRIC PARAMETERS

• US 20090232361A1
• Filed: 03/17/2008
• Published: 09/17/2009
• Est. Priority Date: 03/17/2008
• Status: Active Grant

• Current Assignee: HALO Wearables LLC
• Original Assignee: Ensign Holdings LLC
• Inventors: Miller, David R.
• Granted Patent: US 8,150,108 B2
• Time in Patent Office: Days
• US Class Current: 382/115
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 10/811 the classifiers operating on different input data, e.g. multi-modal recognition
• CPC Class Codes: G06V 40/50 Maintenance of biometric data or enrolment thereof
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities

Abstract

Systems and methods for authenticating a user are disclosed. In some embodiments, information regarding multiple biometric parameters is gathered from a test subject and compared with a validation template. The validation template can be augmented with some or all of the information if the user is successfully authenticated.

Claims

1. A method of authentication, the method comprising:

obtaining from a user a plurality of first measurements corresponding to a first biometric parameter, wherein at least some of the first measurements are obtained at different times;

obtaining from the user a plurality of second measurements corresponding to a second biometric parameter, wherein at least some of the second measurements are obtained at different times;

analyzing the plurality of first measurements to obtain a first correlation value;

analyzing the plurality of second measurements to obtain a second correlation value;

combining the first and second measurements into a first composite dataset in which the first measurements are weighted according to the first correlation value and the second measurements are weighted according to the second correlation value;

obtaining a first test measurement corresponding to the first biometric parameter;

obtaining a second test measurement corresponding to the second biometric parameter; and

providing a confidence level of user authentication based on a comparison of the first and second test measurements with the first composite dataset.

2. The method of claim 1, further comprising granting the user access to a first restricted destination if the confidence level is above a first threshold value.

3. The method of claim 2, further comprising denying the user access to a second restricted destination if the confidence level is above the first threshold value and below a second threshold value.

4. The method of claim 1, further comprising supplementing the plurality of first measurements with the first test measurement if the confidence level is above a first threshold value.

5. The method of claim 4, further comprising augmenting the plurality of second measurements with the second test measurement if the confidence level is above the first threshold value.

6. The method of claim 4, further comprising withholding the second test measurement from augmenting the plurality of second measurements if the confidence level is above the first threshold value and below a second threshold value.

7. The method of claim 1, further comprising:

analyzing the first test measurement in combination with the plurality of first measurements to obtain a third correlation value; and

supplementing the plurality of first measurements with the first test measurement if the confidence level is above a threshold value and the third correlation value is within a predetermined range.

8. The method of claim 7 further comprising withholding the first test measurement from supplementing the plurality of second measurements if the confidence level is above the threshold value and the third correlation value is outside the predetermined range.

9. The method of claim 1, wherein said analyzing of the plurality of first measurements comprises weighting the first measurements according to the chronological order in which the first measurements were obtained such that a newer measurement is weighted more heavily than an older measurement.

10. The method of claim 9, wherein said analyzing of the plurality of second measurements comprises weighting the second measurements according to the chronological order in which the second measurements were obtained such that a newer measurement is weighted more heavily than an older measurement.

11. The method of claim 1, wherein said comparison of the first and second test measurements with the first composite dataset comprises:

combining a weighted version of the first and second test measurements into a second composite dataset, wherein weighting of the first test measurement is based on the first correlation value and weighting of the second test measurement is based on the second composite dataset; and

comparing the second composite dataset with the first composite dataset.

12. The method of claim 1, wherein said obtaining from a user a plurality of first measurements includes enrolling the user with respect to the first biometric parameter and said obtaining from a user a plurality of second measurements includes enrolling the user with respect to the second biometric parameter.

13. A method of authentication, the method comprising:

obtaining from a user a plurality of first measurements corresponding to a first biometric parameter, wherein at least some of the first measurements are obtained at different times;

obtaining from the user a plurality of second measurements corresponding to a second biometric parameter, wherein at least some of the second measurements are obtained at different times;

obtaining a first test measurement corresponding to the first biometric parameter;

obtaining a second test measurement corresponding to the second biometric parameter;

analyzing a combination of the plurality of first measurements and the first test measurement to obtain a first correlation value;

analyzing a combination of the plurality of second measurements and the second test measurement to obtain a second correlation value; and

combining a weighted version of the first and second test measurements into a composite dataset, wherein weighting of the first test measurement is based on the first correlation value and weighting of the second test measurement is based on the second correlation value; and

comparing the composite dataset with a combination of the plurality of first measurements and the plurality of second measurements to determine a confidence level of user authentication.

14. The method of claim 13, further comprising granting the user access to a restricted destination if the confidence level is above a threshold value.

15. The method of claim 13, further comprising supplementing the plurality of first measurements with the first test measurement and supplementing the plurality of second measurements with the second test measurement if the confidence level is above a threshold value.

16. The method of claim 13, further comprising:

comparing the first correlation value with a predetermined range; and

supplementing the plurality of first measurements with the first test measurement if the first correlation value is within the predetermined range and if the confidence level is above a threshold value.

17. The method of claim 13, wherein said analyzing a combination of the plurality of first measurements and the first test measurement to obtain the first correlation value comprises weighting the first measurements and the first test measurement according to the chronological order in which said measurements were obtained such that a newer measurement is weighted more heavily than an older measurement, and

wherein said analyzing a combination of the plurality of second measurements and the second test measurement to obtain the second correlation value comprises weighting the second measurements and the second test measurement according to the chronological order in which said measurements were obtained such that a newer measurement is weighted more heavily than an older measurement.

18. The method of claim 13, wherein said combination of the plurality of first measurements and the plurality of second measurements is obtained by weighting the plurality of first measurements according to the first correlation value and weighting the plurality of second measurements according to the second correlation value.

19. A method of authentication, the method comprising:

obtaining from a user a first comparison dataset comprising a plurality of first measurements of a first biometric parameter, wherein each first measurement is associated with a time at which the measurement was obtained;

obtaining from the user a second comparison dataset comprising a plurality of second measurements of a second biometric parameter, wherein each second measurement is associated with a time at which the measurement was obtained;

obtaining a first test dataset comprising a first test measurement associated with a first test time;

obtaining a second test dataset comprising a second test measurement associated with a second test time;

combining the first and second comparison datasets into a composite dataset; and

comparing the first and second test datasets with the composite dataset to provide a confidence level of user authentication.

20. The method of claim 19, further comprising updating the first comparison dataset to include the first test dataset and updating the second comparison dataset to include the second test dataset if the confidence level is above a threshold value.

21. The method of claim 19, wherein combining the first and second comparison datasets into a composite dataset comprises:

analyzing at least the first comparison dataset to obtain a first correlation value;

analyzing at least the second comparison dataset to obtain a second correlation value;

weighting at least the first comparison dataset based on the first correlation value; and

weighting at least the second comparison dataset based on the second correlation value.

22. The method of claim 21, wherein said analyzing at least the first comparison dataset comprises weighting the first measurements according to the chronological order in which said measurements were obtained such that a newer measurement is weighted more heavily than an older measurement, and

said analyzing at least the second comparison dataset comprises weighting the second measurements according to the chronological order in which said measurements were obtained such that a newer measurement is weighted more heavily than an older measurement.

23. The method of claim 21, wherein said analyzing at least the first comparison dataset to obtain the first correlation value further includes analyzing the first test dataset in combination with the first comparison dataset, and

said analyzing at least the second comparison dataset to obtain the second correlation value further includes analyzing the second test dataset in combination with the second comparison dataset.

24. A method of authentication, the method comprising:

obtaining from a user a plurality of first measurements of a first biometric parameter, wherein at least some of the first measurements are obtained at different times;

obtaining from the user a plurality of second measurements of a second biometric parameter, wherein at least some of the second measurements are obtained at different times;

combining the first and second plurality of measurements into a composite dataset in which measurements obtained during a later timeframe are afforded greater weight than measurements obtained during an earlier timeframe;

obtaining a first test measurement of the first biometric parameter;

obtaining a second test measurement of the second biometric parameter;

comparing the first and second test measurements with the composite dataset; and

providing a confidence level of user authentication based on the comparison of the first and second test measurements with the composite dataset.

25. The method of claim 24, further comprising supplementing the plurality of first measurements with the first test measurement and supplementing the plurality of second measurements with the second test measurement if the confidence level is above a threshold value.

26. The method of claim 24, wherein statistical analysis of the plurality of first measurements yields a first value and statistical analysis of the plurality of second measurements yields a second value that is smaller than the first value, and wherein comparing the first and second test measurements with the composite dataset comprises combining the first and second test measurements into a composite test dataset in which the first test measurement is afforded less weight than is the second test measurement.

27. A method for authenticating a user, the method comprising:

obtaining from the user a first measurement of a first biometric parameter and a first measurement of a second biometric parameter within a first period of time, wherein the first biometric parameter is different from the second biometric parameter;

obtaining from the user a second measurement of the first biometric parameter and a second measurement of the second biometric parameter within a second period of time that is subsequent to the first period of time;

obtaining a third measurement of the first biometric parameter and a third measurement of the second biometric parameter within a third period of time that is subsequent to the second period of time;

comparing the third measurements with a weighted combination of the first measurements and second measurements, wherein the second measurements are more heavily weighted than the first measurements; and

providing a confidence level of user authentication, wherein the confidence level is based on comparing the third measurements with the weighted combination of the first measurements and second measurements.

28. The method of claim 27, further comprising granting the user access to a restricted destination if the confidence level is above a threshold value.

29. The method of claim 27, further comprising updating a template based on the third measurements if the confidence level is above a threshold value.

30. The method of claim 29, further comprising:

obtaining a fourth measurement of the first biometric parameter and a fourth measurement of the second biometric parameter within a fourth period of time; and

comparing the fourth measurements with a weighted combination of at least the second measurements and the third measurements, wherein the third measurements are more heavily weighted than the second measurements.

31. The method of claim 30, wherein the fourth measurements are compared with a weighted combination of the first measurements, the second measurements, and the third measurements, wherein the third measurements are more heavily weighted than the second measurements and the second measurements are more heavily weighted than the first measurements.

32. The method of claim 27, wherein the third measurement of the first biometric parameter and the third measurement of the second biometric parameter are combined into a weighted combination that is compared with the weighted combination of the first measurements and second measurements.

33. The method of claim 32, further comprising:

representing one or more quality metrics of the third measurement of the first biometric parameter with a first value; and

representing one or more quality metrics of the third measurement of the second biometric parameter with a second value,

wherein weighting of the third measurement of the first biometric parameter is further based on the first value and weighting of the third measurement of the second biometric parameter is further based on the second value.

34. The method of claim 32, wherein the third measurement of the first biometric parameter is weighted according to a degree of agreement between the first and second measurements of the first biometric parameter.

35. The method of claim 32, wherein the first biometric parameter is more likely to uniquely identify an individual than is the second biometric parameter, and wherein the first, second, and third measurements of the first biometric parameter are more heavily weighted than the first, second, and third measurements of the second biometric parameter, respectively.

36. The method of claim 27, wherein each of the first biometric parameter and second biometric parameter is selected from the group consisting of fingerprints, facial scans, retinal scans, iris scans, voice signatures, cardiac cycle signatures, and vein thermal profiles.

37. A system for authenticating a user, the system comprising:

a first device configured to obtain one or more measurements of a first biometric parameter;

a second device configured to obtain one or more measurements of a second biometric parameter that is different from the first biometric parameter;

one or more storage devices configured to store;

a first measurement of the first biometric parameter and a first measurement of the second biometric parameter that are obtained within a first time period; and

a second measurement of the first biometric parameter and a second measurement of the second biometric parameter that are obtained within a second time period subsequent to the first time period; and

one or more processors configured to;

combine the first measurements and the second measurements into a weighted combination, with the second measurements being weighted greater than the first measurements;

compare a third measurement of the first biometric parameter obtained via the first device within a third period of time and a third measurement of the second biometric parameter obtained via the second device within the third period of time with the weighted combination of the first measurements and second measurements, wherein the third period of time is subsequent to the second period of time; and

provide a confidence level of user authenication, wherein the confidence level is based on the weighted combination of the first measurements and second measurements.

38. A method of authenticating a test subject as a user, the method comprising:

providing a template comprising information regarding a first biometric parameter and information regarding a second biometric parameter, wherein the template is based on measurements obtained from the user;

obtaining a first set of information from the test subject regarding the first biometric parameter;

associating a first score with the first set of information based on one or more quality metrics of the first set of information;

obtaining a second set of information from the test subject regarding the second biometric parameter;

associating a second score with the second set of information based on one or more quality metrics of the second set of information;

comparing the template with a weighted combination of the first set of information and the second set of information, wherein the weighting of the first set of information is based on the first score and the weighting of the second set of information is based on the second score; and

providing a confidence level regarding whether the test subject is the user, wherein the confidence level is based on said comparing of the weighted combination of the template with the first and second sets of information.

39. The method of claim 38, further comprising updating the template based on the first and second sets of information if the confidence level is above a threshold value.

40. The method of claim 38, further comprising:

altering a first fusion parameter regarding the first biometric parameter based on at least one or more prior authentications of the user; and

altering a second fusion parameter regarding the second biometric parameter based on at least one or more prior authentications of the user,

wherein the weighting of the first set of information is further based on the first fusion parameter and the weighting of the second set of information is further based on the second fusion parameter.

41. The method of claim 38, wherein the weighting of the first set of information is further based on the capacity of the first biometric parameter to uniquely identify an individual and the weighting of the second set of information is further based on the capacity of the second biometric parameter to uniquely identify an individual.

42. The method of claim 38, wherein the first score is substantially different from the second score such that the confidence level is based more on the first set of information than on the second set of information.

43. The method of claim 42, wherein the first score is sufficiently different from the second score such that the confidence level is based substantially entirely on the first set of information.

44. The method of claim 38, wherein the one or more quality metrics of the first set of information and the one or more quality metrics of the second set of information are selected from the group consisting of the level of completeness of a set of information, the signal-to-noise ratio of a set of information, the presence of disqualifying features in a set of information, and the conformance of a set of information to an expected signature profile.

45. A method of authentication, the method comprising:

providing a template comprising a first set of information regarding a first biometric parameter and a second set of information regarding a second biometric parameter;

authenticating a user one or more times based on the template;

altering a first fusion parameter regarding the first set of information as a result of authenticating the user one or more times;

altering a second fusion parameter regarding the second set of information as a result of authenticating the user one or more times;

obtaining a third set of information regarding the first biometric parameter;

obtaining a fourth set of information regarding the second biometric parameter;

comparing the third and fourth sets of information with a weighted version of the template, wherein the first set of information is weighted according to the first fusion parameter and the second set of information is weighted according to the second fusion parameter in the weighted version of the template; and

providing a confidence level of user authentication based on said comparing of the third and fourth sets of information with the weighted version of the template.

46. The method of claim 45, further comprising altering the first fusion parameter based on the third set of information and altering the second fusion parameter based on the fourth set of information if the confidence level is sufficient to identify the test subject as the user.

47. A method of authenticating a user, the method comprising:

providing a template comprising a plurality of first measurements obtained from a user, the plurality of first measurements being of a first biometric parameter;

obtaining a test measurement of the first biometric parameter;

comparing the test measurement of the first biometric parameter with the template to obtain a confidence level of user authentication;

granting the user access to a first restricted destination if the confidence level is above a first threshold value; and

denying the user access to a second restricted destination if the confidence level is below a second threshold value.

48. The method of claim 47, further comprising granting the user access to the second restricted destination if the confidence level is above the second threshold value and denying the user access to a third restricted destination if the confidence level is below a third threshold value.

49. The method of claim 47, wherein the template further comprises a plurality of second measurements obtained from the user, the plurality of second measurements being of a second biometric parameter, and wherein the method further comprises:

obtaining a test measurement of the second biometric parameter; and

comparing the test measurement of the second biometric parameter with the template to obtain the confidence level of user authentication.

50. The method of claim 49, wherein the first restricted destination comprises one of a secured physical location, vehicle, Internet site, intranet site, computer program, and hardware component.