Method and apparatus for characterizing and estimating the parameters of histological and physiological biometric markers for authentication

• US 7,441,123 B2
• Filed: 03/23/2001
• Issued: 10/21/2008
• Est. Priority Date: 03/23/2001
• Status: Active Grant

• Current Assignee: HALO Wearables LLC
• Original Assignee: Ensign Holdings Limited (Co-Operative Group Limited)
• Inventors: Pettit, Matthew W., Murakami, Rick V., Grant, J. Spencer, Hinton, Clark
• Primary Examiner(s): Schaetzle; Kennedy J
• Assistant Examiner(s): SARCIONE, JESSICA LYNN
• Application Number:
  US09/815,885
• Publication Number:
  US 20070016088A1
• Time in Patent Office: 2,769 Days
• Field of Search: 713/186, 382/115, 128/920, 128/923, 128/924, 600508-509
• US Class Current: 713/186
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/117 Identification of persons methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 2218/10 by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
• CPC Class Codes: G06V 40/1341 Sensing with light passing through the finger
• CPC Class Codes: G06V 40/14 Vascular patterns
• CPC Class Codes: G06V 40/15 Biometric patterns based on physiological signals, e.g. heartbeat, blood flow
• CPC Class Codes: G07C 9/37 using biometric data, e.g. fingerprints, iris scans or voice recognition

Abstract

A plurality of electronic signals corresponding to a histological and/or physiological marker, such as a heartbeat, are obtained, from an individual and are converted into electronic signal form. The signals are measured to obtain an actual measurement of a plurality of variable features of the electronic signals relating to the heartbeats. The measurements are mathematically analyzed to provide the probability of divergence of each actual measurement. Using the calculated probability of divergence, subsequent received waveforms measurements are analyzed for authentication purposes.

Claims

1. A method in a computer system for individualizing a heartbeat signal for use as a biometric marker comprising the steps of:

acquiring a plurality of electronic heartbeat signals from an individual in an electronic signal form using an optical sensor;

for each electronic heartbeat signal, measuring, a plurality of pre-selected heartbeat waveform features to generate corresponding measurements;

weighting the pre-selected heartbeat waveform features;

providing a different statistical weight for each pre-selected heartbeat waveform feature; and

authenticating an individual based on the weighted pre-selected heartbeat waveform features.

2. The method of claim 1 further comprising:

for each electronic heartbeat signal, measuring an additional pre-selected heartbeat waveform feature to generate a corresponding additional measurement; and

preventing the weighting of the additional pre-selected heartbeat waveform feature in the statistical analysis.

3. The method of claim 1 further comprising:

individualizing the measurements of the pre-selected heartbeat waveform features; and

calculating probabilities for the measurements.

4. The method of claim 3, wherein individualizing the measurements comprises:

subtracting each corresponding measurement from an average value of the measurements to yield a centroid value for each pre-selected heartbeat waveform feature,

dividing each centroid value by a standard deviation to yield a quotient value,

determining a probability of the quotient value using a distribution calculation, and

selecting a threshold minimum probability.

5. The method of claim 4, wherein calculating probabilities for the measurements comprises calculating a probability of divergence for each measurement using the quotient value.

6. The method of claim 5, wherein calculating the probability of divergence using the quotient value includes using the quotient value in a T-distribution analysis.

7. The method of claim 1, further comprising:

calculating an average for each of said pre-selected heartbeat waveform features from said measurements;

subtracting the average from each corresponding measurement to yield a centroid value;

calculating a standard deviation for each pre-selected heartbeat waveform feature;

dividing the corresponding centroid value by the standard deviation for each pre-selected heartbeat waveform feature; and

calculating a probability of divergence for each measurement corresponding to each pre-selected heartbeat waveform feature.

8. The method of claim 7 further comprising:

for each electronic heartbeat signal, measuring an additional pre-selected heartbeat waveform feature to generate a corresponding additional measurement; and

preventing the weighting of the additional pre-selected heartbeat waveform feature in the statistical analysis.

9. The method of claim 1, wherein the pre-selected heartbeat waveform features include univariate features of a heartbeat waveform.

10. The method of claim 9, wherein the pre-selected heartbeat waveform features include multivariate features of a heartbeat waveform.

11. The method of claim 1, wherein a pre-selected heartbeat waveform feature is a position of a dicrotic notch.

12. The method of claim 1, wherein a pre-selected heartbeat waveform feature is a difference between two peak pressure amplitudes.

13. The method of claim 1, wherein a pre-selected heartbeat waveform feature is a difference between two peak pressure change rates.

14. The method of claim 1, wherein a pre-selected heartbeat waveform feature reflects how far a dicrotic notch is from a zero point.

15. The method of claim 1, wherein a pre-selected heartbeat waveform feature is an up slope of a maximum peak pressure.

16. The method of claim 1, wherein a pre-selected heartbeat waveform feature is a down slope of a maximum peak pressure.

17. The method of claim 1 further comprising:

establishing a threshold probability value for each pre-selected heartbeat waveform feature, wherein the threshold value reflects a desired consistency and selectivity.

18. A computer readable storage medium containing instructions for controlling a computer system to perform a method to individualize a heartbeat electronic signal for use in biometric authentication, the method comprising:

acquiring a plurality of electronic heartbeat signals from an individual in an electronic signal form using an optical sensor;

for each electronic heartbeat signal, measuring one or more pre-selected heartbeat waveform features to generate corresponding measurements;

weighing the pre-selected heartbeat waveform features;

providing a different statistical weight for each of the one or more pre-selected heartbeat waveform features; and

authenticating a user using said weighed pre-selected heartbeat waveform features.

19. The computer readable storage medium of claim 18 where said measurements are made on only one heartbeat waveform feature per acquisition.

20. The computer readable storage medium of claim 18 where said measurements are made on two heartbeat waveform features per acquisition.

21. The computer readable storage medium of claim 18 where said measurements are made on a plurality of heartbeat waveform features per acquisition.

22. The computer readable storage medium of claim 18, wherein said method further comprises:

individualizing the measurements of the pre-selected heartbeat waveform features, and

calculating probabilities for the measurements.

23. The computer readable storage medium of claim 22, wherein individualizing the measurements comprises:

for each pre-selected heartbeat waveform feature, subtracting each corresponding measurement from an average value of the measurements to yield a centroid value,

dividing each centroid value by a standard deviation to yield a quotient value,

determining a probability of the quotient value using a distribution calculation, and

selecting a threshold minimum probability.

24. The computer readable storage medium of claim 23, wherein calculating probabilities for the measurements comprises calculating a probability of divergence for each measurement using the quotient value.

25. The computer readable storage medium of claim 24, wherein calculating the probability of divergence using the quotient value includes using the quotient value in a T-distribution analysis.

26. The computer readable storage medium of claim 18, wherein said method further comprises:

calculating an average for each of said pre-selected heartbeat waveform features from said measurements;

subtracting the average from each corresponding measurement to yield a centroid value;

calculating a standard deviation for each pre-selected heartbeat waveform feature;

dividing the corresponding centroid value by the standard deviation for each pre-selected heartbeat waveform feature; and

calculating a probability of divergence for each measurement corresponding to each pre-selected heartbeat waveform feature.

27. The computer readable storage medium of claim 18, wherein said method further comprises authenticating an individual based on the weighted pre-selected heartbeat waveform features.

28. The computer readable storage medium of claim 18, wherein the pre-selected heartbeat waveform features include univariate features of a heartbeat waveform.

29. The computer readable storage medium of claim 28, wherein the pre-selected heartbeat waveform features include multivariate features of a heartbeat waveform.

30. The computer readable storage medium of claim 18, wherein a pre-selected heartbeat waveform feature is a position of a dicrotic notch.

31. The computer readable storage medium of claim 18, wherein a pre-selected heartbeat waveform feature is a difference between two peak pressure amplitudes.

32. The computer readable storage medium of claim 18, wherein a pre-selected heartbeat waveform feature is a difference between two peak pressure change rates.

33. The computer readable storage medium of claim 18, wherein a pre-selected heartbeat waveform feature reflects how far a dicrotic notch is from a zero point.

34. The computer readable storage medium of claim 18, wherein a pre-selected heartbeat waveform feature is an up slope of a maximum peak pressure.

35. The computer readable storage medium of claim 18, wherein a pre-selected heartbeat waveform feature is a down slope of a maximum peak pressure.

36. The computer readable storage medium of claim 18, wherein said method further comprises:

establishing a threshold probability value for each pre-selected heartbeat waveform feature, wherein the threshold value reflects a desired consistency and selectivity.

37. The computer readable storage medium of claim 18, wherein said method further comprises:

measuring an additional pre-selected heartbeat waveform feature to generate a corresponding additional measurement for each electronic heartbeat signal; and

preventing the weighting of the additional pre-selected heartbeat waveform feature in the statistical analysis.