Method and apparatus for electro-biometric identity recognition

• US 7,689,833 B2
• Filed: 11/09/2004
• Issued: 03/30/2010
• Est. Priority Date: 07/29/2002
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Idesia Limited
• Inventors: Lange, Daniel H.
• Primary Examiner(s): Moorthy; Aravind K
• Application Number:
  US10/984,200
• Publication Number:
  US 20050281439A1
• Time in Patent Office: 1,967 Days
• Field of Search: 713/186, 713/161, 713/168, 726/4, 726/5, 726/17, 726/18, 726/28, 726/29, 382/115
• US Class Current: 713/186
• 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: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 2218/00 Aspects of pattern recognition specially adapted for signal processing
• CPC Class Codes: G06F 2218/06 by applying a scale-space analysis, e.g. using wavelet analysis
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06F 2218/14 by matching peak patterns
• 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 40/15 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 method and apparatus for electro-biometric identity recognition or verification that produces and stores a first biometric signature that identifies a specific individual by forming the difference between a representation of the heartbeat pattern of the specific individual and a stored representation of common features of the heartbeat patterns of a plurality of individuals; after the producing step, the method and apparatus obtains a representation of the heartbeat pattern of a selected individual and produces a second biometric signature by forming the difference between the heartbeat pattern of the selected individual and the stored representation of common features of the heartbeat patterns of the plurality of individuals; it then compares the second biometric signature with the first biometric signature to determine whether the selected individual is the specific individual. The apparatus and method may be employed as a stand-alone unit or as part of another device pursuant to the many applications described herein.

Claims

1. A method for identifying an individual, comprising:

producing and storing a first biometric signature that identifies a specific individual by forming the difference between a representation of a heartbeat pattern of the specific individual and a stored representation of common features of heartbeat patterns of a plurality of individuals;

after said producing step, obtaining a representation of a heartbeat pattern of a selected individual and producing a second biometric signature by forming the difference between the heartbeat pattern of the selected individual and the stored representation of the common features of the heartbeat patterns of the plurality of individuals; and

comparing said second biometric signature with said first biometric signature to determine whether the selected individual is the specific individual.

2. The method of claim 1 wherein:

said step of producing and storing comprises producing and storing a plurality of first biometric signatures, each identifying a respective individual, by forming the difference between a representation of the heartbeat pattern of each respective individual and the stored representation of the common features of the heartbeat patterns; and

said step of comparing is carried out with respect to each of said first biometric signatures.

3. The method of claim 2 comprising a preliminary step of obtaining representations of the heartbeat patterns of a plurality of individuals, and deriving and storing the representation of the common features of the heartbeat patterns of a plurality of individuals from at least a selected number of the representations.

4. The method of claim 3 wherein said step of deriving and storing the representation of the common features of the heartbeat patterns of a plurality of individuals comprises deriving and storing a plurality of representations of the common features of the heartbeat patterns each from a respectively different group of the plurality of individuals.

5. The method of claim 3, wherein said step of deriving and storing the representation of the common features of the heartbeat patterns of a plurality of individuals comprises producing an average of the heartbeat patterns of the plurality of individuals.

6. The method of claim 3, wherein said step of deriving and storing the representation of the common features of the heartbeat patterns of a plurality of individuals comprises performing one of principal component analysis or wavelet decomposition.

7. The method of claim 2 wherein said step of comparing comprises correlating said second biometric signature with each of said first biometric signatures and identifying that one of said first biometric signatures that correlates most closely to said second biometric signature.

8. The method of claim 7, wherein said step of correlating comprises obtaining a correlation coefficient associated with each first biometric signature, and said step of comparing further comprises comparing the correlation coefficient associated with the identified first biometric signature with a correlation coefficient threshold.

9. The method of claim 7 further comprising the steps of:

a) transforming one or more of said correlations; and

b) generating a dynamic threshold for said correlation.

10. The method of biometric identification system of claim 9 wherein the step of transforming one ore more said correlations is used to generate a Z-score.

11. The method of biometric identification of claim 9 wherein said step of transforming said one or more correlations squares said one or more correlations.

12. The method of claim 2 further comprising the steps of:

a) comparing the result of said comparison with an identification threshold; and

b) affecting a locking mechanism based on said comparison.

13. The method of claim 2 further comprising the steps of:

a) comparing the result of said comparison with an identification threshold; and

b) permitting or denying room access based upon said comparison.

14. The method of claim 1 wherein said step of comparing comprises:

correlating said second biometric signature with said first biometric signature to obtain a correlation coefficient; and

comparing the correlation coefficient associated with the first biometric signature with a correlation coefficient threshold.

15. The method of biometric identification of claim 14 further comprising the step of outputting a result of said comparison.

16. The method of claim 1 wherein said step producing and storing a first biometric signature comprises storing the signature in a local database.

17. The method of claim 1 wherein said step producing and storing a first biometric signature comprises storing the signature in a remote database.

18. The method of claim 1 wherein said step of obtaining a representation of the heartbeat pattern of a selected individual comprises compensating for deviations in a pulse rate of the selected individual.

19. The method of claim 1 wherein said step of obtaining a representation of the heartbeat pattern of a selected individual comprises obtaining several representations of heartbeat patterns.

20. The method of claim 1 wherein said step of producing and storing a first biometric signature of a specific individual comprises obtaining a plurality of representations of the heartbeat pattern of the specific individual over a period of time and producing successive first biometric signatures each from a respective one of the plurality of representations of the heartbeat pattern of the specific individual.

21. The method for identifying an individual of claim 1 wherein said stored representation is an analytical representation of common features of heartbeat patterns.

22. The method of claim 1 further comprising the steps of:

a) processing a first ECG signal as part of said step of producing and storing said first biometric signature, an ECG signature template, that is compared with said second biometric signature; and

b) outputting the result of said comparison.

23. The method of claim 22 wherein said processing step removes common features of one or more ECG components from the ECG signal by subtracting common features of one or more ECG components provided by an analytical ECG model.

24. The method of claim 22 further comprising the steps of g) creating a database of such ECG signature templates, h) dividing the ECG signature templates into subsets, and i) using at least one database subset to remove common features of one or more ECG components from an ECG signal.

25. The method of biometric identification of claim 22 further comprising the steps of:

a) correlating said second biometric signature with at least one ECG signature template from a signal taken at a normalized pulse rate or normalized for pulse rate; and

b) comparing the result of said correlation with a threshold.

26. The method of biometric identification system of claim 25 wherein said processing step processes said signal digitally.

27. The method of biometric identification of claim 25 further comprising the step of obtaining a non-ECG biometric reading.

28. The method of biometric identification system of claim 27 further comprising the step of evaluating said non-ECG biometric reading and said outputted comparison result to identify an individual.

29. The method of claim 22 further comprising a step of controlling access to an Internet Website based on the result of said comparison step.

30. The method of claim 29 wherein said comparison step compares said second biometric signature with more than one ECG signature template.

31. The method of claim 29 wherein said comparison step compares the width of a QRS signal complex with the width of one or more reference signal QRS complexes.

32. The method of claim 1 further comprising the step of calculating the quality of a signal used to obtain a representation of a heartbeat pattern.

33. The method of biometric identification system of claim 32 wherein said step of calculating signal quality calculates a Q-value.

34. The method of biometric identification system of claim 32 further comprising the step of adjusting a time of signal acquisition based on the quality of the signal.

35. The method of biometric identification system of claim 32 further comprising the step of acquiring a new signal in response to the signal quality calculation.

36. The method of claim 1 further comprising the steps of:

a) encrypting at least said first signature; and

b) adding said encrypted signature to an enrolled signature database.

37. The method of biometric identification system of claim 36 wherein said signature encryption step scrambles the signature using a public key infrastructure technique.

38. The method of claim 1 further comprising the steps of:

a) acquiring an ECG signal using ultra-high input impedance probes; and

b) processing said ECG signal to generate a biometric signature.

39. The biometric identification system of claim 38 wherein said ultra-high input resistance probes have ultra-low noise characteristics.

40. The method of biometric identification of claim 1 further comprising the step of obtaining a non-ECG biometric reading.

41. The method for identifying an individual of claim 1 further comprising the step of obtaining additional heartbeat patterns and adding them to an individual'"'"'s data file when changes in data signals are encountered.

42. The method of claim 41 further comprising the step of processing newly acquired heartbeat patterns to form an enrolled biometric signature.

43. The method for identifying an individual of claim 1 wherein an enrolled biometric signature database is automatically adjusted to reflect changes in heartbeat pattern over long-term operation.

44. Apparatus for identifying an individual, comprising:

means for producing and storing a first biometric signature that identifies a specific individual by forming the difference between a representation of a heartbeat pattern of the specific individual and a stored representation of common features of the heartbeat patterns of a plurality of individuals;

means for obtaining, after the first biometric signature has been produced and stored, a representation of the heartbeat pattern of a selected individual and producing a second biometric signature by forming the difference between the heartbeat pattern of the selected individual and the stored representation of the common features average of the heartbeat patterns of the plurality of individuals; and

means for comparing said second biometric signature with said first biometric signature to determine whether the selected individual is the specific individual.

45. Apparatus for identifying an individual, comprising:

means for producing and storing a first biometric signature that identifies a specific individual by forming the difference between a representation of a heartbeat pattern of the specific individual and a stored representation of common features of the heartbeat patterns of a plurality of individuals;

means for obtaining, after the first biometric signature has been produced and stored, a representation of the heartbeat pattern of a selected individual and producing a second biometric signature by forming the difference between the heartbeat pattern of the selected individual and the stored representation of a common features average of the heartbeat patterns of a plurality of individuals;

means for comparing said second biometric signature with said first biometric signature to determine whether the selected individual is the specific individual; and

a non-ECG biometric acquisition module.

46. Apparatus for identifying an individual, comprising:

means for producing and storing a first biometric signature that identifies a specific individual by forming the difference between a representation of a heartbeat pattern of the specific individual and a stored representation of common features of the heartbeat patterns of a plurality of individuals;

means for obtaining, after the first biometric signature has been produced and stored, a representation of the heartbeat pattern of a selected individual and producing a second biometric signature by forming the difference between the heartbeat pattern of the selected individual and the stored representation of a common features average of the heartbeat patterns of a plurality of individuals;

means for comparing said second biometric signature with said first biometric signature to determine whether the selected individual is the specific individual; and

means for obtaining additional heartbeat patterns and adding them to an individual'"'"'s data file when changes in data signals are encountered.

47. The apparatus for identifying an individual of claim 46 further comprising means for processing newly acquired heartbeat patterns to form an enrolled biometric signature.

48. Apparatus for identifying an individual, comprising:

means for producing and storing a first biometric signature that identifies a specific individual by forming the difference between a representation of a heartbeat pattern of the specific individual and a stored representation of common features of the heartbeat patterns of a plurality of individuals;

means for obtaining, after the first biometric signature has been produced and stored, a representation of the heartbeat pattern of a selected individual and producing a second biometric signature by forming the difference between the heartbeat pattern of the selected individual and the stored representation of the common features average of the heartbeat patterns of the plurality of individuals;

means for comparing said second biometric signature with said first biometric signature to determine whether the selected individual is the specific individual; and

means for automatically adjusting an enrolled biometric signature database to reflect changes in heartbeat pattern over long-term operation.