Biometric authentication method and biometric authentication apparatus

• US 7,769,209 B2
• Filed: 10/04/2006
• Issued: 08/03/2010
• Est. Priority Date: 03/14/2006
• Status: Active Grant

• Current Assignee: Fujitsu Frontech Limited (Fujitsu Limited)
• Original Assignee: Fujitsu Frontech Limited (Fujitsu Limited), Fujitsu Limited
• Inventors: Arai, Kiyoshi, Komura, Kazuhiro
• Primary Examiner(s): Desire; Gregory M
• Application Number:
  US11/542,570
• Publication Number:
  US 20070217660A1
• Time in Patent Office: 1,399 Days
• Field of Search: 382/115, 382/190, 704/246, 704/270, 704/270.1, 705/1, 705/39, 705/44, 713/186
• US Class Current: 382/115
• CPC Class Codes: G06F 18/211 Selection of the most significant subset of features
• CPC Class Codes: G06Q 20/3674 involving authentication
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G06V 10/431 Frequency domain transformation; Autocorrelation
• CPC Class Codes: G06V 10/469 Contour-based spatial representations, e.g. vector-coding
• CPC Class Codes: G06V 30/2504 Coarse or fine approaches, e.g. resolution of ambiguities or multiscale approaches
• 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 40/14 Vascular patterns

Abstract

A biometric authentication device, which uses biometrics characteristic information to perform individual authentication, prevents declines in verification speed even when numerous biometrics information sets have been registered. A control unit registers broad characteristic quantities for blood vessel image data from an image capture device, together with characteristic data for verification. And at the time of authentication the control unit uses degrees of similarity of characteristic quantities to determine an order of verification, and performs verification of blood vessel image characteristic data in the verification order thus determined. The order of verification is determined based on captured blood vessel images, so that even when numerous characteristic data sets have been registered, verification can be performed in an order of verification based on a blood vessel image of the user, and the speed of verification can be improved.

Claims

1. A biometric authentication apparatus, which detects biometrics characteristic data of a living body and performs individual authentication, comprising:

a detection device which detects the living body and obtains biometrics information;

a control unit which extracts, from said biometrics information, comparatively coarse first biometrics characteristic data and comparatively fine second characteristic data on a user; and

a biometrics information database file, in which is stored, as biometrics information on said user, said first biometrics characteristic data and said second biometrics characteristic data,

wherein said control unit extracts comparatively coarse first biometrics characteristic data and comparatively fine second characteristic data for use in verification from said biometrics information obtained by said detection device, calculates the degree of similarity between said first biometrics characteristic data for verification and first biometrics characteristic data sets stored in said biometrics database file, determines the order of verification with second biometrics characteristic data sets stored in said biometrics database file according to said degrees of similarity, and performs verification of said second biometrics characteristic data for verification against said stored second biometrics characteristic data sets according to said verification order.

2. The biometric authentication apparatus according to claim 1, wherein said control unit calculates scores indicating a difference between said first biometrics characteristic data for verification and first biometrics characteristic data sets stored in said database file, to obtain said degrees of similarity.

3. The biometric authentication apparatus according to claim 2, wherein said control unit calculates a distance between said first biometrics characteristic data for verification and first biometrics characteristic data stored in said biometrics database file, sorts the distances of said stored data, and determines said verification order.

4. The biometric authentication apparatus according to claim 1, wherein said control unit extracts, as said first biometrics characteristic data, direction components of patterns of said biometrics information.

5. The biometric authentication apparatus according to claim 4, wherein said control unit extracts, as the direction components of said patterns, curvature components of said patterns.

6. The biometric authentication apparatus according to claim 4, wherein said control unit extracts, as the direction components of said patterns, angular components of said patterns.

7. The biometric authentication apparatus according to claim 5, wherein said control unit extracts a plurality of component segments of said patterns, vectorizes said component segments, and extracts said curvature direction components from said vectorized segments.

8. The biometric authentication apparatus according to claim 7, wherein said control unit generates a histogram of curvature directions from curvature components of each segment.

9. The biometric authentication apparatus according to claim 6, wherein said control unit calculates spatial frequency components for said biometrics information, and extracts Fourier angular characteristic quantities from said spatial frequency components as said angular components.

10. The biometric authentication apparatus according to claim 1, wherein said control unit extracts, as said first biometrics characteristic data, direction components and periodicity components of patterns of said biometrics information.

11. The biometric authentication apparatus according to claim 10, wherein said control unit extracts, as the periodicity components of said patterns, frequency components of said patterns.

12. The biometric authentication apparatus according to claim 11, wherein said control unit calculates spatial frequency components for said biometrics information, and extracts Fourier texture characteristic quantities from said spatial frequency components as said frequency components.

13. The biometric authentication apparatus according to claim 1, wherein said detection device comprises a unit for capture of images of blood vessels of said user, and

said first biometrics characteristic data is comparatively coarse characteristic data of said blood vessel images, and said second biometrics characteristic data is comparatively fine characteristic data of said blood vessel images.

14. A biometric authentication method of detecting biometrics characteristic data and performing individual authentication, comprising the steps of:

detecting biometrics information of a living body using a detection device;

extracting, from the biometrics information obtained, comparatively coarse first biometrics characteristic data and comparatively fine second characteristic data on the user;

calculating, using a processing device, the degrees of similarity between said first biometrics characteristic data for verification and the first biometrics characteristic data sets stored in a biometrics database file;

determining the order of verification with second biometrics characteristic data stored in said biometrics database file according to the degrees of similarity; and

verifying said second biometrics characteristic data for verification against said stored second biometrics characteristic data sets according to said verification order.

15. The biometric authentication method according to claim 14, wherein said determination step comprises a step of calculating scores indicating a difference between said first biometrics characteristic data for verification and first biometrics characteristic data sets stored in said biometrics database file, and of obtaining said degrees of similarity.

16. The biometric authentication method according to claim 15, wherein said determination step comprises:

a step of calculating the distance between said first biometrics characteristic data for verification and first biometrics characteristic data stored in said biometrics database file; and

a step of sorting the distances of said stored data and determining said verification order.

17. The biometric authentication method according to claim 14, wherein said extraction step comprises a step of extracting, as said first biometrics characteristic data, direction components of patterns of said biometrics information.

18. The biometric authentication method according to claim 17, wherein said extraction step comprises a step of extracting, as the direction components of said patterns, curvature components of said patterns.

19. The biometric authentication method according to claim 18, wherein said extraction step comprises:

a step of extracting a plurality of component segments of said patterns;

a step of vectorizing said component segments; and

a step of extracting said curvature direction components from said vectorized segments.

20. The biometric authentication method according to claim 19, wherein said extraction step comprises a step of generating a histogram of curvature directions from curvature components of each segment.

21. The biometric authentication method according to claim 17, wherein said extraction step comprises a step of extracting, as the direction components of said patterns, angular components of said patterns.

22. The biometric authentication method according to claim 21, wherein said extraction step comprises:

a step of calculating spatial frequency components for said biometrics information; and

a step of extracting Fourier angular characteristic quantities from said spatial frequency components as said angular components.

23. The biometric authentication method according to claim 14, wherein said extraction step comprises a step of extracting, as said first biometrics characteristic data, direction components and periodicity components of patterns of said biometrics information.

24. The biometric authentication method according to claim 23, wherein said extraction step comprises a step of extracting, as the periodicity components of said patterns, frequency components of said patterns.

25. The biometric authentication method according to claim 24, wherein said extraction step comprises:

a step of calculating spatial frequency components for said biometrics information; and

a step of extracting Fourier texture characteristic quantities from said spatial frequency components as said frequency components.

26. The biometric authentication method according to claim 14, wherein said extraction step comprises a step of extracting, from the blood vessel image of said detection device comprising a unit for capture of blood vessel images of said user, said first biometrics characteristic data which is comparatively coarse characteristic data of said blood vessel images, and said second biometrics characteristic data which is comparatively fine characteristic data of said blood vessel images.