Biometric authentication

• US 20080069408A1
• Filed: 09/18/2006
• Published: 03/20/2008
• Est. Priority Date: 09/18/2006
• Status: Active Grant

• Current Assignee: Gula Consulting Limited Liability Company (Intellectual Ventures LLC)
• Original Assignee: Miguel Angel Cervantes
• Inventors: Cervantes, Miguel Angel
• Granted Patent: US 7,676,068 B2
• Time in Patent Office: Days
• US Class Current: 382/115
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

A biometric authentication system, including a database of digital images of biometrics of known people, a camera for capturing a digital image of a biometric of an unknown person, a two-dimensional gradient filter coupled with said database and said camera for deriving a spatial gradient of a digital image, and a match processor coupled with the two-dimensional gradient filter for processing two spatial gradients and determining the extent to which the unknown biometric corresponds with a known biometric. A method and a computer-readable storage medium are also described and claimed.

Claims

1. A biometric authentication system, comprising:

a database of digital images of biometrics of known people;

a camera for capturing a digital image of a biometric of an unknown person;

a two-dimensional gradient filter coupled with said database and said camera for deriving a spatial gradient of a digital image; and

a match processor coupled with said two-dimensional gradient filter for processing two spatial gradients and determining the extent to which the unknown biometric corresponds with a known biometric.

2. The biometric authentication system of claim 1 wherein said two-dimensional gradient filter derives a spatial gradient by averaging horizontal difference quotients over a first sliding window, and by averaging vertical difference quotients over a second sliding window.

3. The biometric authentication system of claim 2 wherein the horizontal difference quotients have a fixed width, and the length of the first sliding window equals the width of the horizontal difference quotients, and wherein the vertical difference quotients have a fixed width, and the length of the second sliding window equals the width of the vertical difference quotients.

4. The biometric authentication system of claim 1 wherein said match processor calculates a probability that the known biometric does not correspond with the unknown biometric, based on metrics calculated by said match processor.

5. The biometric authentication system of claim 4 wherein said match processor calculates a plurality of pairs of blocks of pixels, each pair comprising a block from each of the two spatial gradients, and the pair of blocks being similar to each other, and wherein the metrics relate to the relative placements of the pairs of blocks.

6. The biometric authentication system of claim 1 wherein the biometric is at least one skin texture.

7. The biometric authentication system of claim 1 wherein the biometric is a fingerprint.

8. The biometric authentication system of claim 1 wherein the biometric is a palm print.

9. The biometric authentication system of claim 1 wherein the biometric is a retinal scan.

10. The biometric authentication system of claim 1 wherein the biometric is an iris scan.

11. A method for biometric authentication, comprising:

capturing a digital image, denoted by image F, of a biometric of an unknown person;

retrieving a digital image of a biometric of a known person, denoted by image G, from a database of such images;

deriving a two-dimensional spatial gradient, denoted by grad F, of biometric image F, and a two-dimensional spatial gradient, denoted by grad G, of biometric image G;

for each pixel block B_k from a plurality of pixel blocks B₁, B₂, . . . , B_n, searching for a pixel block C_k such that values of grad F over block B_k substantially correspond with the values of grad G over block C_k;

determining how many pairs of distinct pixel blocks B_k and B_m satisfy a criterion that the relative displacement between B_k and B_m nearly equals the relative displacement between pixel blocks C_k and C_m; and

concluding whether or not the unknown biometric matches the known biometric, based on said determining.

12. The method of claim 11 wherein said deriving derives a spatial gradient by averaging horizontal difference quotients over a first sliding window, and by averaging vertical difference quotients over a second sliding window.

13. The method of claim 12 wherein the horizontal difference quotients have a fixed width, and the length of the first sliding window equals the width of the horizontal difference quotients, and wherein the vertical difference quotients have a fixed width, and the length of the second sliding window equals the width of the vertical difference quotients.

14. The method of claim 11 wherein said concluding calculates a probability that the unknown biometric does not match the known biometric, based on the results of said determining.

15. The method of claim 11 wherein the biometric is at least one skin texture.

16. The method of claim 11 wherein the biometric is a fingerprint.

17. The method of claim 11 wherein the biometric is a palm print.

18. The method of claim 11 wherein the biometric is a retinal scan.

19. The method of claim 11 wherein the biometric is an iris scan.

20. A computer-readable storage medium storing program code for causing a computing device:

to capture a digital image, denoted by image F, of a biometric of an unknown person;

to retrieve a digital image of a biometric of a known person, denoted by image G, from a database of such images;

to derive a two-dimensional spatial gradient, denoted by grad F, of palm image F, and a two-dimensional spatial gradient, denoted by grad G, of palm image G;

for each pixel block B_k from a plurality of pixel blocks B₁, B₂, . . . , B_n, to search for a pixel block C_k such that values of grad F over block B_k substantially correspond with the values of grad G over block C_k;

to determine how many pairs of distinct pixel blocks B_k and B_m satisfy a criterion that the relative displacement between B_k and B_m nearly equals the relative displacement between pixel blocks C_k and C_m; and

to conclude whether or not the unknown biometric matches the known biometric, based on the number of pairs of distinct pixel blocks that satisfy the criterion.

21. A biometric authentication system, comprising:

a database of digital images of biometrics of known people;

a camera for capturing a digital image of a biometric of an unknown person;

a match processor for identifying a second planar graph of nodes within an image of a known biometric that corresponds to a first planar graph of nodes within the image of the known biometric; and

a match detector coupled with said match processor for concluding whether or not the unknown biometric matches the known biometric, based on the extent to which edges in the second planar graph align with edges in the first planar graph.

22. The biometric authentication system of claim 21 wherein said match detector calculates a probability that the unknown biometric does not match the known biometric, based on the extent to which edges in the second planar graph align with edges in the first planar graph.

23. The biometric authentication system of claim 21 wherein the biometric is at least one skin texture.

24. The biometric authentication system of claim 21 wherein the biometric is a fingerprint.

25. The biometric authentication system of claim 21 wherein the biometric is a palm print.

26. The biometric authentication system of claim 21 wherein the biometric is a retinal scan.

27. The biometric authentication system of claim 21 wherein the biometric is an iris scan.

28. A method for biometric authentication, comprising:

capturing a digital image of a biometric of an unknown person;

identifying a second planar graph of nodes within an image of a biometric of a known person that corresponds to a first planar graph of nodes within the image of the unknown biometric; and

concluding whether or not the unknown biometric matches the known biometric, based on the extent to which edges in the second planar graph align with edges in the first planar graph.

29. The method of claim 28 wherein said concluding calculates a probability that the captured image does not match the known image, based on the extent to which edges in the second planar graph align with edges in the first planar graph.

30. The method of claim 28 wherein the biometric is at least one skin texture.

31. The method of claim 28 wherein the biometric is a fingerprint.

32. The method of claim 28 wherein the biometric is a palm print.

33. The method of claim 28 wherein the biometric is a retinal scan.

34. The method of claim 28 wherein the biometric is an iris scan.

35. A computer-readable storage medium storing program code for causing a computing device:

to capture a digital image of a biometric of an unknown person;

to identify a second planar graph of nodes within an image of a biometric of a known person that corresponds to a first planar graph of nodes within the image of the unknown biometric; and

to conclude whether or not the unknown biometric matches the known biometric, based on the extent to which edges in the second planar graph align with edges in the first planar graph.