System for and method of assigning confidence values to fingerprint minutiae points

• US 20080013808A1
• Filed: 07/05/2007
• Published: 01/17/2008
• Est. Priority Date: 07/13/2006
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: AuthenTec Incorporated (Apple Inc.)
• Inventors: Russo, Anthony P., Yang, Wayne
• Granted Patent: US 7,885,436 B2
• Time in Patent Office: Days
• US Class Current: 382/125
• CPC Class Codes: G06V 40/1335 Combining adjacent partial images (e.g. slices) to create a composite input or reference pattern; Tracking a sweeping finger movement
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction

Abstract

A method in accordance with the present invention is used to organize minutiae and other identifying characteristics of a patterned object to verify a user. In one embodiment, the method includes matching minutiae points of the patterned object in one more sets with minutiae points of the patterned object in a candidate set. The method also includes adjusting a confidence value of each minutia point in the one or more sets based on results of the matching. The method also includes organizing the one or more sets based on the confidence values, such as by ordering the minutiae in the one or more sets based on the confidence values, or by deleting from the one or more sets any identifying characteristics with a confidence value below a threshold.

Claims

1. A method of organizing identifying characteristics of a patterned object used to verify the patterned object, the method comprising:

matching identifying characteristics of the patterned object in one more sets with

identifying characteristics of the patterned object in a candidate set; and

adjusting a confidence value of each identifying characteristic in the one or more sets based on results of the matching.

2. The method of claim 1, further comprising organizing the one or more sets based on the confidence values.

3. The method of claim 2, wherein organizing the one or more sets comprises ordering the identifying characteristics in the one or more sets based on the confidence values.

4. The method of claim 2, wherein organizing the one or more sets comprises deleting from the one or more sets any identifying characteristics with a confidence value below a threshold.

5. The method of claim 4, wherein the threshold is predetermined.

6. The method of claim 4, wherein the threshold is dynamic.

7. The method of claim 1, wherein the identifying characteristics are fingerprint minutiae and the candidate set and the one or more sets each forms a template of fingerprint minutiae.

8. The method of claim 1, wherein the identifying characteristics correspond to retinal minutiae and the candidate set and the one or more sets each forms a template corresponding to retinal minutiae.

9. The method of claim 1, further comprising including the candidate set in the one or more sets.

10. A method of verifying a patterned object comprising:

generating a template of candidate identifying characteristics from an image of the patterned object;

matching the candidate identifying characteristics to stored identifying characteristics of the patterned object in one or more other templates, wherein the matches are performed based on confidence values associated with each of the stored identifying characteristics; and

verifying the patterned object based on a result of the matches.

11. The method of claim 10, wherein the identifying characteristics are finger minutiae, the method further comprising reading the image of the patterned object using a finger sensor.

12. The method of claim 10, wherein the identifying characteristics include retinal minutiae, the method further comprising reading the image of the patterned object using a retinal scanner.

13. The method of claim 10, wherein the one or more other templates are generated from one or more images of the patterned object.

14. The method of claim 10, wherein the candidate identifying characteristics are matched to the stored identifying characteristics in a manner based on the confidence values.

15. The method of claim 14, wherein the manner is in an order from highest to lowest confidence values.

16. The method of claim 10, further comprising aligning a template of the candidate identifying characteristics with the one or more other templates.

17. A method of generating templates corresponding to image data comprising:

performing one or more pairwise matches of two or more templates each containing data corresponding to identifying characteristics; and

assigning confidence values to each identifying characteristics in each of the two or more templates based on matches between the identifying characteristics.

18. The method of claim 17, wherein the identifying characteristics are fingerprint minutiae points.

19. The method of claim 17, wherein the identifying characteristics are retinal minutiae.

20. The method of claim 17, wherein assigning a confidence value to an identifying characteristic comprises updating the confidence value associated with the identifying characteristic by an incremental value.

21. The method of claim 20, wherein the incremental value depends on a type of match between identifying characteristics matched during the pairwise matches.

22. The method of claim 21, wherein the type of match is an unsuccessful match, a successful loose match, a successful strict match, a successful match within a bounding box, or a combination of these.

23. The method of claim 17, wherein each of the two or more templates comprises records each mapping a confidence value to an identifying characteristic, the method further comprising organizing each of the records based on its corresponding confidence value.

24. The method of claim 23, wherein organizing each of the records comprises ordering each record according to its confidence value.

25. The method of claim 23, wherein organizing each of the records comprises deleting any record having a corresponding confidence value below a threshold.

26. The method of claim 17, wherein each pairwise match comprises a first stage and a second stage.

27. The method of claim 26, wherein the first stage includes a loose match and the second stage includes a match stricter than the loose match.

28. An apparatus for assigning confidence values to identifying characteristics of a patterned object comprising:

a template builder configured to build templates of identifying characteristics, wherein each template contains a record mapping a confidence value to an associated identifying characteristic; and

an assignor configured to assign confidence values to each of the identifying characteristics generated from a match of the identifying characteristics in a template to identifying characteristics of the patterned object in one or more other templates.

29. The apparatus of claim 28, wherein the assignor is further configured to organize each of the records according to the confidence values.

30. The apparatus of claim 29, wherein each of the records is organized by ordering the record based on an associated confidence value.

31. The apparatus of claim 29, wherein each of the records is organized by deleting any records having a confidence value below a threshold.

32. The apparatus of claim 28, further comprising a biometric sensor coupled to the template builder and configured to read a patterned object and extract data corresponding to identifying characteristics.

33. The apparatus of claim 32, wherein the biometric sensor is a finger image sensor and the identifying characteristics are finger image minutiae.

34. The apparatus of claim 32, wherein the biometric sensor is a retinal scanner and the identifying characteristics include retinal minutiae.

35. The apparatus of claim 28, further comprising a template library configured to store one or more templates containing records mapping confidence values to identifying characteristics.

36. The apparatus of claim 32, further comprising a matcher for matching in a predetermined manner identifying characteristics of the patterned object read by the biometric sensor with identifying characteristics in the template library to thereby verify the patterned object.

37. The apparatus of claim 36, wherein the predetermined manner comprises matching the identifying characteristics in an order determined by the confidence values.

38. The apparatus of claim 36, wherein the matcher comprises a first stage and a second stage.

39. The method of claim 38, wherein the first stage performs a loose match and the second stage performs a match stricter than the loose match.

40. The apparatus of claim 39, wherein the matcher is configured to increment a confidence value by a first value if the first stage determines a successful match and by a second value, larger than the first value, if the second stage determines a successful match.

41. The apparatus of claim 35, further comprising a host device configured to perform a function based on a successful match between a first template of identifying characteristics and a template in the template library.

42. The apparatus of claim 41, wherein the host device is a cellular phone, a personal computer, a digital camera, a digital audio player, a digital audio/video player, or a health/monitor device.

43. An apparatus for assigning confidence values to identifying characteristics of a patterned object comprising:

means for building templates of identifying characteristics, wherein each template contains a record mapping a confidence value to an associated identifying characteristic; and

means for assigning confidence values to each of the identifying characteristics generated from a match of the identifying characteristics in a template to identifying characteristics of the patterned object in one or more other templates.

44. An apparatus for matching minutiae of a patterned object comprising:

a finger sensor for reading an image of the patterned object;

a template builder configured to build templates of minutiae from the image;

a storage containing a library of one or more templates, wherein each of the one or more templates maps confidence values to minutiae from one image of the patterned object, and further wherein the minutiae in the one or more templates have an organization based on the confidence values; and

a matcher configured to match any pair of templates based on the organization, to thereby verify the patterned object.

45. The apparatus of claim 44, further comprising an assignor configured to assign confidence values to minutiae based on a result of matches between templates and to organize templates based on the confidence values.

46. A computer-readable medium having stored thereon a data structure comprising a plurality of records, wherein each record comprises a first field containing data representing a minutia point and a second field containing data representing a confidence value for the minutia point.