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

• US 7,885,436 B2
• Filed: 07/05/2007
• Issued: 02/08/2011
• Est. Priority Date: 07/13/2006
• Status: Expired due to Fees

• Current Assignee: Apple Inc.
• Original Assignee: AuthenTec Incorporated (Apple Inc.)
• Inventors: Russo, Anthony P., Yang, Wayne
• Primary Examiner(s): Le; Vu
• Assistant Examiner(s): Allison; Andrae S
• Application Number:
  US11/825,412
• Publication Number:
  US 20080013808A1
• Time in Patent Office: 1,314 Days
• Field of Search: 382115-117, 382209-223, 382293-297, 283/68, 283/69, 283/73, 283/78, 356/71, 340/825.34, 340 51- 52, 250/556, 713/186
• US Class Current: 382/124
• 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 at least one set with identifying characteristics of the patterned object in a candidate set, wherein the matching includes a loose matching stage and a strict matching stage; and

adjusting a confidence value of each identifying characteristic in the at least one set based on results of the matching, wherein the confidence value is increased by a first value if a match occurs in the loose matching stage and by a second value larger than the first value if a match occurs in the strict matching stage.

2. The method of claim 1, further comprising organizing the at least one set based on the confidence values.

3. The method of claim 2, wherein organizing the at least one set comprises ordering the identifying characteristics in the at least one set based on the confidence values.

4. The method of claim 2, wherein organizing the at least one set comprises deleting from the at least one set 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 at least one set 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 at least one set each forms a template corresponding to retinal minutiae.

9. The method of claim 1, further comprising including the candidate set in the at least one set.

26. The method of claim 1, wherein adjusting the confidence value comprises increasing the confidence value by increasingly larger values if the match occurs outside a bounding box containing matching minutia, inside the bounding box in the looser matching stage, and inside the bounding box in the strict matching stage, respectively.

27. The method of claim 6, wherein the threshold is dynamically altered based on at least one of available memory on a host system, a security level of an application executing on the host system, and a number of finger images scanned on the host system.

10. 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 of a confidence value to an associated identifying characteristic; and

an assignor configured to assign a confidence value to each of the identifying characteristics generated from a loose match and strict match of the identifying characteristics in a template to identifying characteristics of the patterned object in at least one other template, wherein the confidence value of a characteristic is based on whether the loose match and the strict match are made between corresponding ones of the identifying characteristics in the patterned object and the template.

11. The apparatus of claim 10, wherein the assignor is further configured to organize each of the records according to the confidence values.

12. The apparatus of claim 11, wherein each of the records is organized by ordering the record based on an associated confidence value.

13. The apparatus of claim 11, wherein each of the records is organized by deleting any records having a confidence value below a threshold.

14. The apparatus of claim 10, further comprising a biometric sensor coupled to the template builder and configured to read a patterned object and extract data corresponding to identifying characteristics.

15. The apparatus of claim 14, wherein the biometric sensor comprises a finger image sensor and wherein the identifying characteristics are finger image minutiae.

16. The apparatus of claim 14, wherein the biometric sensor comprises a retinal scanner, and wherein the identifying characteristics include retinal minutiae.

17. The apparatus of claim 10, further comprising a template library configured to store at least one template containing records mapping confidence values to identifying characteristics.

18. The apparatus of claim 14, 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.

19. The apparatus of claim 18, wherein the predetermined manner comprises matching the identifying characteristics in an order determined by the confidence values.

20. The apparatus of claim 18, wherein the matcher comprises a first stage and a second stage.

21. The apparatus of claim 20, wherein the first stage performs the loose match and the second stage performs the strict match.

22. The apparatus of claim 21, 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.

23. The apparatus of claim 17, 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.

24. The apparatus of claim 23, wherein the host device comprises at least one of a cellular phone, a personal computer, a digital camera, a digital audio player, a digital audio/video player, and a health/monitor device.

25. 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 of a confidence value to an associated identifying characteristic; and

means for assigning a confidence value to each of the identifying characteristics generated from a loose match and strict match of the identifying characteristics in a template to identifying characteristics of the patterned object in at least one other template, wherein the confidence value of a characteristic is based on whether the loose match and the strict match are made between corresponding ones of the identifying characteristics in the patterned object and the template.