Dynamic handwriting verification and handwriting-based user authentication

• US 9,747,491 B2
• Filed: 11/13/2015
• Issued: 08/29/2017
• Est. Priority Date: 11/14/2013
• Status: Active Grant

• Current Assignee: Wacom Co Limited (Wacom)
• Original Assignee: Wacom Co Limited (Wacom)
• Inventors: Mettyear, Nicholas, Nakayama, Yoshitaka, Ryu, Jin Kon
• Primary Examiner(s): Akhavannik, Hadi
• Application Number:
  US14/940,925
• Publication Number:
  US 20160070951A1
• Time in Patent Office: 655 Days
• Field of Search: None
• CPC Class Codes: G06V 10/754 involving a deformation of the sample pattern or of the reference pattern; Elastic matching
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32
• CPC Class Codes: G06V 30/2268 using stroke segmentation
• CPC Class Codes: G06V 40/30 Writer recognition; Reading and verifying signatures
• CPC Class Codes: G06V 40/33 based only on signature image, e.g. static signature recognition
• CPC Class Codes: G06V 40/394 Matching; Classification

Abstract

Handwriting verification methods and related computer systems, and handwriting-based user authentication methods and related computer systems are disclosed. A handwriting verification method comprises obtaining a handwriting test sample containing a plurality of available parameters, extracting geometric parameters, deriving geometric features comprising an x-position value and a y-position value for each of a plurality of feature points in the test sample, performing feature matching between geometric features of the test sample and a reference sample, determining a handwriting verification result based at least in part on the feature matching, and outputting the handwriting verification result. The geometric features may further comprise values derived from the geometric parameters, such as direction and curvature values. The handwriting verification result can be further based on a count of unlinked feature points. Handwriting-based user authentication methods can employ such handwriting verification methods, or other handwriting verification methods.

Claims

1. A handwriting verification method executed in a computer system, the method comprising:

obtaining a test sample and a reference sample each containing a plurality of feature points, wherein each of the feature points includes;

(i) geometric features including an x-coordinate value and a y-coordinate value, and

(ii) a non-geometric feature;

finding mappings between feature points of the test sample and feature points of the reference sample based on the geometric features of the test sample and reference sample, wherein the finding mappings comprises finding mappings between one or more of evenly distributed feature points in the test sample and one or more evenly distributed feature points in the reference sample; and

after the finding mappings, comparing the non-geometric features of each of the mapped feature points of the test sample and the reference sample.

2. The method of claim 1, wherein the non-geometric feature comprises pen pressure, elapsed time, speed, or acceleration.

3. The method of claim 1, wherein the comparing is performed in the case that the mapping is determined to be a sufficient match.

4. The method of claim 1, wherein the finding mappings is done by an algorithm utilizing a pseudo-random value.

5. The method of claim 1, wherein the finding mappings is based on a count of unlinked feature points of the test sample.

6. The method of claim 1, wherein the finding mappings is based on a count of consecutive unlinked feature points in the test sample.

7. The method of claim 1, wherein the finding mappings comprises:

determining, based on a pseudo-random value, whether to (a) remove a mapping from a selected feature point in the reference sample, or (b) define a new mapping between the selected feature point in the reference sample and a selected feature point in the test sample.

8. The method of claim 1, the geometric features further include direction (D) and curvature (C) derived from the x-coordinate values and y-coordinate values.

9. A handwriting verification method executed in a computer system, the method comprising:

performing feature matching between geometric features of a handwriting test sample and geometric features of a reference sample, wherein the feature matching comprises defining one or more links between one or more feature points in the test sample and one or more feature points in the reference sample;

obtaining a count of consecutive unlinked feature points in the test sample; and

outputting a handwriting verification result based at least in part on the feature matching and the count of consecutive unlinked feature points in the test sample.

10. The method of claim 9, further including comparing non-geometric features of each of the linked feature points of the test sample and the reference sample.

11. The method of claim 9, wherein the feature matching includes:

initializing a pseudo-random value generator to generate a sequence of pseudo-random values, wherein the feature matching is based on a pseudo random value generated by the pseudo random value generator; and

if matching is not sufficient, performing another feature matching by the using another pseudo random value generated by the same uniform random value generator.

12. A handwriting verification method executed in a computer system, the method comprising:

obtaining a test sample and a reference sample each containing a plurality of feature points, wherein each of the feature points includes;

(i) geometric features including an x-coordinate value and a y-coordinate value, and

(ii) a non-geometric feature, wherein the non-geometric feature comprises pen pressure, elapsed time, speed, or acceleration;

finding mappings between feature points of the test sample and feature points of the reference sample based on the geometric features of the test sample and reference sample, wherein the finding mappings is done by an algorithm utilizing a pseudo-random value; and

after the finding mappings, comparing the non-geometric features of each of the mapped feature points of the test sample and the reference sample.

13. The method of claim 12, wherein the comparing is performed in the case that the mapping is determined to be a sufficient match.

14. The method of claim 12, wherein the finding mappings is based on a count of unlinked feature points of the test sample.

15. The method of claim 12, wherein the finding mappings is based on a count of consecutive unlinked feature points in the test sample.

16. The method of claim 12, wherein the finding mappings comprises:

determining, based on the pseudo-random value, whether to (a) remove a mapping from a selected feature point in the reference sample, or (b) define a new mapping between the selected feature point in the reference sample and a selected feature point in the test sample.

17. The method of claim 12, wherein the finding mappings comprises finding mappings between one or more of evenly distributed feature points in the test sample and one or more evenly distributed feature points in the reference sample.

18. The method of claim 12, wherein the geometric features further include direction (D) and curvature (C) derived from the x-coordinate values and y-coordinate values.

19. A handwriting verification method executed in a computer system, the method comprising:

obtaining a test sample and a reference sample each containing a plurality of feature points, wherein each of the feature points includes;

(i) geometric features including an x-coordinate value and a y-coordinate value, and

(ii) a non-geometric feature;

finding mappings between feature points of the test sample and feature points of the reference sample based on the geometric features of the test sample and reference sample, wherein the finding mappings is based on a count of unlinked feature points of the test sample; and

after the finding mappings, comparing the non-geometric features of each of the mapped feature points of the test sample and the reference sample.

20. The method of claim 19, wherein the non-geometric feature comprises pen pressure, elapsed time, speed, or acceleration.

21. The method of claim 19, wherein the comparing is performed in the case that the mapping is determined to be a sufficient match.

22. The method of claim 19, wherein the finding mappings is done by an algorithm utilizing a pseudo-random value.

23. The method of claim 19, wherein the finding mappings is based on a count of consecutive unlinked feature points in the test sample.

24. The method of claim 19, wherein the finding mappings comprises:

determining, based on a pseudo-random value, whether to (a) remove a mapping from a selected feature point in the reference sample, or (b) define a new mapping between the selected feature point in the reference sample and a selected feature point in the test sample.

25. The method of claim 19, wherein the finding mappings comprises finding mappings between one or more of evenly distributed feature points in the test sample and one or more evenly distributed feature points in the reference sample.

26. The method of claim 19, wherein the geometric features further include direction (D) and curvature (C) derived from the x-coordinate values and y-coordinate values.

27. A handwriting verification method executed in a computer system, the method comprising:

obtaining a test sample and a reference sample each containing a plurality of feature points, wherein each of the feature points includes;

(i) geometric features including an x-coordinate value and a y-coordinate value, and

(ii) a non-geometric feature;

finding mappings between feature points of the test sample and feature points of the reference sample based on the geometric features of the test sample and reference sample, wherein the finding mappings comprises determining, based on a pseudo-random value, whether to (a) remove a mapping from a selected feature point in the reference sample, or (b) define a new mapping between the selected feature point in the reference sample and a selected feature point in the test sample; and

after the finding mappings, comparing the non-geometric features of each of the mapped feature points of the test sample and the reference sample.

28. The method of claim 27, wherein the non-geometric feature comprises pen pressure, elapsed time, speed, or acceleration.

29. The method of claim 27, wherein the comparing is performed in the case that the mapping is determined to be a sufficient match.

30. The method of claim 27, wherein the finding mappings is done by an algorithm utilizing a pseudo-random value.

31. The method of claim 27, wherein the finding mappings is based on a count of unlinked feature points of the test sample.

32. The method of claim 27, wherein the finding mappings is based on a count of consecutive unlinked feature points in the test sample.

33. The method of claim 27, wherein the finding mappings comprises finding mappings between one or more of evenly distributed feature points in the test sample and one or more evenly distributed feature points in the reference sample.

34. The method of claim 27, wherein the geometric features further include direction (D) and curvature (C) derived from the x-coordinate values and y-coordinate values.