Systems and methods for biometric identification using handwriting recognition
A biometric handwriting identification system converts characters and a writing sample into mathematical graphs. The graphs comprise enough information to capture the features of handwriting that are unique to each individual. Optical character recognition (OCR) techniques can then be used to identify these features in the handwriting sample so that drafts from two different samples can be aligned to compare to determine if the features in the writing sample correlate with each other.
1. A method for biometric handwriting recognition, comprising:
converting handwriting specimens into electronic images;
converting the electronic images into mathematical graphs that include a vertex and an edge;
detecting similarities between a plurality of graphs;
aligning vertices and edges of similar graphs; and
comparing similar graphs.
2. The method of claim 1 , wherein converting the handwriting specimens into electronic images comprises, converting the handwriting samples into bi-tonal electronic images.
3. The method of claim 1 , wherein converting an electronic image into mathematical graphs comprises converting the electronic image into an image skeleton.
4. The method of claim 3 , wherein converting an electronic image into a mathematical graph further comprises transforming the image skeleton into one or more edges and one or more vertices.
5. The method of claim 3 , wherein converting an electronic image into a mathematical graph further comprises locating a first primary vertex.
6. The method of claim 5 , wherein converting an electronic image into a mathematical graph further comprises following a pixel path from the first primary to the second primary vertex.
7. The method of claim 6 , comprising detecting what type of vertex each located vertex is, wherein the type of vertex is detected by checking a plurality of pixels around a pixel of interest.
8. The method of claim 5 , further comprising locating a secondary vertex.
9. The method of claim 1 , wherein converting the electronic images into mathematical graphs includes minor feature editing.
10. The method of claim 9 wherein the minor feature editing comprises closing a small gap.
11. The method of claim 9 wherein the minor feature editing comprises connecting undershoots.
12. The method of claim 9 wherein the minor feature editing comprises combining a plurality of close vertices.
13. The method of claim 1 , wherein the comparing step includes the additional steps of:
associating contour information with each graph; and
comparing the contour information associated with similar graphs.
14. The method of claim 1 , wherein the detecting step comprises the use of optical character recognition.
15. The method of claim 1 , further comprising transforming a mathematical graph into at least one feature caddie.
16. The method of claim 15 wherein the feature caddie comprises a topology.
17. The method of claim 16 wherein the topology comprises a topology for an individual character.
18. The method of claim 16 wherein the topology comprises a topology for a group of characters.
19. The method of claim 15 wherein the feature caddie comprises a minimum morphing distance.
20. The method of claim 15 wherein the feature caddie comprises a degree 2 graph vertices.
21. The method of claim 15 wherein the feature caddie comprises a vertex-to-vertex direction.
22. The method of claim 15 wherein the feature caddie comprises a vertex-to-vertex distance.
23. The method of claim 15 wherein the feature caddie comprises an edge to vertex direction.
24. The method of claim 15 wherein the feature caddie comprises an edge to vertex distance.
25. The method of claim 15 wherein the feature caddie comprises an edge to edge direction.
26. The method of claim 15 wherein the feature caddie comprises an edge to edge distance.
27. The method of claim 15 wherein the feature caddie comprises an edge to edge direction.
28. The method of claim 15 wherein the feature caddie comprises a contour of a letter.
29. The method of claim 15 wherein the feature caddie comprises a character height.
30. The method of claim 29 wherein the height is an absolute height.
31. The method of claim 29 wherein the height is a middle zone height.
32. The method of claim 29 wherein the height is an upper zone height.
33. The method of claim 29 wherein the height is a lower zone height.
34. The method of claim 15 wherein the feature caddie comprises a character proportion.
35. The method of claim 34 wherein the character proportion comprises an upper zone proportion.
36. The method of claim 34 wherein the character proportion comprises a lower zone proportion.
37. The method of claim 15 wherein the feature caddie comprises a breadth of a letter.
38. The method of claim 15 wherein the feature caddie comprises a distance between a first letter and a second letter.
39. The method of claim 15 wherein the feature caddie comprises a character slant.
40. The method of claim 15 wherein the feature caddie comprises a fluctuation of slant of a plurality of characters.
41. The method of claim 15 wherein the feature caddie comprises loop classification.
42. The method of claim 15 wherein the feature caddie comprises a curve concavity.
43. The method of claim 15 wherein the feature caddie is an ornamentation.
44. The method of claim 43 wherein the ornamentation comprises a simplification.
45. The method of claim 43 wherein the ornamentation comprises a distortion.
46. The method of claim 43 wherein the ornamentation comprises an ornamentation.
47. The method of claim 15 wherein the feature caddie comprises a contour point profile.
48. The method of claim 15 wherein the feature caddie comprises a tangent slope stroke component.
49. The method of claim 48 wherein the tangent slope stroke component comprises a horizontal stroke component.
50. The method of claim 48 wherein the tangent slope stroke component comprises a vertical stroke component.
51. The method of claim 48 wherein the tangent slope stroke component comprises a positive stroke component.
52. The method of claim 48 wherein the tangent slope stroke component comprises a negative stroke component.
53. The method of claim 15 wherein the feature caddie comprises a character tendency.
54. The method of claim 15 wherein the feature caddie comprises a character connection class.
55. The method of claim 15 wherein the feature caddie comprises a character connection consistency.
56. The method of claim 15 wherein the feature caddie comprises a baseline direction.
57. The method of claim 15 wherein the feature caddie comprises a baseline fluctuation.
58. The method of claim 15 wherein the feature caddie comprises an expected but missing punctuation.
59. The method of claim 15 wherein the feature caddie comprises a pressure pattern.
60. The method of claim 15 wherein the feature caddie comprises a pressure pattern.
61. The method of claim 15 wherein the feature caddie comprises a stroke sequence.
62. The method of claim 15 wherein the feature caddie comprises a border stability measurement.
63. The method of claim 15 wherein the feature caddie comprises a border symmetry.
64. The method of claim 15 wherein the feature caddie comprises degree of pressure.
65. The method of claim 15 wherein the feature caddie comprises a use of an abbreviation.
66. The method of claim 15 wherein the feature caddie comprises a use of a symbol.
67. The method of claim 15 wherein the feature caddie comprises retracings.
68. The method of claim 15 wherein the feature caddie comprises terminal conditions.
69. The method of claim 15 wherein the feature caddie comprises stroke type.
70. The method of claim 15 wherein the feature caddie comprises stroke artifacts.
71. The method of claim 15 wherein the feature caddie comprises loop attributes.
72. The method of claim 15 wherein the feature caddie comprises distance between words.
73. The method of claim 15 wherein the feature caddie comprises word proportions.
74. The method of claim 15 wherein the feature caddie comprises word foundation.
75. The method of claim 74 wherein the word foundation comprises a cusp.
76. The method of claim 74 wherein the word foundation comprises a garland.
77. The method of claim 74 wherein the word foundation comprises arcade.
78. The method of claim 74 wherein the word foundation comprises proportion.
79. The method of claim 15 wherein the feature caddie comprises rhythm.
80. The method of claim 15 wherein the feature caddie comprises consistency.
81. The method of claim 15 wherein the feature caddie comprises fine edge contours.
82. The method of claim 15 wherein the feature caddie comprises embedded isomorphisms.
83. The method of claim 1 , wherein the vertex is a cross intersection of two lines.
84. The method of claim 1 , wherein the vertex is a T-intersection of two lines.
85. The method of claim 1 , wherein the vertex is a termination of a line.
86. The method of claim 1 , wherein the edge is a line connecting a plurality of vertices.