FINGERPRINT PREVIEW QUALITY AND SEGMENTATION

• US 20070253605A1
• Filed: 06/23/2006
• Published: 11/01/2007
• Est. Priority Date: 04/26/2006
• Status: Active Grant

• Current Assignee: Aware Incorporated (Crowley Holdings Preferred LLC)
• Original Assignee: Aware Incorporated (Crowley Holdings Preferred LLC)
• Inventors: Maurer, James M., Hills, L. Scott
• Granted Patent: US 7,936,907 B2
• Time in Patent Office: Days
• US Class Current: 382/124
• CPC Class Codes: G06T 2210/12 Bounding box
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/1353 Extracting features related to minutiae or pores
• CPC Class Codes: G06V 40/1359 Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop
• CPC Class Codes: G06V 40/1376 Matching features related to ridge properties or fingerprint texture

Abstract

A ridge flow based fingerprint image quality determination can be achieved independent of image resolution, can be processed in real-time and includes segmentation, such as fingertip segmentation, therefore providing image quality assessment for individual fingertips within a four finger flat, dual thumb, or whole hand image. A fingerprint quality module receives from one or more scan devices ridge-flow—containing imagery which can then be assessed for one or more of quality, handedness, historical information analysis and the assignment of bounding boxes.

Claims

1. An image quality determination method for an input image of any resolution comprising:

determining ridge flow for a received image;

establishing a ridge flow array; and

identifying one or more regions of the image.

2. The method of claim 1, further comprising determining and scoring a quality of the image.

3. The method of claim 1, further comprising assigning a bounding box to a portion of the image.

4. The method of claim 1, further comprising determining handedness of the image.

5. The method of claim 1, further comprising performing a historical analysis of a plurality of received images for one or more of quality, handedness and assignment of bounding boxes.

6. The method of claim 1, further comprising determining a grid spacing for the image based on image resolution.

7. The method of claim 6, further comprising modifying a processing window and Fourier coefficient frequency based on the image resolution.

8. The method of claim 1, further comprising selecting grid points for the image and, for each image grid point, determine Fourier coefficients for a sub-window around the grid point for a predetermined number of frequencies at different angles.

9. The method of claim 8, further comprising determining a correlation map based on a peak correlation between the predetermined number of frequencies at different angles and a local ridge flow.

10. The method of claim 1, further comprising determining a peak ridge flow angle from a correlation map.

11. The method of claim 1, further comprising averaging a correlation map.

12. The method of claim 1, wherein the method is performed in real-time.

58. A computer readable medium having stored thereon instructions for implementing the functionality of any one of claims 1-22.

13. An image quality determination method comprising:

identifying ridge flow detections in a received image and, for each detection;

determining an average contrast;

determining a peak Fourier coefficient; and

determining a peak angle agreement between a ridge flow detection and neighboring ridge flow detections.

14. The method of claim 13, further comprising scoring the received image.

15. The method of claim 13, wherein the received image comprises segmentation information.

16. The method of claim 13, wherein the received image includes ridge flow information.

17. The method of claim 13, further comprising determining and providing feedback based on the image quality determination method.

18. A segmentation method comprising:

clustering neighboring ridge flow detections into groups;

determining an orientation for one or more larger clusters;

determining a dominant orientation angle; and

grouping the one or more large clusters that can be connected via a suspected segment orientation angle into one or more segment cluster groups.

19. The method of claim 18, further comprising removing non-segment cluster groups.

20. The method of claim 18, further comprising identifying an end cluster of each segment cluster group as a digit tip.

21. The method of claim 20, further comprising trimming the digit tip.

22. The method of claim 20, further comprising determining a bounding box for each digit tip.

23. An image quality module for an input image of any resolution comprising:

a ridge flow module adapted to determine ridge flow for a received image, establish a ridge flow array and identify one or more regions of the image.

24. The system of claim 23, further comprising a quality determination module adapted to determine and score a quality of the image.

25. The system of claim 23, wherein the ridge flow module is further adapted to assign a bounding box to a portion of the image.

26. The system of claim 23, further comprising a handedness module adapted to determine handedness of the image.

27. The system of claim 23, further comprising an auto-capture module adapted to perform a historical analysis of a plurality of received images for one or more of quality, handedness and assignment of bounding boxes.

28. The system of claim 23, further adapted to determine a grid spacing for the image based on image resolution.

29. The system of claim 28, further adapted to modify a processing window and Fourier coefficient frequency based on the image resolution.

30. The system of claim 23, further adapted to select grid points for the image and, for each image grid point, determine Fourier coefficients for a sub-window around the grid point for a predetermined number of frequencies at different angles.

31. The system of claim 30, further adapted to determine a correlation map based on a peak correlation between the predetermined number of frequencies at different angles and a local ridge flow.

32. The system of claim 23, further adapted to determine a peak ridge flow angle from a correlation map.

33. The system of claim 23, further adapted to average a correlation map.

34. The system of claim 23, wherein the system operates in real-time.

35. The system of claim 23, further comprising a sampling module adapted to resample the input image.

36. An image quality determination system for an input image of any resolution comprising:

means for determining ridge flow for a received image;

means for establishing a ridge flow array; and

means for identifying one or more regions of the image.

37. The system of claim 36, further comprising means for determining and scoring a quality of the image.

38. The system of claim 36, further comprising means for assigning a bounding box to a portion of the image.

39. The system of claim 36, further comprising means for determining handedness of the image.

40. The system of claim 36, further comprising means for performing a historical analysis of a plurality of received images for one or more of quality, handedness and assignment of bounding boxes.

41. The system of claim 36, further comprising means for determining a grid spacing for the image based on image resolution.

42. The system of claim 41, further comprising means for modifying a processing window and Fourier coefficient frequency based on the image resolution.

43. The system of claim 36, further comprising means for selecting grid points for the image and, for each image grid point, determine Fourier coefficients for a sub-window around the grid point for a predetermined number of frequencies at different angles.

44. The system of claim 43, further comprising means for determining a correlation map based on a peak correlation between the predetermined number of frequencies at different angles and a local ridge flow.

45. The system of claim 36, further comprising means for determining a peak ridge flow angle from a correlation map.

46. The system of claim 36, further comprising means for averaging a correlation map.

47. The system of claim 36, wherein the system operates in real-time.

48. An image quality determination system comprising:

means for identifying ridge flow detections in a received image and, for each detection;

means for determining an average contrast;

means for determining a peak Fourier coefficient; and

means for determining a peak angle agreement between a ridge flow detection and neighboring ridge flow detections.

49. The system of claim 48, further comprising means for scoring the received image.

50. The system of claim 48, wherein the received image comprises segmentation information.

51. The system of claim 48, wherein the received image includes ridge flow information.

52. The system of claim 48, further comprising means for determining and means for providing feedback based on the image quality determination method.

53. A segmentation system comprising:

means for clustering neighboring ridge flow detections into groups;

means for determining an orientation for one or more larger clusters;

means for determining a dominant orientation angle; and

means for grouping the one or more large clusters that can be connected via a suspected segment orientation angle into one or more segment cluster groups.

54. The system of claim 53, further comprising means for removing non-segment cluster groups.

55. The system of claim 53, further comprising means for identifying an end cluster of each segment cluster group as a digit tip.

56. The system of claim 55, further comprising means for trimming the digit tip.

57. The system of claim 55, further comprising means for determining a bounding box for each digit tip.