Statistical Quality Assessment of Fingerprints

• US 20090196469A1
• Filed: 01/06/2009
• Published: 08/06/2009
• Est. Priority Date: 08/07/2003
• Status: Active Grant

• Current Assignee: L-1 Secure Credentialing, LLC (Advent International Corporation)
• Original Assignee: L-1 Secure Credentialing, LLC (Advent International Corporation)
• Inventors: Hwang, Kyungtae, Kim, Nam-Deuk
• Granted Patent: US 7,769,212 B2
• Time in Patent Office: Days
• US Class Current: 382/125
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• 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 40/1371 Matching features related to minutiae or pores
• CPC Class Codes: G06V 40/53 Measures to keep reference information secret, e.g. cancellable biometrics

Abstract

The present invention relates generally to human fingerprints. More specifically the present invention relates to assessing the quality of a fingerprint image. An assessment is made by analyzing characteristics of image sub-regions. For example, the characteristics may include statistics that are associated with a sub-region. If a sub-region is found to have unacceptable characteristics, it can be modified through a morphological operation to compensate for the unacceptable characteristics.

Claims

1-27. -27. (canceled)

28. A method to analyze a fingerprint image corresponding to a human fingerprint of a human subject, the fingerprint image including ridges and valleys, the method being performed by execution of computer readable program code by a processor of a computer system, the method comprising:

processing the fingerprint image to segment the image into at least a plurality of subsets;

for each of the subsets;

determining a measure associated with fingerprint ridges and fingerprint valleys in the each of the subsets, and

based on the measure, assigning the each of the subsets to at least one of a plurality of categories;

assessing an overall acceptability of the fingerprint image by analyzing at least one of the plurality of categories; and

causing capture of another fingerprint image from the human subject if the overall acceptability of the fingerprint image is at or below predetermined criteria, to process the other captured image.

29. The method of claim 28 wherein said analyzing comprises determining whether a number of subsets assigned to a first of the plurality of categories exceeds a predetermined value.

30. The method of claim 29, wherein the first category comprises at least one of acceptable, wet or dry.

31. The method of claim 29, further comprising accepting the fingerprint image when the number of subsets assigned to the first of the plurality of categories exceeds the predetermined value.

32. The method of claim 28, wherein processing the fingerprint image further comprises:

determining image distortion associated with the fingerprint image; and

adjusting the fingerprint image to compensate for the image distortion.

33. The method of claim 28, further comprising modifying image data defined by a subset when the subset is assigned to a predetermined category.

34. The method of claim 33, wherein modifying comprises:

adjusting ridge or valley dimensions.

35. A method of generating an identification document including a fingerprint image, the method being performed by execution of computer readable program code by a processor of a computer system, the method comprising:

receiving a fingerprint image that has been analyzed according to claim 28; and

causing one or more of;

printing the fingerprint image on the identification document and storing the fingerprint image in memory provided by the identification document.

36. A method to analyze a fingerprint image, the fingerprint image including ridges and valleys, the method being performed by execution of computer readable program code by a processor of a computer system, the method comprising:

processing the fingerprint image to segment the image into at least a plurality of subsets;

for each of the subsets;

determining a measure associated with fingerprint ridges and fingerprint valleys in the each of the subsets, and

based on the measure assigning the each of the subsets to at least one of a plurality of categories;

identifying from the plurality of subsets one or more subsets corresponding to a fingerprint core, and weighing the identified one or more subsets corresponding to the fingerprint core more significantly relative to subsets that do not correspond to the fingerprint core;

assessing an overall acceptability of the fingerprint image by analyzing at least one of the plurality of categories;

causing capture of another fingerprint image from the human subject if the overall acceptability of the fingerprint image is at or below predetermined criteria to process the other captured image.

37. A method to analyze a fingerprint image, the fingerprint image including ridges and valleys, the method being performed by execution of computer readable program code by a processor of a computer system, the method comprising:

segmenting the fingerprint image into at least a plurality of subsets; and

for each of the subsets;

determining a statistical measure associated with fingerprint ridges and fingerprint valleys in the each of the subsets, wherein the statistical measure comprises at least a standard deviation of ridge thickness and a standard deviation of valley thickness, and

based on the statistical measure, assigning the each of the subsets to at least one of a plurality of categories; and

causing capture of another fingerprint image to process other captured image based on a quality associated with the fingerprint image computed based on the assigning of the each of the subsets to the at least one of the plurality of categories.

38. The method of claim 37, wherein the statistical measure further comprises at least one of mean of ridge thickness or mean of valley thickness.

39. A method of determining whether to accept a first fingerprint image or to cause capture of a second fingerprint image, the first fingerprint and second fingerprint images comprising a representation of a same human fingerprint, the fingerprint including ridges and valleys, the method being performed by execution of computer readable program code by a processor of a computer system, the method comprising:

determining statistical values that are associated with at least some of the ridges and valleys;

comparing the determined statistical values to predetermined acceptance criteria;

performing a determination if a computed quality associated with the first fingerprint image is acceptable based on at least the comparing; and

based on at least the determination, causing the capture of the second fingerprint image to process the second captured image.

40. The method of claim 39, wherein the statistical values are determined based on ridge and valley thickness.

41. The method of claim 39, wherein statistical values associated with a fingerprint core are weighed more heavily than statistical values that are not associated with the fingerprint core.

42. The method of claim 39, wherein the statistical values comprise a measure related to a frequency domain analysis of at least some of the ridges and valleys.

43. A method of generating an identification document including a fingerprint image, the method being performed by execution of computer readable program code by a processor of a computer system, the method comprising:

receiving a fingerprint image that has been processed according to claim 39; and

performing one or more of;

printing the fingerprint image on the identification document and storing the fingerprint image in memory provided by the identification document.