Fingerprint check to reduce check fraud

• US 9,305,413 B1
• Filed: 11/11/2013
• Issued: 04/05/2016
• Est. Priority Date: 12/01/2008
• Status: Active Grant

• Current Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Original Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Inventors: McCormick, Michael, Jaffe, Frank
• Primary Examiner(s): Strege, John
• Application Number:
  US14/076,369
• Time in Patent Office: 876 Days
• Field of Search: 382/124
• US Class Current: 1/1
• CPC Class Codes: G06Q 20/045 using payment protocols involving tickets
• CPC Class Codes: G06Q 20/40145 Biometric identity checks
• CPC Class Codes: G06Q 20/4016 involving fraud or risk level assessment in transaction processing
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 50/18 Legal services
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening
• CPC Class Codes: G06V 40/1365 Matching; Classification
• CPC Class Codes: G07D 7/003 using security elements using digital security elements G07D7/004
• CPC Class Codes: G07D 7/2033 Matching unique patterns, i.e. patterns that are unique to each individual paper

Abstract

A digital image of a surface of a check is received. A check scanning device captures the digital image as the check moves through the check scanning device. A fingerprint is impressed on the surface of the check. A computing system uses the digital image to determine a match score. The match score represents an approximate probability that the fingerprint on the check matches a reference fingerprint. An alert is presented based on the match score.

Claims

1. A method comprising:

receiving a digital image of a surface of a check, wherein a fingerprint is impressed on the surface of the check, wherein the digital image has a resolution of 500 dpi or less;

using, by a computing system, the digital image to determine a match score, the match score representing a probability that the fingerprint on the check matches a plurality of reference fingerprints stored in a database, wherein using the digital image comprises;

applying one or more image enhancing processing operations to a fingerprint image, the fingerprint image being a digital image containing the fingerprint; and

using the fingerprint image to determine the match score; and

presenting an alert based on the match score.

2. The method of claim 1, wherein presenting the alert comprises:

instructing a cashier to segregate the check for subsequent analysis when the match score exceeds an alert threshold; and

instructing the cashier to complete a transaction involving the check when the match score is below the alert threshold.

3. The method of claim 1, wherein the digital image is a grayscale image.

4. The method of claim 1, wherein using the digital image comprises:

applying one or more image processing operations to the fingerprint image; and

using the fingerprint image to determine the match score.

5. The method of claim 1, wherein applying the one or more image processing operations comprises:

applying one or more image processing operations that reduce artifacts caused by movement of the check through a check scanning device that generated the digital image.

6. The method of claim 1,

wherein the method further comprises:

detecting a fiducial mark on the check; and

wherein applying the one or more image processing operations comprises;

using the fiducial mark during performance of at least one of the image processing operations.

7. The method of claim 1, wherein using the digital image further comprises:

after applying the one or more of image processing operations to the fingerprint image, calculating a fingerprint image quality metric of the fingerprint image, wherein the fingerprint image quality metric of the fingerprint image is a measure of an expected accuracy in representing the fingerprint; and

adjusting the match score based on the fingerprint image quality metric.

8. The method of claim 1,

wherein using the digital image comprises:

using the fingerprint image to generate a target fingerprint template that represents the fingerprint; and

calculating the match score by comparing the target fingerprint template and a given reference fingerprint template, the given reference fingerprint template representing the reference fingerprint; and

wherein presenting the alert comprises presenting the alert when the match score exceeds an alert threshold.

9. The method of claim 1, wherein the method further comprises:

storing a plurality of reference fingerprint templates, each reference fingerprint template representing a fingerprint of a different person, the plurality of reference fingerprint templates including a reference fingerprint template representing the reference fingerprint; and

wherein using the digital image comprises;

generating a target fingerprint template of the fingerprint from the digital image; and

calculating match scores by comparing the target fingerprint template with the plurality of reference fingerprint templates until a given match score is calculated that exceeds a search-ending threshold, the match scores representing approximate probabilities that the target fingerprint template matches the reference fingerprint templates; and

wherein presenting the alert comprises presenting the alert when the given match score exceeds an alert threshold.

10. The method of claim 9, further comprising:

performing a learning process that seeks to reduce a rate of false matches and false non-matches.

11. The method of claim 10, wherein performing the learning process comprises dynamically adjusting the search-ending threshold based on fraud patterns.

12. The method of claim 10, wherein performing the learning process comprises:

dynamically adjusting the alert threshold based on local fraud patterns.

13. A computer-readable storage device comprising instructions that, when executed by a processing unit of a computing device, cause the computing device to:

receive a digital image of a surface of a check, wherein a check scanning device captures the digital image as the check moves through the check scanning device, wherein a fingerprint is impressed on the surface of the check, wherein the digital image has a resolution of less than 500 dpi;

use the digital image to determine a match score, the match score representing an approximate probability that the fingerprint on the check matches a reference fingerprint, wherein use the digital image comprises applying one or more image enhancing processing operations to a fingerprint image, the fingerprint image being a digital image containing the fingerprint; and

cause a workstation device to present an alert when the match score exceeds an alert threshold.

14. The computer-readable storage device of claim 13, wherein the instructions, when executed by the processing unit, cause the computing device to:

generate a target fingerprint template that represents the fingerprint;

store a plurality of reference fingerprint templates in a database, each of the reference fingerprint templates representing a fingerprint of a different person, each of the plurality of reference fingerprint templates representing one of the plurality of reference fingerprints; and

calculate the match score by comparing the target fingerprint template and the reference fingerprint template.

15. The computer-readable storage device of claim 14, wherein the instructions, when executed by the processing unit, further cause the computing device to:

search the fingerprint templates in the database for the reference fingerprint that closely matches the fingerprint using a fingerprint analysis system.

16. The computer-readable storage device of claim 13, wherein at least one reference fingerprint represents a fingerprint of a person suspected of committing check fraud.

17. The computer-readable storage device of claim 13, wherein the instructions, when executed by the processing unit, further cause the computing device to:

perform a learning process that seeks to reduce a rate of false matches and false non-matches.

18. The computer-readable storage device of claim 17, wherein the learning process comprises dynamically adjusting a search-ending threshold based on fraud patterns.

19. The computer-readable storage device of claim 17, wherein the learning process comprises:

dynamically adjusting the alert threshold based on local fraud patterns.

20. The computer-readable storage device of claim 13, wherein the instructions, when executed by the processing unit, further cause the computing device to:

store a plurality of reference fingerprint templates;

generate a target fingerprint template of the fingerprint from the digital image; and

calculate match scores by comparing the target fingerprint template with the plurality of reference fingerprint templates until a given match score is calculated that exceeds a search-ending threshold, the match scores representing approximate probabilities that the target fingerprint template matches the reference fingerprint templates.