Duplicate check detection

• US 8,611,635 B1
• Filed: 12/20/2012
• Issued: 12/17/2013
• Est. Priority Date: 06/11/2008
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Medina, Reynaldo III
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US13/722,576
• Time in Patent Office: 362 Days
• Field of Search: 382100-103, 382112-116, 382135-139, 382/155, 382/168, 382/171, 382174-194, 382/209, 382/220, 382/232, 382/254, 382/274, 382/276, 382285-294, 382/305, 382/321, 235/375, 235/379, 705/43, 705/45, 348/558
• US Class Current: 382/139
• CPC Class Codes: G06Q 20/00 Payment architectures, schemes or protocols apparatus for performing or posting payment transactions G07F7/08, G07F19/00; electronic cash registers G07G1/12
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes

Abstract

Images from checks may be compared with each other to detect a twice-deposited or represented check. An image of a check may be parsed into regions or tiles, for example. In an implementation, values for regions or tiles over a predetermined area (e.g., an area from a character in the magnetic ink character recognition (MICR) line at the bottom of the check to the dollar sign symbol) may be compared. In an implementation, a virtual overlay of two check images may be performed and a correlation may be determined.

Claims

1. A processor implemented method for duplicate check detection, comprising:

receiving a first check image corresponding to a first check;

receiving a second check image corresponding to a second check;

partitioning the first check image into a plurality of regions;

partitioning the second check image into a plurality of regions;

assigning a value to each region of the first check image;

assigning a value to each region of the second check image;

comparing at least one region of the second check image to at least one region of the first check image in order to determine a level of similarity between the second check image and the first check image by comparing at least one region value for the first check image to at least one region value for the second check image, and

determining the second check image is a duplicate of the first check image when a value of the at least one region value for the first check image and a value of the at least one region value for the second check image are within a predetermined threshold.

2. The method of claim 1, wherein comparing the at least one region of the second check image to the at least one region of the first check image comprises:

comparing at least one region of the second check image that is in a path of a line that runs from a first feature to a second feature on the second check image, to at least one region of the first check image that is in a path of a line that runs from a first feature to a second feature on the first check image.

3. The method of claim 2, wherein the first feature on the second check image is the same as the first feature on the first check image, and the second feature on the second check image matches the second feature on the first check image.

4. The method of claim 2, wherein the first feature corresponds to a magnetic ink character recognition (MICR) line represented on each of the first check image and second check image.

5. The method of claim 1, wherein comparing the at least one region of the second check image to the at least one region of the first check image comprises:

comparing at least one region of the second check image that is adjacent to a first feature on the second check image, to at least one region of the first check image that is adjacent to a first feature on the first check image.

6. The method of claim 5, wherein the first feature on the second check image matches the first feature on the first check image.

7. A duplicate check detection system, comprising:

a memory; and

a processor in communication with the memory, wherein the processor is configured to;

receive a first check image corresponding to a first check;

receive a second check image corresponding to a second check;

partition the first check image into a plurality of regions;

partition the second check image into a plurality of regions;

assign a value to each region of the first check image;

assign a value to each region of the second check image;

compare at least one region of the second check image to at least one region of the first check image in order to determine a level of similarity between the second check image and the first check image by comparing at least one region value for the first check image to at least one region value for the second check image, and

determine the second check image is a duplicate of the first check image

when a value of the at least one region value for the first check image and a value of the at least one region value for the second check image are within a predetermined threshold.

8. The system of claim 7, wherein the processor is configured to compare the at least one region of the second check image to the at least one region of the first check image by:

comparing at least one region of the second check image that is in a path of a line that runs from a first feature to a second feature on the second check image, to at least one region of the first check image that is in a path of a line that runs from a first feature to a second feature on the first check image.

9. The system of claim 8, wherein the first feature on the second check image is the same as the first feature on the first check image, and the second feature on the second check image matches the second feature on the first check image.

10. The system of claim 8, wherein the first feature corresponds to a magnetic ink character recognition (MICR) line represented on each of the first check image and second check image.

11. The system of claim 7, wherein the processor is configured to compare the at least one region of the second check image to the at least one region of the first check image by:

comparing at least one region of the second check image that is adjacent to a first feature on the second check image, to at least one region of the first check image that is adjacent to a first feature on the first check image.

12. The system of claim 11, wherein the first feature on the second check image matches the first feature on the first check image.

13. A non-transitory computer-readable medium comprising computer-readable instructions for duplicate check detection, said computer-readable instructions configured for causing a processor to:

receive a first check image corresponding to a first check;

receive a second check image corresponding to a second check;

partition the first check image into a plurality of regions;

partition the second check image into a plurality of regions;

assign a value to each region of the first check image;

assign a value to each region of the second check image;

compare at least one region of the second check image to at least one region of the first check image in order to determine a level of similarity between the second check image and the first check image by comparing at least one region value for the first check image to at least one region value for the second check image, and

determine the second check image is a duplicate of the first check image when a value of the at least one region value for the first check image and a value of the at least one region value for the second check image are within a predetermined threshold.

14. The non-transitory computer-readable medium of claim 13, wherein the computer-readable instructions are further executed by the processor to:

compare at least one region of the second check image that is in a path of a line that runs from a first feature to a second feature on the second check image, to at least one region of the first check image that is in a path of a line that runs from a first feature to a second feature on the first check image.

15. The non-transitory computer-readable medium of claim 14, wherein the first feature on the second check image is the same as the first feature on the first check image, and the second feature on the second check image matches the second feature on the first check image.

16. The non-transitory computer-readable medium of claim 14, wherein the first feature corresponds to a magnetic ink character recognition (MICR) line represented on each of the first check image and second check image.

17. The non-transitory computer-readable medium of claim 13, wherein the computer-readable instructions are further executed by the processor to:

compare at least one region of the second check image that is adjacent to a first feature on the second check image, to at least one region of the first check image that is adjacent to a first feature on the first check image.

18. The non-transitory computer-readable medium of claim 17, wherein the first feature on the second check image matches the first feature on the first check image.