Systems and methods of check detection

• US 8,452,689 B1
• Filed: 02/18/2009
• Issued: 05/28/2013
• Est. Priority Date: 02/18/2009
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Medina, Reynaldo III
• Primary Examiner(s): Kazimi, Hani M
• Assistant Examiner(s): GRAHAM, CLEMENT B
• Application Number:
  US12/388,005
• Time in Patent Office: 1,560 Days
• Field of Search: 705 35- 39
• US Class Current: 705/37
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/41 Analysis of document content recognition of printed characters based on code marks G06V30/224

Abstract

A digital image of a check may be divided into segments. The segments may be processed to determine the edges between the background data and the check data in the segments of the digital image. A histogram of each segment may be determined and used to determine the edges of the check image portions in the segments and thus the edges of the check. The data outside the edges of the check image portions in the segments may be considered to be background data and may be identified and/or removed. The segments, with the background data removed, may be recombined into an image of the check and provided into a digital image file that may be transmitted to an institution system for deposit of the check in an account.

Claims

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

divide a grayscale image of a digital image into a plurality of segments, wherein the digital image includes a check image and a background image, and wherein each segment comprises a portion of the check image and a portion of the background image;

determine a threshold on a data construct of grayscale levels of each segment between data representing the portion of the check image on the segment and data representing the portion of the background image on the segment;

identify the portion of the background image using the threshold;

process each segment to remove the identified portion of the background image;

recombine the segments to form a digital image file comprising the check image; and

transmit the digital image file to an institution for processing of a check associated with the check image in the digital image file.

2. The computer-readable medium of claim 1, wherein the data construct of grayscale levels comprises a histogram, and the threshold corresponds to a level on the histogram between a first density area corresponding to the portion of the background image and a second density area corresponding to the portion of the check image.

3. The computer-readable medium of claim 1, further comprising instructions that blur the grayscale image prior to dividing the grayscale image into the segments.

4. A system for check detection, comprising:

a memory;

a processor disposed in communication with said memory, and configured to issue a plurality of processing instructions stored in the memory, wherein the processor is configured to;

create a digital image of a check, the digital image comprising a check image and a background image;

convert the digital image to a grayscale image;

divide the grayscale image into a plurality of segments, each segment comprising a portion of the check image and a portion of the background image;

obtain a data construct of grayscale levels for each segment;

determine a threshold on the data construct of grayscale levels between data representing the portion of the check image on the segment and data representing the portion of the background image on the segment;

identify the portion of the background image of each segment using the data construct of grayscale levels; and

generate an image comprising the check image using the data construct of grayscale levels for each segment and the identified portion of the background image for each segment.

5. The system of claim 4, wherein the processor is further configured to:

store a copy of the grayscale image prior to dividing the grayscale image into the segments;

retrieve the copy of the grayscale image after generating the image;

process the copy of the grayscale image using the image; and

store a digital image file comprising the processed copy of the grayscale image.

6. The system of claim 5, wherein the processor is further configured to:

detect a plurality of corners of the image comprising the check image using the data construct of grayscale levels for each segment and the identified portion of the background image for each segment; and

dewarp and crop the copy of the grayscale image using the corners of the image.

7. The system of claim 5, wherein the processor is further configured to deposit the check into an account using the digital image file.

8. The system of claim 4, wherein each segment comprises only one portion of the check image and only one portion of the background image.

9. The system of claim 4, wherein the processor is further configured to determine a threshold level on the data construct of grayscale levels representative of an edge between the portion of the check image and the portion of the background image, wherein the portion of the background image is identified as being on one side of the threshold level.

10. The system of claim 4, wherein the processor is further configured to recombine the segments after identifying the portion of the background image of each segment.

11. The system of claim 4, wherein the data construct of grayscale levels comprises a histogram.

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

receive a grayscale image comprising a digital image, the digital image including a check image and a background image;

determine a plurality of segments of the grayscale image;

determine a threshold on a data construct of grayscale levels of each segment of the grayscale image between data representing a portion of the check image on the segment and data representing a portion of the background image on the segment;

identify the portion of the background image in each of the plurality of segments;

recombine the plurality of segments to form a digital image file comprising the check image without the identified portion of the background image;

and

deposit a check associated with the check image in the digital image file into an account.

13. The computer-readable medium of claim 12, further comprising instructions that generate an image comprising the check image using a camera of a mobile device, wherein the mobile device converts the image to the grayscale image and determines the plurality of segments and recombines the plurality of segments.

14. The computer-readable medium of claim 12, further comprising instructions that generate an image comprising the check image using a camera of a mobile device, wherein the mobile device converts the image to the grayscale image and wherein a financial institution determines the plurality of segments and recombines of the plurality of segments.

15. The computer-readable medium of claim 12, wherein the grayscale image is received at an institution, wherein the institution determines the plurality of segments, recombines the plurality of segments, and deposits the check into the account.

16. The computer-readable medium of claim 12, wherein the data construct of grayscale levels comprises a histogram.

17. The computer-readable medium of claim 16, wherein the instructions that determine the threshold comprise instructions that determine a minimum between two density areas on the histogram.