Systems and methods of check detection

• US 9,946,923 B1
• Filed: 04/30/2013
• Issued: 04/17/2018
• Est. Priority Date: 02/18/2009
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Medina, Reynaldo
• Primary Examiner(s): Kazimi, Hani M
• Application Number:
  US13/874,145
• Time in Patent Office: 1,813 Days
• Field of Search: 705 37, 705 38, 705 39- 43, 705 45, 395600, 382283, 382284, 382209, 382137, 235379
• 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 document detection, the 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 document image representing a document and a background image representing a background, each of the plurality of segments comprising at least a part of the document image;

apply a convolution filter to each of the plurality of segments by;

generating a plurality of filtered segments based on a product of the plurality of segments with a convolution matrix, each of the plurality of filtered segments comprising at least a part of a filtered document image representing the document;

differentiating a filtered background image from the filtered document image in the plurality of filtered segments, wherein the filtered background image is representative of the background;

identifying filtered background images in the plurality of filtered segments;

removing the identified filtered background images from the plurality of filtered segments; and

recombine the plurality of filtered segments to form a digital image file comprising parts of the filtered document image representing the document.

2. The computer-readable medium of claim 1, further comprising instructions for causing the processor to transmit the digital image file to an institution for processing of the document represented by the document image.

3. The computer-readable medium of claim 1, wherein the convolution filter comprises a convolution matrix formed from a vector.

4. The computer-readable medium of claim 1, comprising instructions to dewarp the digital image after recombining the segments.

5. A system for document detection, comprising:

a memory;

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

create a digital image representative of a document, the digital image comprising a document image representing the document and a background image representing a background;

convert the digital image to a grayscale image;

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

apply a convolution filter to each of the plurality of segments by;

generating a plurality of filtered segments based on a product of the plurality of segments with a convolution matrix, each of the plurality of filtered segments comprising at least a part of a filtered document image representing the document;

differentiating a filtered background image from the filtered document image in the plurality of filtered segments, wherein the filtered background image is representative of the background;

identifying filtered background images in the plurality of filtered segments;

removing the identified filtered background images from the plurality of filtered segments; and

recombine the plurality of filtered segments to form a digital image file comprising parts of the filtered document image representing the document.

6. The system of claim 5, wherein the processor is further configured to transmit the digital image file to an institution for processing of the document represented by the document image.

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

detect a plurality of corners in the filtered document image formed from the recombined plurality of filtered segments; and

dewarp and crop the copy of the filtered document image using the detected corners of the image.

8. The system of claim 5, wherein the document comprises a financial document.

9. The system of claim 8, wherein the financial document comprises a check.

10. The system of claim 8, wherein the processor is further configured to deposit the financial document into an account using the digital image file.

11. The system of claim 5, wherein the convolution filter comprises a convolution matrix formed from a vector.

12. The system of claim 5, wherein the processor is further configured to recombine the plurality of filtered segments after identifying the filtered background images in each of the plurality of filtered segments.

13. The system of claim 5, wherein the memory and the processor are part of a mobile user computing device.

14. The system of claim 13, wherein the mobile user computing device comprises a smartphone.

15. A method for document detection in a computing device having a processor and a memory, the method comprising the processor of the computing device:

creating a digital image representative of a document, the digital image comprising a document image representing the document and a background image representing a background;

converting the digital image to a grayscale image;

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

applying a convolution filter to each of the plurality of segments by;

generating a plurality of filtered segments based on a product of the plurality of segments with a convolution matrix, each of the plurality of filtered segments comprising at least a part of a filtered document image representing the document;

differentiating a filtered background image from the filtered document image in the plurality of filtered segments, wherein the filtered background image is representative of the background;

identifying filtered background images in the plurality of filtered segments;

removing the identified filtered background images from the plurality of filtered segments; and

recombining the plurality of filtered segments to form a digital image file comprising parts of the filtered document image representing the document.

16. The method of claim 15, further comprising transmitting the digital image file to an institution for processing of the document represented by the document image.

17. The method of claim 15, wherein the computing device comprises a mobile device and wherein creating the digital image representative of the document further comprises the processor controlling a camera of the mobile device to capture the digital image.

18. The method of claim 15, wherein the document comprises a financial document.

19. The method of claim 18, wherein the financial document comprises a check.

20. The method of claim 18, further comprising the processor depositing the financial document into an account using the digital image file.