Systems and methods for digital signature detection

• US 10,713,629 B1
• Filed: 05/16/2019
• Issued: 07/14/2020
• Est. Priority Date: 09/28/2007
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Medina, III, Reynaldo
• Primary Examiner(s): Vu, Kim Y
• Assistant Examiner(s): Vanchy, Jr., Michael J
• Application Number:
  US16/414,220
• Time in Patent Office: 425 Days
• CPC Class Codes: G06Q 20/02 involving a neutral party, e.g. certification authority, notary or trusted third party [TTP]
• CPC Class Codes: G06Q 20/042 characterized in that the payment protocol involves at least one cheque
• CPC Class Codes: G06Q 20/0425 the cheque being electronic only
• CPC Class Codes: G06Q 20/4014 Identity check for transactions
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
• CPC Class Codes: G06V 40/33 based only on signature image, e.g. static signature recognition
• CPC Class Codes: G07C 9/35 by means of a handwritten signature

Abstract

A system, method and computer-readable medium are provided to enable digital bank endorsement. A digital image of a back side of a check may be placed in a computer memory. Appropriate coordinates for a bank endorsement may be determined. A bank endorsement may be automatically generated. The digital image may then be electronically altered by overlaying, merging, or rendering text of the generated bank endorsement. A modified digital image may be combined with an image of the front side of the check and stored and/or exported to check clearing operations.

Claims

1. A processor-implemented method for detecting a signature, comprising:

using a processor for;

receiving an image of a negotiable instrument in an image memory;

converting the negotiable instrument image from a first digital image format to a second digital image format;

detecting a type of the negotiable instrument in the second digital image format, wherein detecting the type of the negotiable instrument comprises;

determining whether the negotiable instrument image is a business check image or a personal check image;

in response to determining that the negotiable instrument image is a business check image, accessing a business check image minimum pixel count threshold; and

in response to determining that the negotiable instrument image is a personal check image, accessing a personal check image minimum pixel count threshold, wherein the business check image minimum pixel count threshold is different from the personal check image minimum pixel count threshold;

selecting a signature window location technique to apply to the negotiable instrument image based on the detected type of the negotiable instrument;

determining a signature window location using the selected signature window location technique;

counting a number of dark pixels in the determined signature window location in the negotiable instrument image to generate a signature window pixel count;

comparing the signature window pixel count to a minimum pixel count threshold for the detected type of negotiable instrument; and

determining a potential signature error when the signature window pixel count is less than the minimum pixel count threshold for the detected type of negotiable instrument.

2. The method of claim 1, wherein in response to determining that the negotiable instrument image is a business check image, accessing a business check image pixel count threshold range;

and

in response to determining that the negotiable instrument image is a personal check image, accessing a personal check image pixel count threshold range.

3. The method of claim 1, wherein in response to determining that the negotiable instrument image is the business check image, the potential signature error is determined when the signature window pixel count is outside a business check image pixel count range;

and

wherein in response to determining that the negotiable instrument image is the personal check image, the potential signature error is determined when the signature window pixel count is outside a personal check image pixel count range, wherein the personal check image pixel count range is greater than the business check image pixel count range.

4. The method of claim 1, wherein detecting the type of the negotiable instrument comprises detecting a size of the negotiable instrument in the negotiable instrument image in the second digital image format.

5. The method of claim 4, wherein in response to detecting the type of the negotiable instrument to be a business check, analyzing the negotiable instrument image for a presence of a graphical feature and determining the signature window location to be adjacent the graphical feature.

6. The method of claim 5, wherein in response to detecting the type of the negotiable instrument to be a personal check, performing optical character recognition on the negotiable instrument image and identifying a predetermined word;

and

determining the signature window location to be adjacent the predetermined word.

7. A processor-implemented method for detecting a signature, comprising:

using a processor for;

receiving an image of a negotiable instrument in an image memory;

converting the negotiable instrument image from a first digital image format to a second digital image format;

detecting a type of the negotiable instrument in the second digital image format;

selecting a signature window location technique to apply to the negotiable instrument image based on the detected type of the negotiable instrument;

determining a signature window location using the selected signature window location technique;

counting a number of dark pixels in the determined signature window location to generate a signature window pixel count;

comparing the signature window pixel count to a pixel count threshold range;

determining a potential signature error when the signature window pixel count is outside the pixel count threshold range; and

wherein comparing the signature window pixel count to the pixel count threshold range comprises dynamically determining a maximum pixel count threshold by;

sampling pixel counts from multiple areas in the negotiable instrument image;

determining, from amongst the multiple areas sampled, a highest pixel count and a lowest pixel count;

averaging the highest pixel count and the lowest pixel count to generate an average pixel count; and

selecting the maximum pixel count threshold to be between the highest pixel count and the average pixel count.

8. The method of claim 7, wherein comparing the signature window pixel count to the pixel count threshold range further comprises:

comparing the signature window pixel count to the maximum pixel count threshold, and

wherein the potential signature error is determined when the signature window pixel count is greater than the maximum pixel count threshold.

9. The method of claim 7, further comprising:

determining a minimum pixel count threshold dynamically; and

comparing the signature window pixel count to the minimum pixel count threshold and the maximum pixel count threshold, and

wherein the potential signature error is determined when the signature window pixel count is greater than the maximum pixel count threshold or less than the minimum pixel count threshold.

10. The method of claim 7, wherein a first signature window location technique is associated with detecting that the type of the negotiable instrument is a personal check, wherein the first signature window location technique comprises the processor using optical character recognition to identify a predetermined word on the negotiable instrument and positioning a signature window location adjacent the predetermined word.

11. The method of claim 10, wherein a second signature window location technique is associated with detecting that the type of the negotiable instrument is a business check, wherein the second signature window location technique comprises the processor identifying a graphical check feature and positioning the signature window location adjacent the graphical check feature.

12. The method of claim 11, wherein the graphical check feature comprises a horizontal line.

13. A system for detecting a signature on a negotiable instrument, the system comprising:

a memory including processor-executable instructions; and

a processor in communication with the memory and configured, when executing the processor-executable instructions, to;

receive an image of a negotiable instrument in an image memory;

convert the negotiable instrument image from a first digital image format to a second digital image format;

detect a type of the negotiable instrument in the second digital image format, wherein to detect the type of the negotiable instrument the processor is configured to;

determine whether the negotiable instrument image is a business check image or a personal check image;

in response to determining that the negotiable instrument image is a business check image, access a business check image minimum pixel count threshold; and

in response to determining that the negotiable instrument image is a personal check image, access a personal check image minimum pixel count threshold, wherein the business check image minimum pixel count threshold is different from the personal check image minimum pixel count threshold;

select a signature window location technique to apply to the negotiable instrument image based on the detected type of the negotiable instrument;

determine a signature window location using the selected signature window location technique;

count a number of dark pixels in the determined signature window location to generate a signature window pixel count;

compare the signature window pixel count to a minimum pixel count threshold for the detected type of the negotiable instrument; and

determine a potential signature error when the signature window pixel count is less than the minimum pixel count threshold for the detected type of negotiable instrument.

14. The system of claim 13, wherein the processor is further configured to access a maximum pixel count threshold based on the detected type of the negotiable instrument.

15. The system of claim 13, wherein the processor, when executing the processor-executable instructions, is configured to, in response to determining that the negotiable instrument is a business check, analyze the negotiable instrument image for a presence of a graphical feature and determine the signature window location to be adjacent the graphical feature.

16. The system of claim 13, wherein the processor, when executing the processor-executable instructions, is configured to, in response to determining that the negotiable instrument is a personal check:

perform optical character recognition on the negotiable instrument image and identify a predetermined word; and

determining the signature window location to be adjacent the predetermined word.

17. The system of claim 13, wherein a first signature window location technique is associated with detecting that the type of the negotiable instrument is a personal check, wherein the first signature window location technique comprises the processor using optical character recognition to identify a predetermined word on the negotiable instrument and positioning a signature window location adjacent the predetermined word.

18. The system of claim 17, wherein a second signature window location technique is associated with detecting that the type of the negotiable instrument is a business check, wherein the second signature window location technique comprises the processor identifying a graphical check feature and positioning the signature window location adjacent the graphical check feature.

19. The system of claim 18, wherein the graphical check feature comprises a horizontal line.