Granted Patent B1

US 10,713,629 · App. 16/414,220 · Granted Jul 14, 2020

Inventor: Reynaldo Medina, III (San Antonio, TX)

Assignee: United Services Automobile Association (USAA)

G06Q20/042G06K9/00161G06K9/6202G06Q20/4014G07C9/35

Abstract

Claims (68)

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.

Assignments (1)

Continuity (2)

Cited By (19)

US 12,211,095 US 12,229,734 US 12,229,737 US 12,260,700 US 12,265,952 US 12,346,884 US 12,400,257 US 12,482,288 US 12,499,422 US 12,499,423 US 12,505,414 US 12,511,692 US 12,573,224 US 12,608,690 US 12,626,526 US 12,632,899 US 12,682,327 US 12,699,970 US 12,705,587