Patent Issued for Systems And Methods For Digital Signature Detection (USPTO 10,354,235)

2019 JUL 30 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- United Services Automobile Association (San Antonio, Texas, United States) has been issued patent number 10,354,235, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Medina, III, Reynaldo (San Antonio, TX).

This patent was filed on June 12, 2015 and was published online on July 29, 2019.

From the background information supplied by the inventors, news correspondents obtained the following quote: “Check usage has undergone global decline as a result of faster, cheaper, and more secure electronic payment systems. Checks have not disappeared entirely however. In several major economies including the United States, checks remain widely used. The Check Clearing for the 21.sup.st Century Act (‘Check 21’) was enacted by the United States federal government on Oct. 28, 2003 and took effect exactly one year later. The law allows a recipient of a check to create a digital version, thereby eliminating any need for further handling of the physical document.

“A check made and cleared in the United States typically follows the following cycle: the maker of the check first writes the check, signs the front of the check, and gives it to the payee. The payee then endorses the check by signing the back side of the check, and gives the check to a receiving bank, e.g. a bank at which the payee may have a deposit account. The receiving bank stamps the check on the back side with a bank endorsement, and presents the check to the drawee. The drawee is a financial institution at which the maker holds an account, and the drawee is therefore legally obliged to honor the check.

“The portion of the above described cycle occurring after receipt of the check by the receiving bank is referred to herein as clearing the check. After Check 21, the receiving bank may convert the front and back sides of the check into digital images. The images thus acquired may be presented to the drawee instead of the physical check.

“Because check processing has become increasingly mechanized, and to further reduce check processing costs and improve check clearing speed under Check 21, there is a need in the industry to provide effective technologies for digital signature detection on checks.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “The described embodiments contemplate systems, methods and computer-readable media with computer-executable instructions for digital signature detection on checks. In one embodiment, a method for detecting a signature on a check is contemplated. The method includes loading a check image into a computer memory, then determining a signature window location on the check image. A process counts a number of pixels in the signature window to acquire a signature window pixel count. The signature window pixel count can then be compared to a minimum pixel threshold and a maximum pixel threshold. If the count is below the minimum threshold, the presence of a signature is unlikely. Similarly, if the count is above the maximum threshold, the presence of a signature is unlikely. Additional comparisons and analysis may be performed in some embodiments. Finally, a detection flag may be set to true when the signature window pixel count is, for example, greater than the minimum pixel threshold and less than the maximum pixel threshold.

“In another exemplary embodiment, a method for detecting a signature on a check comprises determining whether a check image is a business check image or a personal check image, using common characteristics that can be used to distinguish such images. When the check is a business check, a business check signature detection process is applied. Alternatively, when the check is a personal check, a personal check signature detection process is applied.

“In a third exemplary embodiment, a method for detecting a signature on a check comprises loading a check image and determining signature window locations for a first signature window on a first end of said check image, and for a second signature window on a second end of said check image, said second end being opposite from said first end. The method may next count a number of pixels in said first and second signature windows to acquire first and second signature window pixel counts. The first signature window pixel count can be compared to said second signature window count, and a detection flag may be set to true when the first signature window pixel count differs from said second signature window pixel count.

“Additional advantages and features of the invention are described below.”

The claims supplied by the inventors are:

“The invention claimed is:

“1. A processor-implemented method for detecting a signature, comprising: using a processor for: accessing a negotiable instrument image, the negotiable instrument image in a first digital image format; converting the negotiable instrument image from the first digital image format to a second digital image format; dynamically determining a maximum pixel count threshold by sampling multiple areas in the converted negotiable instrument image; counting a number of a type of pixels in a signature window of the converted negotiable instrument image to generate a signature window pixel count, wherein the type of pixels comprise dark pixels; comparing the signature window pixel count to the maximum pixel count threshold; and determining a potential signature error when the signature window pixel count is greater than the maximum pixel count threshold.

“2. The method of claim 1, further comprising determining a type of negotiable instrument; and wherein the accessed maximum pixel count threshold is based on the determined type of negotiable instrument.

“3. The method of claim 2, wherein determining the type of negotiable instrument comprises determining whether the converted negotiable instrument image is a business check image or a personal check image; in response to determining that the converted negotiable instrument image is a business check image, accessing a business check image maximum pixel count threshold; and in response to determining that the converted negotiable instrument image is a personal check image, accessing a personal check image maximum pixel count threshold.

“4. The method of claim 3, in response to determining that the converted negotiable instrument image is a business check image, accessing a business check image minimum pixel count threshold; in response to determining that the converted negotiable instrument image is a personal check image, accessing a personal check image minimum pixel count threshold; and wherein the business check image minimum pixel count threshold is different from the personal check image minimum pixel count threshold.

“5. The method of claim 4, wherein in response to determining that the converted negotiable instrument image is the business check image, the potential signature error is determined when the signature window pixel count is greater than the business check image maximum pixel count threshold or less than the business check image minimum pixel count threshold; and wherein in response to determining that the converted negotiable instrument image is the personal check image, the potential signature error is determined when the signature window pixel count is greater than the personal check image maximum pixel count threshold or less than the personal check image minimum pixel count threshold.

“6. The method of claim 1, wherein dynamically determining the maximum pixel threshold comprises: 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 threshold to be between the highest pixel count and the average pixel count.

“7. The method of claim 6, further comprising: determining a minimum pixel count threshold dynamically; and comparing the signature window pixel count to the minimum 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.

“8. The method of claim 7, wherein the minimum pixel count threshold is determined dynamically by: selecting the minimum pixel threshold to be between the lowest pixel count and the average pixel count.

“9. The method of claim 1, further comprising comparing the signature window pixel count to a minimum pixel threshold; and wherein the potential signature error is determined when the signature window pixel count is less than the minimum pixel threshold.

“10. 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: access a negotiable instrument image, the negotiable instrument image in a first digital image format; convert the negotiable instrument image from the first digital image format to a second digital image format; dynamically determine a maximum pixel count threshold by sampling multiple areas in the converted negotiable instrument image; count a number of a type of pixels in a signature window of the converted negotiable instrument image to generate a signature window pixel count, wherein the type of pixels comprise dark pixels; compare the signature window pixel count to the maximum pixel count threshold; and determine a potential signature error when the signature window pixel count is greater than the maximum pixel count threshold.

“11. The system of claim 10, wherein the processor, when executing the processor-executable instructions, is further configured to determine a type of negotiable instrument; and wherein the processor, when executing the processor-executable instructions, is configured to access maximum pixel count threshold based on the determined type of negotiable instrument.

“12. The system of claim 11, wherein the processor, when executing the processor-executable instructions, is configured to determine the type of negotiable instrument by determining whether the converted negotiable instrument image is a business check image or a personal check image; in response to determining that the converted negotiable instrument image is a business check image, the processor, when executing the processor-executable instructions, is configured to access a business check image maximum pixel count threshold; and in response to determining that the converted negotiable instrument image is a personal check image, the processor, when executing the processor-executable instructions, is configured to access a personal check image maximum pixel count threshold.”

For the URL and additional information on this patent, see: Medina, III, Reynaldo. Systems And Methods For Digital Signature Detection. U.S. Patent Number 10,354,235, filed June 12, 2015, and published online on July 29, 2019. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=10,354,235.PN.&OS=PN/10,354,235RS=PN/10,354,235

(Our reports deliver fact-based news of research and discoveries from around the world.)