US 11,875,397 B2
Image-based financial processing
Michael Mettler, San Francisco, CA (US); and Josh Bleecher Snyder, San Francico, CA (US)
Assigned to PAYPAL, INC., San Jose, CA (US)
Filed by PAYPAL, INC., San Jose, CA (US)
Filed on Sep. 3, 2019, as Appl. No. 16/559,527.
Application 16/559,527 is a continuation of application No. 13/101,067, filed on May 4, 2011, granted, now 10,402,898.
Prior Publication US 2020/0184549 A1, Jun. 11, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 40/02 (2023.01); G06Q 20/04 (2012.01); G06Q 20/32 (2012.01)
CPC G06Q 40/02 (2013.01) [G06Q 20/0425 (2013.01); G06Q 20/3276 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
a non-transitory memory; and
at least one hardware processor coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
receiving a first electronic image of a payment instrument;
performing a preliminary analysis of the first electronic image by:
detecting edges within an overlay box for the first electronic image;
computing an aspect ratio for the detected edges based on a first length of a first edge of a first pair of edges in relation to a second length of a second pair of edges; and
determining, based on a comparison of the aspect ratio for the detected edges of the first electronic image with stored image information, that the first electronic image contains an object that corresponds to a source of financial information;
in response to the determining that the first electronic image contains the object that corresponds to the source of financial information in the preliminary analysis:
identifying areas of image noise in the first electronic image, wherein each area of the image noise indicates a potential character of the financial information;
segmenting the first electronic image into segments corresponding to each area of the image noise in the first electronic image;
extracting, using optical character recognition on each segmented area of the image noise, portions of the financial information corresponding to each segmented area of the image noise;
sequentially ordering the extracted portions of the financial information to provide extracted financial information;
verifying an authenticity of the extracted financial information based on at least the first electronic image and the sequentially ordered extracted portions; and
processing an electronic transaction using the extracted financial information.