US 11,816,182 B2
Character encoding and decoding for optical character recognition
Marco Spinaci, Le Chesnay (FR); and Marek Polewczyk, Berlin (DE)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Jun. 7, 2021, as Appl. No. 17/340,794.
Prior Publication US 2022/0391637 A1, Dec. 8, 2022
Int. Cl. G06F 18/214 (2023.01); G06V 30/28 (2022.01)
CPC G06F 18/214 (2023.01) [G06V 30/287 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer system, comprising:
one or more processors; and
one or more machine-readable medium coupled to the one or more processors and storing computer program code comprising sets of instructions executable by the one or more processors to:
determine a plurality of character encodings mapping sets of numbers to a plurality of characters in a language character set, the plurality of characters composed of a plurality of graphical units, different values of numbers in the sets of numbers corresponding to a different graphical unit of the plurality of graphical units, each particular character of the plurality of characters being mapped to a particular set of the sets of numbers having values corresponding to a set of graphical units used in composing the particular character; and
train a machine learning model using the plurality of character encodings, the machine learning model configured to perform optical character recognition of the language character set.