US 11,837,001 B2
Stroke attribute matrices
Claes-Fredrik U. Mannby, Mercer Island, WA (US)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Mar. 15, 2022, as Appl. No. 17/695,356.
Application 17/695,356 is a continuation of application No. 16/744,654, filed on Jan. 16, 2020, granted, now 11,301,674.
Prior Publication US 2022/0207899 A1, Jun. 30, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/00 (2022.01); G06V 30/32 (2022.01); G06F 3/04883 (2022.01); G06F 17/16 (2006.01); G06V 30/142 (2022.01)
CPC G06V 30/347 (2022.01) [G06F 3/04883 (2013.01); G06F 17/16 (2013.01); G06V 30/1423 (2022.01); G06V 30/387 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
one or more processors; and
one or more memory devices that store program code configured to be executed by the one or more processors, the program code comprising:
a stroke recognizer including at least one machine-learning (ML) classifier, the stroke recognizer configured to:
receive a bitmap, wherein the bitmap encodes at least one stroke attribute generated from stroke data associated with stroke input from a user;
provide the bitmap to the at least one ML classifier to generate a classification; and
determine what the stroke input from the user represents based on the classification.