US 12,462,345 B2
Glare mitigation techniques in symbologies
Michael Soborski, Allentown, NJ (US); Bodhayan Dev, Sturbridge, MA (US); Prem Swaroop, Lexington, MA (US); Atish P. Kamble, Acton, MA (US); and Matthias Voigt, Lawrenceville, NJ (US)
Assigned to Sys-Tech Solutions, Inc., Princeton, NJ (US)
Filed by Sys-Tech Solutions, Inc., Princeton, NJ (US)
Filed on Mar. 10, 2022, as Appl. No. 17/692,063.
Prior Publication US 2023/0289922 A1, Sep. 14, 2023
Int. Cl. G06K 9/00 (2022.01); G06K 7/14 (2006.01); G06T 5/50 (2006.01); G06T 5/70 (2024.01); G06T 7/246 (2017.01); G06T 7/33 (2017.01); G06V 10/10 (2022.01); G06V 10/24 (2022.01); G06V 10/82 (2022.01)
CPC G06T 5/70 (2024.01) [G06K 7/1413 (2013.01); G06K 7/146 (2013.01); G06T 5/50 (2013.01); G06T 7/246 (2017.01); G06T 7/33 (2017.01); G06V 10/16 (2022.01); G06V 10/245 (2022.01); G06V 10/82 (2022.01); G06T 2207/20221 (2013.01); G06T 2207/30244 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining, with at least one processor, first images containing a representation of a mark, the images comprising multiple poses of the mark;
generating, with the at least one processor, a single image with reduced glare from the first images using a trained machine learning model, wherein the glare associated with the single image is reduced relative to glare associated with the first images; and
providing, with the at least one processor, the single image for processing of the representation of the mark to identify information associated with the mark.