US 11,675,495 B2
Handwriting feedback
David Duffy, Zurich (CH); Christopher-John Wright, Lausanne (CH); Timothy Giles Beard, Lausanne (CH); Wai Keith Lau, Lausanne (CH); and William Andrew Schnabel, Lausanne (CH)
Assigned to SOCIÉTÉ BIC, Clichy (FR)
Filed by SOCIETE BIC, Clichy (FR)
Filed on Feb. 18, 2022, as Appl. No. 17/676,014.
Claims priority of application No. 21305281 (EP), filed on Mar. 9, 2021.
Prior Publication US 2022/0291827 A1, Sep. 15, 2022
Int. Cl. G06F 3/04883 (2022.01); G06F 40/166 (2020.01); G06F 40/20 (2020.01); G06V 30/142 (2022.01); G06F 3/044 (2006.01); G06V 30/244 (2022.01); G06V 30/226 (2022.01); G06V 30/32 (2022.01); G06F 3/0354 (2013.01); G06F 3/01 (2006.01)
CPC G06F 3/04883 (2013.01) [G06F 3/03545 (2013.01); G06F 3/044 (2013.01); G06F 40/166 (2020.01); G06F 40/20 (2020.01); G06V 30/1423 (2022.01); G06V 30/226 (2022.01); G06V 30/245 (2022.01); G06V 30/32 (2022.01); G06F 3/018 (2013.01); G06T 2200/24 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method for generating feedback based on a handwritten text, comprising steps of:
initializing a writing instrument to be used in a writing operation comprising the handwritten text;
capturing and processing the handwritten text to generate digital text data by applying a writing digitization algorithm, wherein applying the writing digitization algorithm includes converting tracking data to a set of handwriting feature vectors, and converting the set of handwriting feature vectors to the digital text data via vector-to-character mapping;
identifying at least one handwritten text attribute associated with the digital text data;
comparing the at least one handwritten text attribute with predefined textual feature attributes;
generating a textual feature based on the compared at least one handwritten text attribute and the predefined textual feature attributes, wherein generating the textual feature comprises applying a textual feature generator network trained to perform a style transfer of the predefined textual feature attributes;
modifying the digital text data using the textual feature; and
generating the feedback to a user (U) based on the modified digital text data.