System and method for recognizing online handwriting

Abstract

A method for recognizing online handwriting comprisingacquiring, by a handwriting instrument comprising a module comprising at least one motion sensor, motion data on the handwriting of the user when the user is writing a sequence of characters with the handwriting instrument, the handwriting instrument further including a body extending longitudinally between a first end and a second end, the first end having a writing tip which is able to write on a support,analyzing the motion data with a machine learning model trained in a multi-task way, the machine learning model being configured to deliver as an output the sequence of characters which was written by the user with the handwriting instrument.

1 .- 8 . (canceled) 
     
     
         9 . A method for recognizing online handwriting comprising
 acquiring, with a handwriting instrument comprising a module comprising at least one motion sensor, motion data on the handwriting of the user when said user is writing a sequence of characters with said handwriting instrument, said handwriting instrument further including a body extending longitudinally between a first end and a second end, said first end having a writing tip which is able to write on a support,   analyzing said motion data with a machine learning model trained in a multi-task way, said machine learning model being configured to deliver as an output the sequence of characters which was written by the user with said handwriting instrument.   
     
     
         10 . The method according to  claim 19 , further comprising a prior step of multi-task training of the machine learning model, wherein the machine learning model is trained to perform:
 a stroke segmentation task,   a character classification task.   
     
     
         11 . The method according to  claim 10 , wherein the stroke segmentation task comprises labelizing samples of the acquired motion data in at least one of the following classes:
 on-paper stroke,   in-air movement.   
     
     
         12 . The method according to  claim 14 , wherein the acquired motion data are pre-processed before being used in the stroke segmentation task by:
 windowing the raw motion data in time frames of N samples, each sample in the time frame step being labelized in one of the on-paper stroke and/or in-air movement.   
     
     
         13 . The method according to claim  1 , wherein the in-air movement label comprises at least two sub labels:
 forward in-air movement,   backward in-air movement.   
     
     
         14 . The method according to claim  1 , wherein once trained, the machine learning model is stored, the method further comprising the analysis of said acquired motion data continuously and in real time with the trained machine learning model. 
     
     
         15 . The method according to claim  1 , wherein the module is embedded in the second end of the handwriting instrument. 
     
     
         16 . The method according to claim  1 , wherein the module is distinct from the handwriting instrument, said module being intended to be placed on the second end of the handwriting instrument. 
     
     
         17 . The method according to claim  1 , wherein the module further comprises the calculating unit. 
     
     
         18 . The method according to claim  1 , wherein the module further includes a short-range radio communication interface configured to communicate raw motion data acquired by the motion sensor to a mobile device comprising the calculating unit via a communication interface of the mobile device. 
     
     
         19 . The method according to claim  1 , wherein the motion sensor is a three-axis accelerometer. 
     
     
         20 . The method according to  claim 11 , wherein the module further comprises a second motion sensor being a three-axis gyroscope.