IP Library › Granted Patent US 12,249,112
Granted Patent B1
US 12,249,112 · App. 17/583,063 · Granted Mar 11, 2025

Handwriting recognition systems and methods

Inventor: Thomas O Binford (Cupertino, CA)
Assignee: Read-Ink Corporation
G06V10/751G06T7/60G06V10/426G06V10/44G06V30/153G06V30/268G06V30/347G06V30/36G06T2207/30176G06V30/10
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,249,112
App. No.
17/583,063
Granted
Mar 11, 2025
Kind
B1
Abstract

The present disclosure includes systems and methods for handwriting recognition. Handwriting data is received. Geometric data of text in handwriting data is determined. Sub-characters of the text are determined. Sub-characters of text are matched to a model. Most probable characters of the text is determined based on the matching.

Claims (23)

1. A method for recognizing handwriting, the method comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein the model includes co-articulation of every pair of characters to make use of their orthographic evidence to reduce their variance.

2. The method of claim 1 , further comprising estimating math support to reduce variance of segments of the segmentation of the sub-characters of the text.

3. A non-transitory computer-readable storage medium storing instructions for handwriting recognition, the instructions when executed by one or more processors causing the one or more processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein the model includes co-articulation of every pair of characters to make use of their orthographic evidence to reduce their variance.

4. A computer system for handwriting recognition, the computer system comprising: one or more computer processors; and one or more non-transitory computer-readable storage media, the storage media storing computer program instructions executable by the one or more computer processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein the model includes co-articulation of every pair of characters to make use of their orthographic evidence to reduce their variance.

5. The method of claim 3 , further comprising using arc lengths of segments of the sub-characters of the text.

Continuity (2)
Continuation 16925090 · Jul 9, 2020
Division 16419635 · May 22, 2019
References Cited (12)
US 5687254A · Poon · 1997 [cited by examiner]
US 6556712B1 · Loudon · 2003 [cited by examiner]
US 6813624B1 · Dharanipragada · 2004 [cited by examiner]
US 6986106B2 · Soin · 2006 [cited by examiner]
US 7886236B2 · Kolmykov-Zotov · 2011 [cited by examiner]
US 7929770B2 · Arai · 2011 [cited by examiner]
US 10748031B1 · Binford · 2020 [cited by examiner]
US 10872266B1 · Binford · 2020 [cited by examiner]
US 11216688B1 · Binford · 2022 [cited by examiner]
US 11232322B1 · Binford · 2022 [cited by examiner]
US 11496635B2 · Okuma · 2022 [cited by examiner]
US 20120287089A1 · Shiota · 2012 [cited by examiner]