Electronic device and handwriting recognition method

Patent metadata

Field	Value
Publication number	US-12266200-B2
Application number	US-202217875605-A
Country	US
Kind code	B2
Filing date	Jul 28, 2022
Priority date	Jul 28, 2021
Publication date	Apr 1, 2025
Grant date	Apr 1, 2025

Abstract

According to certain embodiments, an electronic device may include a display, a memory, and a processor operatively connected to the display and the memory. The processor may be configured to, while receiving user's touch input in a handwriting area of the display, the user's touch input comprising successive input stokes: output the successive input strokes in the handwriting area on the display; determine a first stroke group including some of the successive input strokes, to determine a first character corresponding to the first stroke group, to output the first stroke group in an output area adjacent to the handwriting area on the display, to determine a second stroke group including at least another input stroke received after the some of the successive input strokes, to determine a second character corresponding to the second stroke group, and to output the second stroke group in the output area, move the first stroke group to on one side of the second stroke group on the display.

First claim

The invention claimed is:

1. An electronic device comprising:
a display;
a memory; and
a processor operatively connected to the display and the memory,
wherein the processor is configured to:
determine a first stroke group including at least one input stroke upon receiving a user's touch input,
determine a first character corresponding to the first stroke group,
output the first stroke group in an output area adjacent to a handwriting area on the display,
determine a second stroke group including at least another input stroke received after the some of a successive input strokes,
determine a second character corresponding to the second stroke group, and
output the second stroke group on one side of the previously outputted first stroke group.

2. The electronic device of claim 1 , further comprising:
a handwriting recognition module,
wherein the processor is configured to:
generate a template including at least one input stroke of the successive input strokes,
extract a character corresponding to the template using the handwriting recognition module,
calculate a score indicating similarity between the template and the character in accordance, and
store the calculated score in the memory after mapping the score to the template.

3. The electronic device of claim 2 , wherein the processor is configured to:
use the score stored in the memory when a score corresponding to the template is needed to determine a character corresponding to a stroke group.

4. The electronic device of claim 2 , wherein the processor is configured to:
generate a segment, which is a minimum unit constituting the template, by combining at least one stroke.

5. The electronic device of claim 4 , wherein the processor is configured to:
generate at least one template by combining a predetermined number of consecutive segments.

6. The electronic device of claim 2 , wherein the processor is configured to:
generate at least one character string candidate including at least one template, and
calculate a score of the at least one character string candidate, based on the score of the template included in each character string candidate.

7. The electronic device of claim 2 , calculating the score includes using at least one of a multiple template classifier (MTC), a Gaussian mixture models (GMM), or a language model (LM).

8. The electronic device of claim 1 , wherein the processor is configured to:
output a first text corresponding to the first character or a second text corresponding to the second character.

9. The electronic device of claim 1 , further comprising:
a communication module,
wherein the processor is configured to:
establish a communication connection with an external device by using the communication module, and
display a stroke group or a character on the display of the external device.

10. The electronic device of claim 1 , wherein the processor is configured to:
assign an index to at least one input stroke of the successive input strokes in an inputted order, and
generate a stroke index by mapping a character corresponding to each stroke group and at least one input stroke included in each stroke group.

11. The electronic device of claim 10 , wherein the processor is configured to:
generate a recognition thread for each stroke group, based on the stroke index, and output each stroke group or shift a position, based on the recognition thread.

12. The electronic device of claim 1 , wherein the processor is configured to:
recognize an input stroke of the successive input strokes by identifying a language.

13. The electronic device of claim 1 , wherein the output area is left of the handwriting area on the display.

14. A method for recognizing handwriting in an electronic device, the method comprising:
while receiving user's touch input in a handwriting area of a display, the user's touch input comprising successive input strokes:
outputting the successive input strokes in the handwriting area on the display;
determining a first stroke group including some of the successive input strokes;
determining a first character corresponding to the first stroke group;
outputting the first stroke group in an output area adjacent to the handwriting area on the display;
determining a second stroke group including at least another input received after the some of the successive input strokes;
determining a second character corresponding to the second stroke group; and
outputting the second stroke group in the output area;
moving the first stroke group to one side of the second stroke group on the display.

15. The method of claim 14 , wherein determining a character corresponding to each stroke group further comprises:
generating a template including at least one input stroke of the successive input strokes,
extracting a character corresponding to the template by using a handwriting recognition module,
calculating a score indicating similarity between the template and the character, and
storing the calculated score in a memory after mapping the score to the template.

16. The method of claim 15 , wherein determining the character corresponding to each stroke group further comprises:
using the score stored in the memory when a score corresponding to the template is needed to determine a character corresponding to a stroke group.

17. The method of claim 15 , wherein determining a character corresponding to each stroke group further comprises:
generating at least one character string candidate including at least one template, and
calculating a score of the at least one character string candidate, based on the score of the template included in each character string candidate.

18. The method of claim 14 , further comprising:
outputting a first text corresponding to the first character or a second text corresponding to the second character.

19. The method of claim 14 , wherein outputting each stroke group on a display further comprises:
assigning an index to at least one stroke in an inputted order, and
generating a stroke index by mapping a character corresponding to each stroke group and at least one stroke included in the stroke group.

20. The method of claim 19 , wherein outputting each stroke group on a display further comprises:
generating a recognition thread for each stroke group, based on the stroke index, and
outputting each stroke group or shift a position, based on the recognition thread.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Jihoon
• Park Gwanyong
• Park Jeongwan
• Lee Donghyuk

Classifications

• G06V30/22

  characterised by the type of writing · CPC title

• G06V30/19093

  Proximity measures, i.e. similarity or distance measures · CPC title

• G06V30/347

  Sampling; Contour coding; Stroke extraction · CPC title

• G06F3/04883 Primary

  for inputting data by handwriting, e.g. gesture or text · CPC title

• G06V2201/02

  Recognising information on displays, dials, clocks · CPC title