RECOGNIZING HANDWRITING INPUT USING ROTATABLE SUPPORT LINES

• US 20140267072A1
• Filed: 03/14/2013
• Published: 09/18/2014
• Est. Priority Date: 03/14/2013
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Andersson, Jonas, Morwing, Lars Jonas
• Granted Patent: US 9,069,462 B2
• Time in Patent Office: Days
• US Class Current: 345/173
• CPC Class Codes: G06F 18/20 Analysing
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1475 Inclination or skew detection or correction of characters or of image to be recognised
• CPC Class Codes: G06V 30/32 Digital ink

Abstract

Software, firmware, and systems are described for identifying characters in a handwritten input received from a user on an input device, irrespective of an angle that the input is received at. In one implementation, the system establishes an anchor point and distances from the anchor point to reference support lines. A set of candidate characters is identified based on received handwritten input. The system estimates support lines for each of the candidate characters. The system ranks the candidate characters based on a total deviation measurement from the expectation for each candidate, where the expectation in part is based on the established distance from the established anchor point to reference support lines, and identifies a best-ranked candidate based at least in part on a smallest total deviation measurement.

Claims

1. A method for identifying characters in a handwritten input on a touch-sensitive device, the method comprising:

establishing an anchor point on the touch-sensitive device;

establishing distances from the anchor point to one or more reference support lines;

receiving a handwritten user input via the touch-sensitive device;

identifying a set of candidate characters based on the handwritten user input;

estimating support lines for each of the candidate characters;

associating temporary reference support lines for each candidate character based on an angle of the estimated support lines for the candidate character and the established anchor point and established distance from anchor point to the one or more reference support lines;

for each candidate character,

measuring a deviation between the estimated support lines and temporary reference support lines to determine a scale and position deviation from an expectation for each candidate character, and

combining the measured deviation with candidate expectation deviation measurements for properties than other scale and position;

ranking each candidate character based on a total deviation measurement for each candidate character; and

,

identifying a best-ranked candidate character based at least in part on a smallest total deviation measurement.

2. The method of claim 1, wherein the method further comprises establishing new reference support lines based on the temporary reference support lines associated with the best-ranked candidate character.

3. The method of claim 1,

wherein the total deviation measurement for each candidate character is further based at least in part on a deviation between an estimated candidate writing angle and an angle of an orthogonal projection point of a mass center of the curve to the baseline of the estimated support lines around the anchor point.

4. The method of claim 1 further comprising:

receiving a selection of one of the candidate characters from the user; and

setting the new reference support lines as the candidate support lines for the selected candidate.

5. The method of claim 1 wherein:

the reference support lines include a helpline and the baseline and the helpline and the baseline are parallel;

the helpline is a first predetermined perpendicular distance from the anchor point; and

the baseline is a second predetermined perpendicular distance from the anchor point.

6. The method of claim 5 wherein the touch-sensitive device has a circular shape and the anchor point is at a center of the touch-sensitive device.

7. The method of claim 5 wherein a distance between the helpline and the baseline is equal to an expected height of a character of the handwritten input.

8. The method of claim 6 further comprising displaying the helpline and the baseline on the touch-sensitive device.

9. The method of claim 1 wherein the handwritten user input comprises a single character.

10. A system for identifying characters in a handwritten input on an input device, the system comprising:

at least one processor;

at least one data storage device coupled to the at least one processor;

at least one input device, coupled to the at least one processor, to receive single-character manually input by a user;

means for establishing an anchor point on the touch-sensitive device;

means for establishing distances from the anchor point to one or more reference support lines;

means for receiving a handwritten user input via the touch-sensitive device;

means for identifying a set of candidate characters based on the handwritten user input;

means for estimating support lines for each of the candidate characters;

means for associating temporary reference support lines for each candidate character based on an angle of the estimated support lines for the candidate character and the established anchor point and established distance from anchor point to the one or more reference support lines;

means, for each candidate character, for measuring a deviation between the estimated support lines and temporary reference support lines to determine a scale and position deviation from an expectation for each candidate character, and for combining the measured deviation with candidate expectation deviation measurements for properties than other scale and position;

means for ranking each candidate character based on a total deviation measurement for each candidate character; and

,

means for identifying a best-ranked candidate based at least in part on a smallest total deviation measurement.

11. The system of claim 10 wherein:

the reference support lines includes a helpline and the baseline and the helpline and the baseline are parallel;

the helpline is a first predetermined perpendicular distance from the anchor point; and

the baseline is a second predetermined perpendicular distance from the anchor point.

12. The system of claim 10, further comprising means for establishing new reference support lines based on the temporary reference support lines associated with the best-ranked candidate character, and

wherein the total deviation measurement for each candidate character is further based at least in part on a deviation between an estimated candidate writing angle and an angle of an orthogonal projection point of a mass center of the curve to the baseline of the estimated support lines around the anchor point.

13. A tangible computer-readable storage medium containing instructions that when executed by a computing device cause the computing device to perform a method for identifying characters in a handwritten input manually provided by a user to an input device, the method comprising:

establishing a point on the touch-sensitive device;

establishing distances from the point to reference support lines;

receiving a handwritten user input via the touch-sensitive device;

identifying a set of candidate characters based on the handwritten user input;

estimating support lines for each of the candidate characters;

for each candidate character, measuring a deviation between a distance between the support lines and the point and a distance between the reference support lines and the point;

for each candidate character, measuring a distance between a baseline of the support lines and a baseline of the reference support lines;

ranking the candidate characters based on a deviation measurement for each candidate character, wherein the deviation measurement is based at least in part on;

the measured deviation between the distance between the support lines and the point and the distance between the reference support lines and the point, and

the measured distance between the baseline of the support lines and the baseline of the reference support lines; and

identifying a best-ranked candidate based at least in part on a smallest total deviation measurement.

14. The computer-readable storage medium of claim 13, wherein the estimated support lines each include an estimated candidate writing angle, and wherein the method further comprises establishing new reference support lines based on the orthogonal distance of the reference support lines and the candidate writing angle associated with the best-ranked candidate character.

15. The computer-readable storage medium of claim 13 further comprising:

receiving a second handwritten user input via the touch-sensitive device;

identifying a set of candidate characters for the second handwritten user input based on the second handwritten user input;

estimating support lines for each of the candidate characters for the second handwritten user input;

for each candidate character for the second handwritten user input, measuring a deviation between a distance between the support lines and the point and a distance between the new reference support lines and the point;

for each candidate character for the second handwritten user input, measuring an distance between a baseline of the support lines and a baseline of the new reference support lines;

ranking the candidate characters for the second handwritten user input based on a second total measurement for each candidate character, wherein the second total measurement is based at least in part on;

the measured deviation between the distance between the support lines and the point and the distance between the new reference support lines and the point, and

the measured distance between the baseline of the support lines and the baseline of the new reference support lines; and

identifying a best-ranked second candidate character based at least in part on the smallest second total deviation measurement.

16. The computer-readable storage medium of claim 15,

wherein the handwritten user input includes a curve,

wherein the estimated support lines each include an estimated candidate writing angle, and

wherein the total deviation measurement for each candidate character is further based at least in part on a deviation between the estimated candidate writing angle and an angle of an orthogonal projection point of a mass center of the curve to the baseline of the temporary support lines around the point.

17. The computer-readable storage medium of claim 15 further comprising:

receiving a selection of one of the candidate characters from the user; and

setting the new reference support lines as the candidate support lines for the selected candidate.

18. The computer-readable storage medium of claim 15 wherein:

the reference support lines include a helpline and the baseline and the helpline and the baseline are parallel;

the helpline is a first predetermined perpendicular distance from the point; and

the baseline is a second predetermined perpendicular distance from the point.

19. A tangible computer-readable storage medium containing instructions that when executed by a computing device cause the computing device to perform a method for identifying characters in a handwritten input manually provided by a user to an input device, the method comprising:

establishing distances from a point to reference support lines;

receiving a first handwritten user input via the input device;

identifying candidate characters based on the first handwritten user input;

estimating a candidate writing angle for the candidate characters;

associating candidate support lines that have candidate writing angles estimated for candidate characters and established distances from the point to the reference support lines;

identifying at least one deviation between the reference support lines and the candidate support lines for the candidate characters;

identifying a preferred candidate character based at least in part on one or more deviations between the reference support lines and the candidate support lines; and

establishing new reference support lines based on the candidate support lines associated with the preferred candidate character.

20. The computer-readable storage medium of claim 19 wherein:

the support lines includes a helpline and a baseline that are parallel;

the helpline is a first predetermined perpendicular distance from the point; and

the baseline is a second predetermined perpendicular distance from the point, and

wherein the handwritten user input comprises a single character associated with one of multiple, different languages.