Recognizing handwriting input using rotatable support lines

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 a 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 the established distances from the 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 other than 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.

A non-transitory computer-readable 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.

A non-transitory computer-readable 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.