Rotating Support Lines for Handwriting Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for recognizing handwritten input on touch-sensitive devices are limited by the requirement for constrained orientation, which restricts user input flexibility, especially in applications like vehicle center consoles where both driver and passenger need to input characters freely.
Innovation Solution
A system that uses rotating support lines anchored at a point, allowing for recognition of handwritten input regardless of orientation by establishing a baseline, helpline, and anchor point, with candidate characters ranked based on deviations from these lines, enabling accurate recognition across various angles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fixed horizontal lines are used to constrain handwritten input orientation, then character case differentiation accuracy is improved, but user input flexibility and accessibility are worsened
Solution Approach 1:
The patent applies the dynamics principle by transforming the static fixed horizontal lines into dynamic support lines that rotate around an anchor point. The support lines adapt their orientation based on the user's writing angle, allowing the system to maintain accurate character case differentiation regardless of whether the user writes horizontally, vertically, or at any intermediate angle. This dynamic adjustment resolves the contradiction by preserving measurement precision across multiple orientations while significantly improving user input flexibility.
Solution Approach 2:
The patent employs parameter changes by modifying the orientation parameter of the support lines. Instead of maintaining a fixed horizontal orientation (0 degrees), the support lines rotate to match the user's writing angle parameter. The system calculates the writing angle based on the distribution of touch points and adjusts the support lines accordingly, enabling accurate character recognition across different writing orientations while maintaining case differentiation accuracy.
2Measurement precision
If constrained writing orientation is enforced, then character recognition accuracy is improved, but device deployability in multi-user environments is worsened
Solution Approach 1:
The patent applies universality by designing a support line system that serves multiple functions and orientations. The support lines can accommodate writing from any angle around the anchor point, making the device universally accessible to multiple users in different positions (e.g., driver and passenger in a vehicle). This multi-functional capability allows the same device to maintain high character recognition accuracy regardless of which user is writing or from what angle, thereby improving deployability in multi-user environments.
Solution Approach 2:
The patent transitions from a one-dimensional fixed horizontal orientation to a two-dimensional rotational system. By introducing the angular dimension around the anchor point, the support lines can orient themselves in any direction within the plane. This dimensional expansion allows the device to accept input from multiple users at different angles while maintaining recognition accuracy, thus resolving the deployability constraint.
3Device complexity
If fixed support lines are used, then system complexity is reduced, but recognition accuracy across orientations is worsened
Solution Approach 1:
The patent applies preliminary action by pre-establishing an anchor point and a rotational framework for the support lines before user input occurs. The system prepares the rotational mechanism and anchor point configuration in advance, so that when the user writes at any angle, the support lines can immediately rotate to the correct orientation without complex real-time calculations. This preliminary setup reduces system complexity while enabling accurate recognition across all orientations.
Data Source
AI summary
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.