Handwritten Stroke Recognition on Interactive Key Layouts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems for disambiguating stroke-typed input on virtual keyboards face challenges in accurately recognizing handwritten strokes due to ambiguity in input, requiring unique recognition systems and engines for each type of input.
Innovation Solution
A system and method that utilize a non-transitory computer readable medium configured to detect handwritten strokes on an interactive key layout, characterize them by determining reference points, assign probability scores to candidate characters, and apply a language model for recognition, allowing for the recognition of sequences of characters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional disambiguation techniques are used for stroke-typed input, then reasonable success in accurately disambiguating input is achieved, but unique recognition systems or engines must be produced for stroke-typing
Solution Approach 1:
The patent combines handwriting recognition technology with stroke-typing disambiguation by integrating multiple disambiguation techniques (stroke path characteristics, language models, lexica) into a unified recognition system that processes both handwriting and stroke-typing input through the same engine, eliminating the need for separate recognition systems
Solution Approach 2:
The recognition system is designed to handle multiple input types (handwriting and stroke-typing) using the same engine and processing pipeline, making the system universal and multi-functional rather than requiring specialized engines for each input type
2Productivity
If stroke-like input is used on virtual keyboards, then increased typing speed is achieved, but ambiguity in input increases requiring disambiguation processing
Solution Approach 1:
The system uses language models and lexica to provide feedback during disambiguation processing, analyzing stroke path characteristics and comparing them against expected patterns to determine the most likely intended input, thereby resolving ambiguity while maintaining typing speed
Solution Approach 2:
The system changes parameters such as bend, speed, and direction of the stroke path to disambiguate input, using these characteristics to differentiate between intended keys and accidentally struck keys during rapid stroke-typing
Data Source
AI summary
A system, method and computer program product for use in recognizing content associated with handwritten stroke input to a computing device is provided. The computing device is connected to an input interface. A user is able to provide input by applying pressure to or gesturing above the input interface using a finger or an instrument such as a stylus or pen. The computing device has an input management system for recognizing content defined by the input. The input management system is configured to detect input of a handwritten stroke with respect to the interactive key layout, characterize the detected handwritten stroke by a reference stroke by determining a sequence of reference points associated with a sequence of interactive keys of the interactive key layout, assign probability scores to candidate characters, and cause recognition of sequences of characters by applying a language model in accordance with the assigned probability scores.