Handwriting Recognition Candidate Ranking for Math Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computer algebra systems lack a common standard for inputting mathematical notation, leading to confusion and inefficiency due to diverse and complex input methods, which can be difficult for users to master, especially for beginners, and pose challenges in localization and input speed.
Innovation Solution
A handwriting recognition system that processes user input via a graphical user interface, using a recognizer to rank candidates and adjust rankings based on application-level criteria, displaying the most likely intended input for efficient mathematical expression entry.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If handwriting recognition with candidate ranking is used, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The patent introduces a recognizer as an intermediary component between the handwriting input device and the application program. This recognizer processes handwriting input, generates candidate interpretations, and ranks them before passing to the application. This mediator handles the complexity of interpretation algorithms, keeping the main application simple while enabling intuitive handwriting input.
Solution Approach 2:
The system segments the input processing into distinct modules: handwriting input device, recognizer with candidate generation, candidate ranking system, and application program. This segmentation allows each component to specialize in specific tasks, improving overall ease of operation while distributing complexity across manageable segments rather than concentrating it in one complex system.
2Manufacturing precision
If application-level criteria scanning is implemented, then manufacturing precision is improved, but loss of time increases
Solution Approach 1:
The recognizer performs preliminary action by generating and ranking multiple candidate interpretations before the application program processes them. This preliminary candidate generation and ranking filters out unlikely interpretations early, so when application-level criteria scanning occurs, it operates on a pre-filtered, high-probability candidate set, reducing the time needed to achieve high recognition accuracy.
Solution Approach 2:
The system performs partial action by not requiring exhaustive scanning of all possible interpretations. Instead, it generates a limited set of top-ranked candidates and scans only those against application-level criteria. This partial scanning approach achieves sufficient recognition accuracy without the time cost of exhaustive search through all possible interpretations.
Data Source
AI summary
Systems and methods for use in handwriting recognition in computer algebra are provided. One disclosed method includes receiving handwriting input from a user via a handwriting input device, the handwriting input representing a mathematical expression. The method further includes, at a recognizer, processing the handwriting input to recognize a plurality of candidates and ranking the plurality of candidates to form initial candidate data. The method may further include, at an application program, scanning the plurality of candidates for segments that match application-level criteria, and adjusting a rank of one or more of the plurality of candidates based on the matching, to form a processed candidate list. The method may further include displaying the processed candidate list via a graphical user interface.