Overlapping Handwritten Character Recognition on Touchscreens
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing touch-sensitive devices struggle with recognizing handwritten characters that overlap, requiring users to wait between inputs or use horizontal offsets, which limits efficiency on devices with small input areas.
Innovation Solution
A method that receives and processes touch-based input by determining confidence levels for character recognition, allowing overlapping strokes to be recognized without waiting, and altering the graphical representation based on confidence thresholds, enabling continuous input on small devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional character recognition methods are used with touch-sensitive screens, then character differentiation is achieved through single-stroke drawing and timeouts, but user input efficiency is reduced and input area utilization is limited
Solution Approach 1:
The patent segments the touch input area into multiple overlapping character recognition zones. Each zone independently processes strokes for character recognition, allowing simultaneous input in different areas without requiring timeouts between characters. This segmentation enables continuous input while maintaining accurate character differentiation.
Solution Approach 2:
The patent introduces vertical stacking of characters through overlapping strokes in the same horizontal space. By utilizing the vertical dimension and temporal sequencing of strokes, the system recognizes characters written on top of each other without requiring horizontal separation or timeouts, thus improving input efficiency.
2Area of stationary object
If horizontal offset between characters is used for differentiation, then character recognition accuracy is maintained, but input area utilization is reduced
Solution Approach 1:
The input area is divided into multiple overlapping recognition zones that can independently process strokes. This allows characters to be written in the same horizontal space at different vertical positions or times, maximizing area utilization while maintaining differentiation through spatial segmentation rather than requiring horizontal offsets.
Solution Approach 2:
Different regions of the touch screen are assigned different recognition characteristics based on local stroke patterns. The system analyzes the local quality of strokes (vertical position, stroke sequence, pressure patterns) to differentiate characters, allowing efficient use of limited input area without sacrificing recognition accuracy.
3Speed
If timeout period is implemented between characters, then character differentiation is achieved, but input speed is limited
Solution Approach 1:
The system performs preliminary stroke analysis and character recognition continuously as strokes are input, without waiting for timeouts. By pre-processing and analyzing stroke patterns in real-time, the system can confidently identify characters even when written overlappingly, maintaining both speed and accuracy without requiring pause periods.
Solution Approach 2:
The system provides real-time feedback by displaying recognized characters as they are written and allowing users to correct misrecognitions. This feedback mechanism enables continuous input at high speed while maintaining high accuracy through iterative refinement of recognition results based on user interaction.
Data Source
AI summary
Techniques described herein may recognize handwritten characters that are written at least partially over the top of one another that are input to a computing device. The handwritten characters may be formed of one or more strokes. A user may write characters or parts of words over approximately the same area of graphical user interface (i.e., on top of each other) without having to wait for a timeout between character input and without having to select a button or provide another input indicating the character is complete before entering input for another character. Once a character is at least partially recognized, a graphical indication corresponding to the user input displayed on a screen may be altered. Such alterations may include fading or changing size or location of the graphical indication.