Stroke Untangler for Overlapping Handwritten Input

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current text input methods on small screens, such as mobile devices, face challenges due to limited space, leading to decreased accuracy and speed, and existing handwriting recognition systems require predefined gestures or strokes, increasing complexity and computational overhead.

Innovation Solution

The Stroke Untangler system automatically untangles, segments, and composites overlapping handwritten strokes into characters without requiring user gestures or predefined strokes, using trained segmentation models to reduce computational overhead and facilitate real-time rendering and recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If handwriting recognition systems use predefined gestures or strokes for segmentation, then character recognition accuracy is improved, but device complexity and computational overhead increase

Engineering Contradiction:

Improvecharacter recognition accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically segmenting overlapping strokes through analysis of stroke characteristics (position, size, shape) without requiring predefined gestures or user actions. The segmentation is embedded within the recognition process itself, allowing the system to serve its own segmentation needs internally.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The segmentation function is extracted from the traditional predefined gesture framework and integrated directly into the handwriting recognition pipeline. By taking out the segmentation step and making it automatic based on stroke analysis, the system eliminates the need for separate gesture definitions while maintaining recognition accuracy.

Inventive Principle:

Principle #2Taking out (Extraction)

2Measurement precision

If handwriting recognition systems use predefined gestures or strokes for segmentation, then character recognition accuracy is improved, but computational overhead increases

Engineering Contradiction:

Improvecharacter recognition accuracyVSAvoidcomputational overhead

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary analysis of stroke characteristics (position, size, shape) to determine segmentation before full recognition processing. This preliminary action allows the system to prepare segmented character regions in advance, reducing the computational burden during the main recognition phase.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If users write characters with proper spacing and organization, then character recognition accuracy is improved, but ease of operation decreases

Engineering Contradiction:

Improvecharacter recognition accuracyVSAvoidwriting ease

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

Instead of requiring users to write with proper spacing and organization (traditional approach), the system inverts the approach by accepting随意 overlapping strokes and automatically performing the segmentation that would normally be the user's responsibility. This makes writing easier while maintaining recognition accuracy.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

Inventive Principle:

Principle #25Self-service

4Area of moving object

If screen size is decreased, then device portability is improved, but typing accuracy decreases

Engineering Contradiction:

Improvescreen areaVSAvoidtyping accuracy

Core Design Contradiction:

Area of moving objectVSMeasurement precision

Solution Approach 1:

The system transitions from the traditional two-dimensional keyboard interface to a free-form handwriting interface where characters can be written in overlapping strokes. This dimensional change allows users to express characters without being constrained by the limited screen real estate of small displays, thereby maintaining accuracy while improving portability.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP3084580B1User interface for overlapping handwritten text input

Publication Date: 2020.06.03 MICROSOFT TECHNOLOGY LICENSING LLC

Figure 1
Figure 2
Figure 3

AI summary

A "Stroke Untangler" composes handwritten messages from handwritten strokes representing overlapping letters or partial letter segments are drawn on a touchscreen device or touch-sensitive surface. These overlapping strokes are automatically untangled and then segmented and combined into one or more letters, words, or phrases. Advantageously, segmentation and composition is performed without requiring user gestures, timeouts, or other inputs to delimit characters within words, and without using handwriting recognition-based techniques to guide untangling and composing of the overlapping strokes to form characters. In other words, the user draws multiple overlapping strokes. Those strokes are then automatically segmented and combined into one or more corresponding characters. Text recognition of the resulting characters is then performed. Further, the segmentation and combination is performed in real-time, thereby enabling real-time rendering of the resulting characters in a user interface window. A related drawing mode enables entry of drawings in combination with the handwritten characters.