Slanted Handwriting Recognition via Block Rotation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional electronic devices face difficulties in accurately recognizing slanted handwriting inputs due to limitations in detecting separations between lines, leading to errors in text recognition.
Innovation Solution
The method involves preprocessing slanted handwriting by grouping strokes into blocks based on coordinate distances, determining the slope of each block, rotating the area corresponding to the blocks, and performing handwriting recognition on the rotated area to enhance recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional line separation based on horizontal writing assumption is used, then the system is simple, but recognition accuracy deteriorates for slanted handwriting
Solution Approach 1:
The patent applies preliminary action by performing preprocessing operations (grouping strokes into blocks, calculating slopes, rotating the writing area) before the main handwriting recognition process. This prepares the slanted handwriting data in advance to match the horizontal assumption of conventional recognition algorithms, thereby improving accuracy without requiring changes to the core recognition system.
Solution Approach 2:
The patent segments the handwriting input by grouping strokes into multiple blocks based on coordinate distances and spatial relationships. This segmentation allows different blocks to be processed independently with their own slope calculations and rotations, enabling accurate handling of complex slanted handwriting while maintaining system manageability.
2Measurement precision
If preprocessing for slanted handwriting is implemented, then recognition accuracy improves, but processing time increases
Solution Approach 1:
By segmenting handwriting into blocks and processing each block independently with targeted rotations, the system avoids unnecessary preprocessing of the entire writing area. This selective approach reduces overall processing time while maintaining high accuracy for slanted handwriting.
Solution Approach 2:
The patent dynamically changes parameters (slope angles, rotation degrees) based on the actual characteristics of each handwriting block. This adaptive parameter adjustment ensures that preprocessing is applied only to the extent necessary, optimizing the balance between accuracy improvement and processing time.
Data Source
AI summary
An electronic device and method are disclosed. The electronic device includes a touch-sensitive display, a memory and a processor. The processor implements the method, including: detect a written input including a plurality of strokes through the display, group the plurality of strokes into a first group and a second group based on respective coordinates of each of the plurality of strokes, group first strokes included in the first group into a plurality of blocks, based on a distance between respective coordinates of each of the first strokes, determine a slope for each of the plurality of blocks, rotate an area corresponding to the first group based on the determined slope, execute handwriting recognition on the first strokes based on the rotated area, and displaying a result of the handwriting recognition on the display.