Dynamic Threshold Adjustment for Handwritten Stroke Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Handwritten character recognition systems face challenges in accurately distinguishing between strokes based on distance and time variations, leading to inconsistent recognition of user intentions.
Innovation Solution
An editing program that allows users to easily change distance and time thresholds via an input interface, enabling recognition of strokes as intended by calculating distances and time differences between strokes and adjusting thresholds accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fixed distance and time thresholds are used for stroke recognition, then the recognition process is simple and fast, but the recognition accuracy does not align with user intentions due to variations in handwriting
Solution Approach 1:
The patent makes the distance and time thresholds dynamic rather than fixed. The system automatically adjusts thresholds based on the specific handwriting characteristics being analyzed, allowing the recognition criteria to adapt to variations in user handwriting styles while maintaining operational simplicity through automated adjustment mechanisms
Solution Approach 2:
The system changes the threshold parameters dynamically based on the handwriting data being processed. By analyzing the distribution of distances and time intervals in the specific handwriting sample, the system optimizes the threshold values to better distinguish between intentional separations and natural variations, thereby improving recognition accuracy without requiring manual calibration
2Adaptability or versatility
If multiple fixed thresholds are used to handle stroke variations, then recognition covers more cases, but the system becomes complex and difficult to adjust for different users
Solution Approach 1:
The system performs self-adjustment of thresholds by automatically analyzing the handwriting characteristics and optimizing the threshold values without user intervention. The algorithm examines the distribution of distances and time intervals in the handwriting data and autonomously determines appropriate threshold settings, eliminating the need for users to manually configure multiple thresholds while still achieving high adaptability to different handwriting styles
Solution Approach 2:
The system incorporates feedback mechanisms that analyze the results of stroke recognition and continuously optimize the threshold values. By monitoring recognition outcomes and adjusting thresholds based on the specific characteristics of each user's handwriting, the system achieves high adaptability while maintaining operational simplicity through automated feedback-driven optimization
Data Source
AI summary
A non-transitory computer-readable storage medium stores an editing program including a set of program instructions for an information processing apparatus comprising a controller and an input interface. The set of program instructions, when executed by the controller, causes the information processing apparatus to perform: acquiring a plurality of strokes inputted via the input interface; calculating a distance between two strokes of the acquired plurality of strokes; in response to determining that the calculated distance is shorter than a distance threshold, recognizing the two strokes as a same item; in response to determining that the calculated distance is longer than or equal to the distance threshold, recognizing the two strokes as separate items; and changing the distance threshold based on input via the input interface.