Handwriting Search Module Using Stroke Feature Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic devices with touchscreen displays are not suitable for business use due to inefficiencies in searching handwritten documents, often failing to find intended information or retrieving unintended data during handwriting searches.
Innovation Solution
An electronic device equipped with a touchscreen display, a search module, and a display processing module that stores and searches handwriting information as time-series data, allowing for precise similarity-based searches and adjustable reference values to improve search accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If handwriting information is stored and searched using simple locus similarity comparison, then the search process is fast and simple, but the search accuracy is poor leading to unintended results
Solution Approach 1:
The patent segments the handwriting stroke data into multiple feature components including locus, pressure, tilt angle, and time series information. By dividing the complex handwriting recognition task into these separate feature dimensions, the system can perform accurate similarity comparisons without excessive computational complexity, resolving the contradiction between search speed and accuracy.
Solution Approach 2:
The patent changes the parameters used for similarity comparison from simple locus data to multiple parameters including pressure, tilt angle, and time series information. This parameter expansion enables accurate distinction between similar and dissimilar handwriting strokes, improving search accuracy while maintaining reasonable search speed through efficient comparison algorithms.
2Ease of operation
If the reference value for similarity comparison is fixed, then the search process is simple and fast, but it cannot adapt to different search requirements leading to missed or false results
Solution Approach 1:
The patent makes the reference value dynamic by allowing users to adjust it according to different search requirements. The system provides multiple reference values (e.g., high, medium, low thresholds) that can be selected based on the specific search task, enabling the same search system to adapt to various accuracy and speed requirements without changing the fundamental simplicity of the search process.
Solution Approach 2:
The system incorporates feedback mechanisms where users can review search results and adjust the reference value accordingly. This feedback loop allows the system to learn from user interactions and optimize the reference value selection, maintaining ease of operation while improving adaptability to different search scenarios.
3Device complexity
If basic stroke data is used for handwriting storage, then the device complexity is low, but the search reliability is insufficient causing intended handwriting to be missed
Solution Approach 1:
The patent segments the handwriting data into multiple independent feature components (locus, pressure, tilt angle, time series). This segmentation allows the system to maintain relatively simple data structures for each individual feature while achieving high search reliability through the combination of multiple features, avoiding the need for overly complex integrated data structures.
Solution Approach 2:
The patent implements a nested data structure where multiple feature datasets are organized in a hierarchical manner. The basic stroke data contains nested information about pressure, tilt angle, and time series within each stroke record. This nesting approach increases search reliability by providing comprehensive feature data while keeping the overall data structure manageable and not excessively complex.
Data Source
AI summary
According to one embodiment, a device includes a search module configured to search handwriting information stored in a storage medium for a first handwriting information part whose degree of a similarity with a specific handwriting information part specified as a search key is greater than or equal to a reference value, the handwriting information includes a plurality of stroke data corresponding to a plurality of strokes, and a display processing module configured to display, on a touchscreen display, one or more thumbnail corresponding to handwriting information includes the first handwriting information part and a first user interface for changing the reference value.