Electronic Device Writing Data Generation Using Gesture Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic devices face challenges in accurately generating writing data due to camera shake, slippery surfaces, and recognition algorithm limitations, leading to distorted user inputs and unintended data generation.
Innovation Solution
An apparatus and method that utilize attribute information, including position, size, and feature data, to generate writing data by extracting and processing user input through a touch screen, employing a gesture analysis program to determine the type and attributes of the writing data, and correcting inputs to match intended user inputs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the electronic device uses pre-stored normalized writing data for recognition, then the recognition process is simplified and faster, but the accuracy of distorted user input recognition deteriorates
Solution Approach 1:
The system performs preliminary actions by detecting attribute information (position, size, shape) before full recognition, and provides candidate writing data in advance. This allows the system to prepare multiple potential matches based on geometric attributes, then select the best match after distortion correction, maintaining both speed and accuracy.
Solution Approach 2:
The system implements feedback by providing a list of candidate writing data to the user and allowing selection or correction. The distortion correction process continuously refines the recognition based on feedback from attribute matching, improving accuracy while maintaining efficient processing through iterative refinement.
2Device complexity
If the electronic device relies on basic recognition algorithms, then the device complexity is reduced, but the accuracy of determining user intent deteriorates
Solution Approach 1:
The recognition process is segmented into distinct stages: attribute information detection (position, size, shape), candidate generation based on attributes, distortion correction, and final selection. This segmentation allows each stage to use appropriately complex methods without overwhelming the overall system complexity.
Solution Approach 2:
Attribute information serves as an intermediary between the simple input detection and complex intent determination. By first extracting geometric attributes and using them to generate candidates, the system bridges the gap between simple detection algorithms and accurate intent recognition without requiring overly complex direct recognition algorithms.
3Device complexity
If the electronic device processes handwritten input directly without attribute analysis, then the processing steps are reduced, but the accuracy of generating intended writing data deteriorates
Solution Approach 1:
The system performs preliminary attribute analysis (position, size, shape detection) before generating writing data. This preliminary action extracts key geometric features that guide the subsequent candidate generation and distortion correction processes, improving accuracy without adding excessive processing steps.
Solution Approach 2:
The system applies different processing qualities to different aspects of the input: precise geometric attribute detection for position and shape, candidate generation based on local attribute matching, and targeted distortion correction. This local quality approach ensures high accuracy in critical areas without uniformly increasing complexity across all processing steps.
Data Source
Figure 1A~1B
Figure 2
Figure 3
AI summary
An apparatus and a method for generating writing data by obtaining data generation information in an electronic device are provided. A method for inputting data in the electronic device includes displaying an attribute of the writing data by detecting a first input, checking a type of the writing data by detecting a second input, and determining output writing data, and displaying the output writing data according to the attribute of the writing data. The attribute of the writing data includes at least one of a position of the writing data to generate, a length, an angle, and a vertex of a line of the writing data.