Flowchart Image Conversion via Path Grouping and Likelihood Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to efficiently convert images of flowcharts into editable, computer-readable formats, limiting the ability to manipulate and edit flowchart content without manual re-creation.
Innovation Solution
A method and system that reads an image of a flowchart, identifies paths, groups them, calculates likelihood scores for flowchart elements, selects a primary group for each path based on maximum likelihood scores, and generates a flowchart object for editable representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic flowchart conversion from images is implemented, then productivity is improved, but measurement precision deteriorates due to inaccurate path identification and grouping
Solution Approach 1:
The patent segments the flowchart image into multiple paths by detecting continuous lines and grouping them into distinct segments. Each path is then independently processed to identify flowchart elements, which improves both the speed of conversion and the accuracy of element identification by avoiding the complexity of processing the entire image at once.
Solution Approach 2:
The patent introduces likelihood scores as an intermediary mechanism to evaluate and select the most probable flowchart element for each path. This intermediary scoring system allows the system to automatically determine element types with confidence, resolving the precision issue by using statistical probability rather than rigid deterministic rules.
2Adaptability or versatility
If multiple paths are grouped into multiple groups, then adaptability is improved, but device complexity increases due to likelihood score calculations and primary group selections
Solution Approach 1:
The patent implements dynamic grouping where paths can belong to multiple groups simultaneously, and the system dynamically selects the primary group based on likelihood scores. This dynamic approach allows the same grouping mechanism to adapt to different flowchart structures and complexities without requiring separate algorithms for different scenarios.
Solution Approach 2:
The patent uses likelihood scores as a parameter to determine the primary group for each path. By changing the selection criterion from fixed rules to probabilistic scoring, the system can handle various flowchart configurations uniformly, reducing the need for multiple specialized algorithms while maintaining high adaptability.
3Measurement precision
If likelihood scores are calculated for all groups, then measurement precision is improved, but use of energy increases due to computational requirements
Solution Approach 1:
The patent calculates likelihood scores for all possible groups that a path could belong to, even though only one primary group is ultimately selected. This excessive calculation ensures that no potential element identification is missed, maintaining high precision while the computational cost is managed through efficient algorithms that process paths in sequence rather than all at once.
Data Source
AI summary
A method for image processing. The method includes: reading an image of a flowchart; identifying, within the image, a plurality of paths corresponding to the flowchart; grouping the plurality of paths into a plurality of groups including a first group and a second group; calculating a plurality of likelihood scores corresponding to flowchart elements for each of the plurality of groups; identifying a first path belonging to the first group and the second group; and selecting the first group as the primary group for the first path based on a maximum likelihood score for the first group and a maximum likelihood score for the second group; and generating a flowchart object based on the primary group for the first path.