Spatial Figure–Character Association in Digitized Drawings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies cannot automatically identify associations between figures and character strings in analog drawings converted to images, limiting their reuse and data reduction potential.
Innovation Solution
An information processing apparatus that acquires images containing figures and character strings and generates association information based on positional relationships, such as distance and direction, between the figures and character strings, using machine-learned predictive models for accurate association detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional OCR and object recognition technology is used to convert analog drawings to digital images, then character strings can be converted to data and specific objects can be recognized, but the association between figures and character strings cannot be identified
Solution Approach 1:
The patent introduces a new dimension of analysis by considering the spatial positional relationship between figures and character strings in the image. Instead of treating them as independent elements, the system analyzes their relative positions, distances, and orientations to infer associations, thereby recovering information that was lost in conventional conversion processes.
Solution Approach 2:
The patent uses the spatial positional relationship as an intermediary to bridge figures and character strings. By analyzing metrics such as distance, direction, and relative position between these elements, the system indirectly infers their semantic associations without requiring direct semantic understanding or manual annotation.
2Measurement precision
If manual methods are used to identify associations between figures and character strings, then accurate association information can be obtained, but the process requires significant time and human intervention
Solution Approach 1:
The system performs self-service by automatically analyzing the spatial relationships between figures and character strings using image processing algorithms. The computer independently calculates distances, directions, and positional relationships to determine associations without requiring human intervention, thereby eliminating time loss while maintaining accuracy through objective mathematical measurements.
3Productivity
If simple distance-based criteria are used to determine associations, then processing is fast and simple, but accuracy decreases when figures and character strings are far apart or have complex relationships
Solution Approach 1:
The patent employs multiple parameters to determine associations, including not only distance but also direction, relative position, and orientation of character strings. By changing from a single parameter (distance) to multiple parameters (distance, direction, position, orientation), the system maintains processing speed through algorithmic efficiency while significantly improving accuracy for complex spatial relationships.
Solution Approach 2:
The association determination uses a composite approach combining multiple spatial relationship metrics. Rather than relying on a single criterion, the system integrates distance, direction, and positional information to form a comprehensive assessment of association, similar to how composite materials combine different properties to achieve superior performance.
Data Source
AI summary
An information processing apparatus (10) includes a controller (11) that acquires an image containing a figure and a character string and generates association information indicating an association between the figure and the character string based on a positional relationship between the figure and the character string in the image.