Technical Drawing Data Extraction Using View-Annotation Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting technical data in technical drawings are inefficient and lack the ability to accurately identify and associate views and annotations, hindering the conversion to numerical models for manufacturing and defect detection.
Innovation Solution
A computer-implemented method using neural networks for view-splitting, annotation-detection, and text-recognition modules to identify and associate views, annotations, and characters in technical drawings, creating a graph representation for reconstructing a numerical model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual conversion of technical drawings to numerical models is performed, then accuracy can be maintained through human expertise, but productivity is severely reduced due to time-consuming manual processes
Solution Approach 1:
The patent segments the technical drawing analysis into distinct modules: view identification module, annotation detection module, text recognition module, and graph representation module. Each module handles a specific aspect of the conversion process, enabling parallel processing and improving overall productivity while maintaining accuracy through specialized processing for each task.
Solution Approach 2:
The patent introduces an intermediary graph representation structure that bridges the gap between image-based technical drawings and numerical models. This graph structure serves as a mediator that organizes detected views, annotations, and their relationships in a structured format that can be easily converted to numerical models, improving both speed and accuracy.
2Productivity
If simple text recognition is applied to technical drawings, then processing speed increases, but the ability to accurately identify and associate views with their annotations deteriorates
Solution Approach 1:
The graph representation acts as an intermediary structure that preserves the relationships between views and annotations. By organizing detected elements into a graph where nodes represent views, annotations, and text, and edges represent their associations, the system maintains complete information about relationships while enabling efficient processing through structured data organization.
Solution Approach 2:
The patent transforms the two-dimensional spatial relationships in technical drawings into a graph-based dimensional representation. This dimensional transformation allows the system to capture complex associations between views and annotations in a structured format that is easier to process computationally while preserving all relationship information.
3Measurement precision
If comprehensive analysis of all drawing elements is performed, then detection accuracy improves, but device complexity and computational requirements increase
Solution Approach 1:
The patent divides the complex analysis task into separate functional modules: view identification, annotation detection, text recognition, and graph construction. Each module focuses on a specific aspect of the analysis, reducing the complexity of individual components while achieving comprehensive detection accuracy through their coordinated operation.
Solution Approach 2:
The graph representation structure automatically organizes and associates detected elements based on their spatial and semantic relationships. The system uses the detected information to build the graph structure itself, where nodes and edges are created based on the detected views, annotations, and their relationships, reducing the need for additional complex processing logic.
Data Source
AI summary
A technical data detection method in a technical drawing image. The technical drawing includes a view of a technical object and a technical annotation. The method includes identifying one or more views in the technical drawing. The method includes identifying one or more technical annotations in each view. The method includes identifying characters in each technical annotation. The method includes determining a graph representation of each view. The graph representation includes nodes each corresponding to a classification of pixels in the view into a semantic class and edges each connects two nodes either if the two nodes represent neighboring pixels or if the two nodes represent pixels distant from each other below a threshold. The method includes, for each identified view, using the graph topology and the identified characters to associate nodes corresponding to the dimension-related symbol or dimension classes to nodes corresponding to the geometry class.