Dimension Line Recognition for Raster-to-Vector Drawing Conversion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for converting raster data to vector data in design diagrams require manual input of dimension values and lines, leading to increased operating time and operational errors.

Innovation Solution

A drawing assistance device and method that utilizes machine learning algorithms to detect dimensional information, arrows, and lines, generating dimension lines and guidelines to assist operators in converting raster data to vector data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual input of dimension values and lines is used, then the conversion from raster data to vector data can be performed, but the operating time increases and operational errors increase

Engineering Contradiction:
Improveconversion speedVSAvoidoperational accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent replaces the manual mechanical input process with an automated optical recognition system. The recognition unit automatically detects dimension values, arrows, and lines from raster images using image processing algorithms, eliminating the need for manual transcription and reducing both time and errors.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the raster image data to automatically provide its own dimension information through recognition. The dimension information is extracted directly from the image without requiring external manual input, making the process self-sufficient and efficient.

Inventive Principle:
Principle #25Self-service

2Loss of time

If automated recognition is implemented, then operating time decreases, but system complexity increases

Engineering Contradiction:
Improveoperating timeVSAvoidsystem complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The recognition unit is designed with multi-functionality, capable of simultaneously recognizing dimension values, arrows, and lines within a single integrated system. This universal approach consolidates multiple functions into one module, reducing overall system complexity while maintaining automation benefits.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent segments the complex recognition task into distinct functional components: dimension value recognition, arrow detection, and line detection. Each component handles a specific aspect of the recognition process, making the overall system more manageable and easier to implement despite the automated nature.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4453773B1Drawing assistance device and drawing assistance method
Publication Date: 2026.02.04 AMADA CO LTD
  • EP4453773B1 patent drawingFigure 1
  • EP4453773B1 patent drawingFigure 2
  • EP4453773B1 patent drawingFigure 3

AI summary

A drawing assistance device 1 acquires image data of a design diagram to detect dimensional information drawn on the image data, detects arrows drawn on the image data, detects a line drawn on the image data, combines the arrows and the line based on positions of the arrows and a position of the line to generate a dimension line, detects a dimension value corresponding to a position of the dimension line from the dimensional information so as to assign the detected dimension value to the dimension line, generates guidelines indicating positions of ends of the dimension line, superposes the guidelines on the image data to display the guidelines on an editing screen, and outputs digital data of the design diagram drawn by the operator on the editing screen on which the guidelines are displayed.