Image Processing for Plate Position and Angle Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing laser processing systems face inaccuracies in determining the position and angle of plate materials due to manual placement errors or vibrations, leading to material waste and inefficient processing.

Innovation Solution

An image processing device that processes captured images to generate expected data for comparison with actual data, allowing accurate detection and correction of object placement through a simple configuration without the need for additional lighting or position measuring units.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a lighting unit and position measuring unit are provided to improve detection rate, then detection accuracy is improved, but device complexity and cost increase

Engineering Contradiction:
Improvedetection accuracyVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a virtual model (copy) of the object with known three-dimensional reference data, including expected two-dimensional image data from multiple viewpoints. This virtual copy is then compared with actual captured images to determine object position and angle, eliminating the need for complex lighting units and position measuring units while maintaining detection accuracy

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical/optical measurement system (lighting unit and position measuring unit) with an image processing system that uses computational methods. The system substitutes physical measurement hardware with software-based image analysis and comparison algorithms, reducing device complexity while achieving the same measurement function

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

2Measurement precision

If a lighting unit and position measuring unit are provided to improve detection rate, then detection accuracy is improved, but device cost increases

Engineering Contradiction:
Improvedetection accuracyVSAvoiddevice cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent creates a virtual model (copy) of the object with known three-dimensional reference data, including expected two-dimensional image data from multiple viewpoints. This virtual copy is then compared with actual captured images to determine object position and angle, eliminating the need for complex lighting units and position measuring units while maintaining detection accuracy

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent uses standard imaging devices (cameras) that are relatively inexpensive and widely available, replacing expensive specialized measurement hardware. The system uses multiple standard images taken from different viewpoints rather than a single expensive position measuring unit, achieving better accuracy at lower cost

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

3Ease of operation

If the plate material is manually placed on the table without a guide, then ease of operation is improved, but position accuracy deteriorates

Engineering Contradiction:
Improveease of operationVSAvoidposition accuracy
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The patent captures images of the actually placed object, compares them with the virtual model to detect position and angle deviations, and uses this feedback information to correct the nesting arrangement. This allows manual placement without guides while achieving accurate positioning through image-based feedback and automatic correction

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent performs preliminary nesting calculations based on the object model before actual placement, then uses image comparison to detect deviations from the expected position. The system prepares the expected two-dimensional image data in advance, allowing quick comparison and correction after manual placement, maintaining both ease of operation and position accuracy

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS12620117B2Image processing device, non-transitory computer-readable storage medium, and image processing method
Publication Date: 2026.05.05 MITSUBISHI ELECTRIC CORP
  • US12620117B2 patent drawing
  • US12620117B2 patent drawing
  • US12620117B2 patent drawing

AI summary

An image processing device includes an object detecting unit that processes captured image data representing a captured image, which is an image including an object or detection target and a background of the object, to generate processed image data representing a processed image, which is an image in which the object is detected; an expected-data generating unit that generates expected data representing an expected image, which a virtual image in which the object represented by an attribute is placed at a position on the background on the basis of object data representing the position of the object and background data representing the background; and a detection-result determining unit that compares the processed image data and the expected data to determine whether or not the object is detected correctly in the processed image data.