X-ray Inspection Algorithm Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional inspection apparatuses require human intervention to select the optimal image processing algorithm for foreign matter detection, which can be time-consuming and may not result in the best selection.

Innovation Solution

An inspection apparatus that automatically evaluates and selects the optimal image processing algorithm by using a storage unit to store combined algorithms, an acquisition unit to acquire reference transmission images, an evaluation unit to assess detection accuracy, and a setting unit to set the selected algorithm based on evaluation results, eliminating the need for human intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If an operator manually selects an image processing algorithm from multiple extracted algorithms, then the selection process allows human judgment and flexibility, but it consumes time and labor while potentially failing to select the optimal algorithm

Engineering Contradiction:
Improvedetection accuracyVSAvoidselection time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary evaluation of multiple image processing algorithms using evaluation images before actual inspection. The evaluation unit pre-assesses detection accuracy for each algorithm, and the setting unit pre-selects the optimal algorithm, so that when inspection is needed, the best algorithm is already ready without requiring manual selection during operation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The inspection apparatus performs self-evaluation and self-selection of the optimal image processing algorithm. The evaluation unit automatically assesses detection accuracy by processing evaluation images through multiple algorithms, and the setting unit automatically selects and sets the algorithm with the highest evaluation result, eliminating the need for operator intervention in the selection process.

Inventive Principle:
Principle #25Self-service

2Reliability

If multiple image processing algorithms are extracted and displayed for operator selection, then the system provides choices based on foreign-matter detection characteristics, but the manual selection process reduces productivity and may not achieve optimal detection

Engineering Contradiction:
Improvealgorithm selection reliabilityVSAvoidinspection throughput
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The inspection apparatus performs self-evaluation and self-selection of the optimal image processing algorithm. The evaluation unit automatically assesses detection accuracy by processing evaluation images through multiple algorithms, and the setting unit automatically selects and sets the algorithm with the highest evaluation result, eliminating the need for operator intervention in the selection process.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system uses evaluation images to assess the detection accuracy of each image processing algorithm and feeds back this evaluation information to automatically determine the optimal algorithm. This feedback mechanism ensures that the algorithm with the highest detected foreign matter accuracy is selected, improving both reliability and productivity by eliminating manual selection.

Inventive Principle:
Principle #23Feedback

3Productivity

If the system automatically evaluates and sets the optimal image processing algorithm, then selection time is reduced and productivity increases, but the system requires additional components for evaluation and automatic setting

Engineering Contradiction:
Improvealgorithm selection efficiencyVSAvoidsystem structure
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The evaluation unit and setting unit serve multiple functions: they evaluate detection accuracy using test pieces, assess multiple algorithms simultaneously, and automatically select the optimal algorithm for future inspections. This multi-functionality justifies the added components by providing comprehensive algorithm management capabilities that improve overall system productivity.

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

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The apparatus objectively evaluates and automatically sets the optimal image processing algorithm, enhancing detection accuracy and efficiency by reducing reliance on human judgment.

Implementation Method 1

a transmission image obtaining unit configured to acquire, as a transmission image, an image obtained by transmitting X-rays through the article

Methodology Applied
Scientific EffectX-ray transmission: X-Ray

Data Source

PatentEP3764088B1Inspection apparatus
Publication Date: 2023.08.30 ISHIDA CO LTD
  • EP3764088B1 patent drawingFigure 1
  • EP3764088B1 patent drawingFigure 2
  • EP3764088B1 patent drawingFigure 3

AI summary

An X-ray inspection apparatus (1) includes a storage unit (21) configured to store therein a plurality of image processing algorithms; an acquisition unit (22) configured to acquire, as a reference transmission image, a transmission image obtained by transmitting electromagnetic waves through an article (A) to which a foreign matter is attached or a synthesized transmission image; an evaluation unit (24) configured to evaluate detection accuracy of the foreign matter for each image processing algorithm based on an evaluation image obtained by processing the reference transmission image with the image processing algorithms stored in the storage unit; and a setting unit (25) configured to set at least one of the image processing algorithms as an image processing algorithm selected in advance based on evaluation in the evaluation unit.