Circuit Board Mounting Inspection With Complementary-Color Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image processing devices fail to execute mounting inspections of components on circuit boards with precision using captured images.

Innovation Solution

The device obtains three monochromatic images of a board in R, G, B, sets board color using brightness values, calculates complementary colors, and determines the color component with the largest brightness value to enhance inspection precision.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a single captured image is used for mounting inspection, then the inspection process is simple, but the inspection precision is insufficient

Engineering Contradiction:
Improveinspection precisionVSAvoidinspection process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the captured image into multiple regions of interest (ROIs) corresponding to different components on the circuit board. Each ROI is processed separately to extract feature vectors, allowing the system to focus on specific inspection areas and improve overall precision without requiring the entire image to be analyzed uniformly.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transforms the inspection from a single 2D image analysis to a multi-dimensional feature space by extracting multiple features (position, size, shape, color, intensity) for each component. This dimensional expansion enables more comprehensive inspection criteria to be applied, thereby improving precision while maintaining manageable process complexity through automated feature extraction.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If multiple inspection criteria are applied, then the inspection precision improves, but the difficulty of detecting and measuring increases

Engineering Contradiction:
Improvemounting inspection precisionVSAvoidinspection complexity
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent implements automatic feature extraction where the system self-determines the appropriate inspection criteria based on the extracted feature vectors. The machine learning model automatically evaluates components against multiple criteria (position accuracy, size tolerance, orientation) without requiring manual configuration of each inspection parameter, thereby reducing operational complexity while maintaining high precision.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent dynamically adjusts inspection parameters based on the extracted feature vectors and the specific component type. The system modifies detection thresholds and measurement criteria according to the actual component characteristics, allowing multiple inspection criteria to be applied adaptively rather than rigidly, thus reducing measurement difficulty while improving precision.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If the board color is not accurately determined, then the inspection process is faster, but the inspection precision deteriorates

Engineering Contradiction:
Improvecomponent recognition precisionVSAvoidcolor determination time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs color determination as a preliminary step before component recognition and inspection. By first accurately identifying the board color through feature vector extraction from the captured image, the system establishes a reference baseline that enables subsequent precise comparison with component colors. This preliminary action ensures high precision in component recognition while the automation keeps the time loss minimal.

Inventive Principle:
Principle #10Preliminary action

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

Improves inspection precision by using the optimum light source to capture images for accurate component mounting.

Implementation Method 1

a light projecting means including a plurality of ring-shaped light sources for directing light of different hues to said part obliquely from above at different angles of incidence; the top light source comprising any hue other than red; an imaging means including a color camera located in the center of the ring-shaped light sources and directly over the part for imaging reflected light from the surface of said portion to be inspected

Methodology Applied
Scientific EffectReflection: Reflection

Data Source

PatentEP4007480B1Inspection device
Publication Date: 2025.09.17 FUJI CORP
  • EP4007480B1 patent drawingFigure 1
  • EP4007480B1 patent drawingFigure 2~3
  • EP4007480B1 patent drawingFigure 4~5

AI summary

An inspection device is such that the inspection device executes a mounting inspection of a component using an inspection image of a board on which the component is mounted and includes an imaging device and an image processing device. The imaging device obtains three monochromatic images of the board in R, G, B. The image processing device sets a board color using brightness values of the three monochromatic images obtained by the imaging device, calculates complementary colors of the board color so set, determines on a color component having a largest brightness value in individual color components of the complementary colors so calculated, and sets the monochromatic image having the color component so determined in the obtained three monochromatic images as the inspection image.