Substrate Inspection Merging Image Data for Stain Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing substrate inspection methods struggle with accuracy and reliability due to the formation of stains at the same position on multiple substrates, which are often undetected by automated facilities and require human judgment to assess acceptability.

Innovation Solution

A substrate inspecting apparatus and method that divides and merges image data to normalize brightness levels, allowing for improved detection of stains by calculating normal values and enhancing the detection of stains at fixed positions through merged image data analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated facility inspection is used, then productivity is improved, but measurement precision deteriorates due to undetected stains

Engineering Contradiction:

Improveinspection speedVSAvoidstain detection accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent merges multiple basic image data sets captured from different substrates to create composite image data. By combining images where stains appear at the same positions, the inspection system enhances stain visibility and detection accuracy while maintaining automated high-speed inspection capabilities.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system performs preliminary normalization processing on basic image data before merging, calculating normal values for stain and non-stain areas in advance. This preprocessing ensures that when images are combined, brightness variations are corrected and stains become more prominent, improving detection precision without adding inspection time.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If human judgment is involved in inspection, then measurement precision is improved, but productivity deteriorates

Engineering Contradiction:

Improvestain detection accuracyVSAvoidinspection speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the mechanical human inspection process with an automated image processing system that performs normalization and merging operations. The merger unit automatically identifies stains by comparing merged image data against normal values, eliminating the need for manual inspection while maintaining or improving detection accuracy through systematic image analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Device complexity

If basic image data is used directly, then device complexity is reduced, but measurement precision deteriorates due to brightness variations

Engineering Contradiction:

Improveprocessing simplicityVSAvoidstain detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system changes the brightness parameter of image data by normalizing each basic image data set against calculated normal values. This parameter transformation enhances the contrast between stain and non-stain areas, making stains more detectable in the merged image data while using only standard image processing operations.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250209597A1Substrate inspecting apparatus and method of inspecting substrate

Publication Date: 2025.06.26 SAMSUNG DISPLAY CO LTD

AI summary

A substrate inspecting apparatus includes an image sensor that captures an image of a substrate to generate basic image data, and a merger that divides the basic image data into first image data including a first stain area and a first non-stain area and second image data including a second stain area and a second non-stain area, and that merges the first image data and the second image data to generate merged image data including a merged stain area representing the first stain area and the second stain area and a merged non-stain area representing the first non-stain area and the second non-stain area.