Automated Reference Image Selection for Print Quality Inspection

Solution Overview

Problem

The existing image forming apparatuses face difficulties in efficiently selecting appropriate reference image data, as visually checking read image data for dirt or defects is time-consuming and prone to errors, leading to potential misclassification of image quality during inspections.

Innovation Solution

An inspection device and image forming apparatus that performs a first inspection using original image data as reference, registering read image data satisfying predetermined criteria as second reference image data for subsequent inspections, thereby automating the selection process and improving efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If visual check is performed to select reference image data, then reliability of reference image data is improved, but loss of time increases and productivity deteriorates

Engineering Contradiction:

Improvereliability of reference image dataVSAvoidtime for visual check

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the manual visual inspection process with an automated image processing system that uses a determination unit to objectively evaluate read image data. The system automatically detects dirt, stains, and other defects by comparing images against reference data and applying predetermined criteria, eliminating the need for time-consuming human visual checks while maintaining or improving selection reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the inspection device to automatically select appropriate reference image data without human intervention. The determination unit autonomously evaluates multiple read image data sets, applies quality criteria, and selects the most suitable reference images, making the system self-sufficient in the reference selection process.

Inventive Principle:

Principle #25Self-service

2Reliability

If visual check is performed to select reference image data, then reliability of reference image data is improved, but productivity deteriorates

Engineering Contradiction:

Improvereliability of reference image dataVSAvoidproductivity of inspection process

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent replaces the manual visual inspection process with an automated image processing system that uses a determination unit to objectively evaluate read image data. The system automatically detects dirt, stains, and other defects by comparing images against reference data and applying predetermined criteria, eliminating the need for time-consuming human visual checks while maintaining or improving selection reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs preliminary automated evaluation of multiple read image data sets before final reference image selection. The determination unit pre-processes and scores candidate images based on quality criteria, so that when reference images are needed, the selection can be made quickly from pre-evaluated candidates, maintaining high reliability without sacrificing productivity.

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If any read image data is selected as reference, then ease of operation is improved, but reliability deteriorates due to potential dirt or defects

Engineering Contradiction:

Improveease of selecting reference image dataVSAvoidquality of reference image data

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system enables self-service by allowing the inspection device to automatically select appropriate reference image data without human intervention. The determination unit autonomously evaluates multiple read image data sets, applies quality criteria, and selects the most suitable reference images, making the system self-sufficient in the reference selection process.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual visual inspection process with an automated image processing system that uses a determination unit to objectively evaluate read image data. The system automatically detects dirt, stains, and other defects by comparing images against reference data and applying predetermined criteria, eliminating the need for time-consuming human visual checks while maintaining or improving selection reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11997234B2Inspection device for inspecting quality of printed images

Publication Date: 2024.05.28 FUJIFILM BUSINESS INNOVATION CORP

AI summary

An inspection device includes a processor configured to perform a first inspection of using original image data as first reference image data and collating the first reference image data with at least one of plural pieces of read image data obtained by reading image-formed matters obtained by forming the first reference image data on plural recording media, and register read image data satisfying a predetermined criterion among the plural pieces of read image data as a result of the first inspection, as second reference image data for a second inspection different from the first inspection.