Inspection Device Correcting Defective Read Image Data for Reference Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing image forming apparatuses face difficulties in efficiently selecting appropriate reference image data for inspections, as visual checks are cumbersome and may miss image data with defects, leading to inappropriate selection even when data does not meet predetermined criteria.

Innovation Solution

An inspection device and image forming apparatus that displays read image data with recognizable defects, allowing for correction and registration as reference image data, enabling the use of image data that initially does not satisfy criteria for inspections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If visual check is performed to select reference image data, then appropriate reference image data can be selected, but the process becomes troublesome and inefficient

Engineering Contradiction:

Improveselection accuracy of reference image dataVSAvoidoperational convenience in selecting reference image data

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system automatically performs quality assessment of read image data by comparing it with reference image data, and autonomously determines whether to select it as new reference image data. The quality determination unit calculates quality based on feature amounts and collation results, eliminating the need for manual visual inspection while ensuring reliable selection.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual visual check process is replaced with an automated image processing system that uses feature amount calculation, collation algorithms, and quality determination units to objectively assess and select reference image data, substituting human visual inspection with computational analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If only read image data satisfying predetermined criterion is selected as reference image data, then quality is ensured, but read image data that could be adopted is excluded

Engineering Contradiction:

Improvequality of reference image dataVSAvoidefficiency in selecting reference image data

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The quality criterion is made dynamic and adjustable. The quality determination unit can flexibly determine quality based on various factors including feature amount collation results, and the system allows setting different quality thresholds. This enables the balance between quality assurance and selection efficiency to be dynamically adjusted based on specific needs.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of quality determination by using feature amount calculation and collation results to assess quality, rather than relying on fixed predetermined criteria. This allows read image data with minor defects to be accepted if their overall quality metric meets the threshold, improving selection efficiency while maintaining quality standards.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If read image data with dirt or defects is selected as reference image data, then selection process is simplified, but other read image data may be incorrectly determined as failure

Engineering Contradiction:

Improvesimplicity of reference image data selectionVSAvoidaccuracy of inspection results

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system uses feedback from feature amount collation between reference image data and inspection target images to identify and correct defective portions. When defects are detected in reference image data, the system can correct them by referencing other images or adjusting the feature amounts, ensuring that the reference data does not lead to incorrect inspection results.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary quality assessment and defect detection on read image data before final selection as reference image data. By calculating feature amounts and comparing them with existing reference data in advance, the system identifies potential defects and can correct them before the defective data is used for inspections, preventing false failure determinations.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11570310B2Inspection device for correcting read image data that does not satisfy predetermined criterion, image forming apparatus, and non-transitory computer readable medium storing inspection

Publication Date: 2023.01.31 FUJIFILM BUSINESS INNOVATION CORP

AI summary

An inspection device includes a processor configured to display at least one of plural pieces of read image data on a display unit in a state where a defective portion is recognizable, and set reception of a correction instruction of the defective portion to be enabled, the plural pieces of read image data being obtained by reading image-formed matters obtained by forming original image data on plural recording media, and correct read image data that does not satisfy a predetermined criterion, and then register the corrected read image data as reference image data used for inspecting the image-formed matter.