Printed Image Inspection Alignment With Noise-Applied Reference Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional inspection methods for printed products suffer from erroneous detections due to noise in scanned images, caused by differences in color space and surface properties, leading to reduced inspection precision.

Innovation Solution

An inspection apparatus that applies noise components to a reference image and aligns it with a scanned image, using modules for skew detection, color conversion, resolution adjustment, geometric correction, and random number application to enhance collation precision.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If color matching is performed to bring reference image and scanned image closer, then color consistency is improved, but erroneous detections increase due to noise in scanned images

Engineering Contradiction:

Improvecolor consistencyVSAvoidinspection accuracy

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent extracts and removes noise components from the scanned image through filtering operations. The noise removal unit specifically targets and eliminates noise while preserving the actual defect information, thereby resolving the contradiction between color consistency and inspection accuracy by eliminating the harmful noise elements that cause erroneous detections

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces an intermediate processing step where noise components are identified and separated from the scanned image before comparison. This intermediary noise removal process acts as a mediator between the color matching requirement and the need for accurate defect detection, allowing both goals to be achieved simultaneously

Inventive Principle:

Principle #24Intermediary (Mediator)

2Extent of automation

If scanned image is used for inspection, then inspection automation is improved, but noise from surface properties and scanner reduces measurement precision

Engineering Contradiction:

Improveinspection automationVSAvoidimage quality

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The patent converts the harmful noise in scanned images into a manageable characteristic by modeling and removing it systematically. The noise removal unit transforms the disadvantage of scanned image noise into an advantage by using the noise characteristics to improve defect detection accuracy, thereby maintaining automation while enhancing measurement precision

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Solution Approach 2:

The patent replaces manual visual inspection with an automated system that includes digital noise removal and image processing. This substitution of mechanical/manual inspection with automated digital processing eliminates the subjectivity of visual inspection while incorporating algorithms to handle noise, thus achieving both automation and precision

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12530763B2Inspection apparatus, method of controlling the same, and storage medium

Publication Date: 2026.01.20 CANON KK

AI summary

The present invention provides an inspection apparatus that inspects an image formed on a recording medium by a printing apparatus. The inspection apparatus stores, as a reference image, image data used to form an image on the recording medium, obtains target image data to be inspected, by reading an image to be inspected formed on the recording medium. The inspection apparatus applies noise components to the reference image, aligns the reference image to which the noise components have been applied with the target image data, and performs collation processing between the reference image and the target image data that have been aligned.