Image Processing Apparatus for Printed Product Inspection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automatic inspection systems for printed products face challenges in accurately detecting defects, especially at the periphery of the medium, due to variations in print position and medium size, leading to inaccurate inspection results.
Innovation Solution
An image processing apparatus that determines a picture region and a peripheral region on the printed product, performing inspection processing specific to each region. This allows for accurate detection of defects even when print position errors occur.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If alignment is performed to make pictures of reference image and target image match, then inspection accuracy for printed content is improved, but inspection accuracy at the periphery of the medium deteriorates due to print position variations
Solution Approach 1:
The inspection area is divided into a picture region (where images are printed) and a peripheral region (at the edges of the medium). Different inspection methods are applied to each region: alignment-based inspection for the picture region and non-alignment-based inspection for the peripheral region, thereby resolving the contradiction between needing alignment for image matching and avoiding alignment for periphery accuracy
Solution Approach 2:
Different inspection settings and methods are applied to different regions of the medium. The picture region receives alignment-based inspection while the peripheral region receives inspection that does not rely on alignment, allowing each region to be inspected with the most appropriate method for its characteristics
2Measurement precision
If alignment processing is applied to compensate for print position errors, then defect detection accuracy in the picture region is improved, but detection reliability at the periphery deteriorates due to cumulative errors
Solution Approach 1:
The medium is segmented into picture region and peripheral region, with different inspection strategies applied to each. This segmentation allows alignment processing to be used where it benefits detection accuracy (picture region) while avoiding its negative effects in the peripheral region where reliability is compromised by cumulative errors
3Device complexity
If a single inspection method is used for the entire medium, then device complexity is reduced, but inspection accuracy varies across different regions
Solution Approach 1:
The inspection system implements local quality by applying different inspection methods to different regions: a first inspection method using alignment for the picture region and a second inspection method without alignment for the peripheral region. This ensures high inspection accuracy in each region without requiring overly complex device architecture
Data Source
Figure 1
Figure 2
Figure 3
AI summary
There is provided with an image processing apparatus. An obtaining means (210) obtains a first image serving as a read image of an inspection target medium having undergone printing, and a second image serving as a read image of a reference medium representing a target print result. An inspection means (205) inspects a defect on the inspection target medium based on the first image and the second image by performing inspection at inspection settings different between a print region and a peripheral region of the inspection target medium.