Print Defect Detection via Consecutive Image Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image inspection methods in printing often misclassify relevant defects as pseudo-defects due to substrate or camera influences, leading to increased workload and reduced transparency in identifying genuine print defects, especially when using lower-quality printing substrates.
Innovation Solution
A method that records and analyzes multiple consecutive printed products to filter out pseudo-defects by considering deviations present in all assessed products, using image sensors and computer analysis to differentiate between genuine and pseudo-defects based on positional and size similarities, and applying predefined tolerance ranges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If inspection parameters are modified to suppress substrate defects, then the occurrence of pseudo-defects is reduced, but relevant print defects may be suppressed or not displayed
Solution Approach 1:
The system dynamically adjusts defect evaluation by comparing the same image content across multiple printed products. Defects are evaluated based on their consistency appearance rather than static parameter thresholds, allowing the system to adapt between suppressing substrate defects and detecting genuine print defects
Solution Approach 2:
The system uses feedback from comparing multiple printed products to distinguish between pseudo-defects and genuine defects. By analyzing whether defects appear consistently across multiple products, the system provides feedback that helps differentiate between substrate issues and actual printing problems
2Ease of manufacture
If lower-quality printing substrates are used to reduce costs, then cost-efficiency is improved, but additional non-relevant defects are displayed increasing operator workload
Solution Approach 1:
The system extracts and filters out pseudo-defects caused by substrate characteristics by comparing multiple printed products. Non-relevant defects that appear inconsistently across products are separated from genuine print defects, reducing the burden on operators to manually assess false alarms
3Reliability
If multiple consecutive printed products are analyzed to filter pseudo-defects, then detection reliability is improved, but inspection time increases
Solution Approach 1:
The system performs partial analysis by comparing only identical image content across multiple printed products rather than analyzing entire images. This selective approach maintains high detection reliability while reducing the overall inspection time and computational burden
4Object-affected harmful factors
If tolerances are increased to suppress substrate defects, then pseudo-defects are reduced, but transparency of current status is reduced and important deviations may remain undetected
Solution Approach 1:
Instead of using fixed tolerance thresholds, the system dynamically evaluates defects based on their consistency across multiple printed products. This dynamic approach maintains visibility of relevant defects while suppressing substrate defects, preserving information transparency without losing important deviations
Data Source
AI summary
A method of controlling the quality of printed products by using a computer includes always producing multiple printed products with at least partially identical image content in a printing machine in a course of a print job to be completed. The multiple printed products are recorded by at least one image sensor and are sent to the computer as digital image data. The computer examines and assesses the digital image data in an image inspection process to find print defects and to sort out printed products that have been found to be unusable. The computer assesses the identical image content of the digital image data of at least two consecutive printed products and only takes into consideration such detected print defects that are present on the at least two assessed consecutive printed products.