Inkjet Print Defect Detection via Color Separation Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting white line defects in inkjet printing machines are inefficient and unreliable, often requiring test charts, generating reference images, and are prone to false positives, especially in complex print jobs with varying paper types and ink qualities.
Innovation Solution
A method using a camera system to record and digitize printed products, applying a detection algorithm that separates color separations, filters images, and identifies genuine print defects directly in the camera image, with optional reference image processing to eliminate pseudo defects, ensuring accurate nozzle compensation without operator intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If test charts are used to detect white line defects, then detection reliability is improved, but waste increases due to test chart consumption
Solution Approach 1:
The patent extracts the defect detection function from the test chart process and applies it directly to the actual printed image. By using the real print data itself for analysis rather than separate test charts, the system eliminates the waste associated with test chart consumption while maintaining detection capability through direct examination of the printed output.
Solution Approach 2:
The patent makes the printed image serve multiple functions: it is both the final product and the basis for defect detection. The same image data that represents the printed output is also used for analyzing nozzle performance and identifying defects, eliminating the need for separate test charts and reducing overall waste.
2Extent of automation
If column profile comparison methods are used, then detection automation is improved, but measurement precision deteriorates due to calibration errors and paper type variations
Solution Approach 1:
Instead of comparing printed images against theoretical or reference column profiles (which introduces calibration errors), the patent inverts the approach by directly analyzing the actual printed image data for defect characteristics. This inversion eliminates the need for complex calibration and reference profiles, improving measurement precision while maintaining automation.
Solution Approach 2:
The patent changes the detection parameters from comparing overall column profiles to analyzing specific local characteristics of the printed image, such as color separation values and pixel-level variations. This parameter change allows for more precise defect detection that is less sensitive to calibration errors and paper type variations.
3Measurement precision
If reference images are generated for comparison, then defect detection accuracy is improved, but device complexity increases
Solution Approach 1:
The patent extracts the essential defect detection capability from the complex reference image generation process. By directly analyzing the printed image for characteristic defect patterns rather than comparing against generated references, the system achieves accurate defect detection with significantly reduced device complexity and processing requirements.
4Ease of manufacture
If white lines are detected in solid areas only, then detection simplicity is improved, but adaptability deteriorates for images without solid areas
Solution Approach 1:
The patent segments the image analysis into color separation channels (C, M, Y, K) and applies defect detection algorithms to each channel independently. This segmentation allows the system to detect white line defects in various image types including those without large solid areas, as each color channel can be analyzed for its specific characteristics and defect patterns.
Solution Approach 2:
The patent applies local quality analysis by examining color separation values and pixel characteristics at specific locations within the image. This local analysis approach enables the system to detect defects in diverse image content including text, graphics, and images without solid areas, significantly improving adaptability while maintaining detection simplicity through localized processing.
Data Source
AI summary
A method for determining print defects in a printing operation carried out on an inkjet printing machine for processing a print job includes using a camera system to record and digitize printed products generated during the printing operation, feeding the camera image having been thus generated to a detection algorithm on the computer, alerting a machine control unit when print defects are found, and ejecting the printed product through a waste ejector if necessary. The detection algorithm separates color separations of the camera images, detects the print defects in the color separations, links images of the individual color separations to form a candidate image, filters the candidate image, enters the remaining detected print defects into a list, and forwards the list to the machine control unit of the printing machine.