Sheet Inspection Brightness Compensation for Printed Products

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image inspection methods for printed products are sensitive to pseudo-errors caused by irregularities in print substrate transport, such as air turbulence and sheet deformations, leading to false positives due to brightness fluctuations, which are not effectively corrected by previous methods.

Innovation Solution

The method involves separating areas with paper white in both the print and reference images, determining their color values, and compensating for brightness differences by adjusting the image with the darker image being brightened or the brighter image being darkened, ensuring accurate comparison and reducing pseudo-errors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If automated image inspection is performed without brightness compensation, then inspection speed is maintained, but false positive errors increase due to brightness fluctuations from sheet deformations

Engineering Contradiction:
Improveinspection accuracyVSAvoidinspection speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent applies preliminary action by performing brightness compensation before the image comparison step. The system calculates brightness deviation maps from reference images and uses these to pre-adjust the brightness of captured images, ensuring that brightness fluctuations from sheet deformations are corrected before comparison with reference images, thereby preventing false positive errors while maintaining automated inspection speed

Inventive Principle:
Principle #10Preliminary action

2Reliability

If brightness compensation is performed using previous methods, then some brightness deviations are corrected, but pseudo-errors from arc deformations remain undetected

Engineering Contradiction:
Improveerror detection accuracyVSAvoidprocessing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies local quality by creating and applying brightness deviation maps that are specific to different regions of the image. Instead of uniform brightness adjustment, the system calculates local brightness deviations for each image region and applies region-specific compensation, allowing precise correction of brightness fluctuations while maintaining clear distinction between real defects and pseudo-errors

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent applies parameter changes by dynamically adjusting brightness parameters based on calculated deviation maps. The system modifies brightness values pixel-by-pixel or region-by-region according to the deviation map, transforming the brightness distribution to match reference conditions and enabling accurate detection of real printing errors

Inventive Principle:
Principle #35Parameter changes

3Reliability

If manual monitoring of image inspection is performed, then pseudo-errors can be recognized and classified, but automation is lost

Engineering Contradiction:
Improveerror classification accuracyVSAvoidautomation level
Core Design Contradiction:
ReliabilityVSExtent of automation

Solution Approach 1:

The patent applies feedback by using reference images as a benchmark and calculating brightness deviation maps that provide feedback on actual brightness conditions. The system continuously compares captured images against reference images, uses the deviation feedback to adjust brightness compensation parameters, and repeats the process, enabling automated recognition and classification of pseudo-errors with accuracy comparable to manual monitoring

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3882032B1Sheet inspection with global brightness adjustment
Publication Date: 2022.03.30 HEIDELBERGER DRUCKMASCHINEN AG
  • EP3882032B1 patent drawingFigure 1
  • EP3882032B1 patent drawingFigure 2~3
  • EP3882032B1 patent drawingFigure 4~5

AI summary

A method for image inspection of printed products in a printing material processing machine using a computer, wherein, within the framework of the image inspection, the produced printed products are captured and digitized by an image acquisition system using at least one image sensor, the captured digital print images are compared by the computer with a digital reference image, and in the event of deviations of the captured digital print images from the digital reference image, the incorrectly identified printed products are rejected, which is characterized in that the computer separates areas with paper white for print and reference images respectively and determines their color values ​​and compensates for brightness differences between print and reference images on the basis of the differences between these two color values.