Image Registration Measurement Using Source Content

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for image registration between a source image and a printed image are time-consuming and prone to errors due to device drift, leading to geometric differences and poor alignment, especially when printing on both sides of a sheet of paper.

Innovation Solution

A system and method for real-time registration error measurement between source and printed images using a processor-based registration component that aligns corners and local features of the images, allowing for continuous adjustment and alignment without the need for separate diagnostic routines.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If separate diagnostic routines with test patterns are used for image registration, then registration accuracy can be improved, but time consumption and device complexity increase

Engineering Contradiction:
Improveimage registration accuracyVSAvoidtime for diagnostic routines
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent extracts the registration measurement function from separate diagnostic routines and integrates it directly into the normal printing process. Instead of using dedicated test patterns and separate measurement procedures, the system uses the actual content images themselves as registration references, eliminating the need for separate diagnostic time.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent makes the printing system multi-functional by enabling it to perform both normal printing and registration measurement simultaneously. The same printing and scanning components used for production are also used for registration error measurement, eliminating the need for separate diagnostic equipment and routines.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Manufacturing precision

If separate diagnostic routines with test patterns are used for image registration, then registration accuracy can be improved, but device complexity increases

Engineering Contradiction:
Improveimage registration accuracyVSAvoidcomplexity of registration system
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent removes the need for separate test pattern generation and dedicated registration measurement equipment. By using the actual content images and their printed outputs directly for registration analysis, the system eliminates complex diagnostic routines while maintaining measurement capability.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs self-measurement of registration errors using its own printing and scanning capabilities. The printed output is scanned and compared with the original digital image to automatically determine registration accuracy, eliminating the need for external diagnostic equipment and complex calibration procedures.

Inventive Principle:
Principle #25Self-service

3Reliability

If frequent recalibration is performed to correct device drift, then registration reliability can be improved, but productivity decreases

Engineering Contradiction:
Improveregistration consistencyVSAvoidprinting output rate
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent implements continuous registration measurement during normal printing operations rather than interrupting production for periodic recalibration. Each printed page is scanned and measured in real-time, providing continuous feedback on registration accuracy without stopping the printing workflow.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The system provides real-time feedback on registration errors by comparing scanned printed images with original digital images. This continuous feedback loop allows for immediate detection and correction of drift issues without requiring scheduled recalibration interruptions, maintaining both reliability and productivity.

Inventive Principle:
Principle #23Feedback

4Measurement precision

If separate diagnostic routines are used for registration measurement, then measurement precision can be improved, but waste of materials increases

Engineering Contradiction:
Improveregistration error measurement accuracyVSAvoidpaper and ink waste
Core Design Contradiction:
Measurement precisionVSLoss of substance

Solution Approach 1:

The patent eliminates idle diagnostic printing by integrating measurement into the continuous printing workflow. Every printed page serves both as production output and as a measurement sample, ensuring that no materials are wasted on separate test patterns or calibration pages.

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The system uses its own production output for self-measurement, eliminating the need for separate test materials. The printed pages that would normally require disposal or special handling are instead utilized as measurement samples, reducing material waste while maintaining measurement precision.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS11348214B2System and method for measuring image on paper registration using customer source images
Publication Date: 2022.05.31 XEROX CORP
  • US11348214B2 patent drawing
  • US11348214B2 patent drawing
  • US11348214B2 patent drawing

AI summary

A system and method are provided for registering source and target images. The method includes receiving a first source image and a first scanned image. The first scanned image is one that has been generated by scanning a printed page that has been generated by printing the first source image or a transformed first source image derived from the first source image. Locations of corners of a target image in the first scanned image are identified. With a first computed transform, the corners of the target image in the first scanned image are aligned to corners of the first source image to generate an aligned target image. Local features in the source image and aligned target image are detected. A second transform is computed to align the target image with the first source image, based on the detected local features.