Correcting registration errors in digital printing

Patent metadata

Field	Value
Publication number	US-11630618-B2
Application number	US-202217683401-A
Country	US
Kind code	B2
Filing date	Mar 1, 2022
Priority date	Dec 11, 2019
Publication date	Apr 18, 2023
Grant date	Apr 18, 2023

Abstract

A method for correcting an error in image printing, the method includes receiving a reference digital image (RDI). Based on a predefined selection criterion, one or more regions in the RDI that are suitable for use as anchor features for sensing the error, are automatically selected. A digital image (DI) acquired from a printed image of the RDI, is received and the one or more regions are automatically identified in the DI. Based on the anchor features of the DI, the error is automatically estimated in the printed image. A correction that, when applied to the DI, compensates for the estimated error, is calculated. The estimated error is corrected in a subsequent digital image (SDI) to be printed, and the SDI having the corrected error, is printed.

First claim

The invention claimed is:

1. A method for correcting an error in image printing, the method comprising:
receiving a reference digital image (RDI);
automatically selecting, based on a predefined selection criterion comprising a score of a geometrical gradient, one or more regions in the RDI that are suitable for use as anchor features for sensing the error;
receiving a digital image (DI) acquired from a printed image of the RDI, and automatically identifying the one or more regions in the DI;
automatically estimating, based on the anchor features of the DI, the error in the printed image;
calculating a correction that, when applied to the DI, compensates for the estimated error, by: (i) selecting one or more candidate regions, (ii) calculating the score for each of the candidate regions, and (iii) based on the score, selecting the one or more regions from among the candidate regions;
correcting the estimated error in a subsequent digital image (SDI) to be printed; and
printing the SDI having the corrected error.

2. The method according to claim 1 , wherein the error comprises a registration error, which is a relative shift between two structures in the DI, and wherein the score is indicative of whether the relative shift between a given candidate region and a given structure in the DI is distinguishable for automatically estimating the registration error.

3. The method according to claim 2 , wherein the relative shift is carried out in: (i) a first axis, (ii) a second axis, which is orthogonal to the first axis, and (iii) a combination of the first and second axes, and wherein automatically estimating the error comprises estimating at least one of the relative shifts.

4. The method according to claim 3 , wherein the given structure comprises first and second lines crossing one another at a corner, and wherein calculating the score comprises applying a detection algorithm for detecting the corner and the first and second lines.

5. The method according to claim 4 , wherein when the candidate region is positioned on the corner, calculating the score comprises detecting the relative shift in the first and second axes, and the combination.

6. The method according to claim 4 , wherein when the candidate region is positioned on the first line or the second line, calculating the score comprises detecting the relative shift in at least one of the first and second axes.

7. The method according to claim 1 , wherein the DI comprises first and second color images, wherein the error comprises a color-to-color (C2C) registration error, which is a relative shift between the first and second color images, wherein automatically selecting the regions comprises: (i) automatically selecting first and second color candidate regions in the first and second color images, respectively, and (ii) calculating the score by calculating a C2C gradient between the first and second color candidate regions, which is indicative of the relative shift between the first and second color images.

8. The method according to claim 7 wherein calculating the C2C gradient comprises calculating, in the geometrical gradient, a structure tensor indicative of the score.

9. The method according to claim 7 , wherein calculating the C2C gradient comprises calculating at least one of: (i) a distance between the first and second color candidate regions, and (ii) a variation in the distance between the first and second color candidate regions.

10. A system for correcting an error in image printing, the system comprising:
a processor, which is configured to:
receive a reference digital image (RDI);
automatically select, based on a predefined selection criterion comprising a score of a geometrical gradient, one or more regions in the RDI that are suitable for use as anchor features for sensing the error;
receive a digital image (DI) acquired from a printed image of the RDI, and automatically identify the one or more regions in the DI;
automatically estimate, based on the anchor features of the DI, the error in the printed image; calculate a correction that, when applied to the DI, compensates for the estimated error by: (i) selecting one or more candidate regions, (ii) calculating the score for each of the candidate regions, and (iii) based on the score, selecting the one or more regions from among the candidate regions; and
correct the estimated error in a subsequent digital image (SDI) to be printed; and

a printing subsystem configured to print the SDI having the corrected error.

11. The system according to claim 10 , wherein the error comprises a registration error, which is a relative shift between two structures in the DI, and wherein the score is indicative of whether the relative shift between a given candidate region and a given structure in the DI is distinguishable for automatically estimating the registration error.

12. The system according to claim 11 , wherein the relative shift is carried out in: (i) a first axis, (ii) a second axis, which is orthogonal to the first axis, and (iii) a combination of the first and second axes, and wherein the processor is configured to estimate at least one of the relative shifts.

13. The system according to claim 12 , wherein the given structure comprises first and second lines crossing one another at a corner, and wherein the processor is configured to calculate the score by applying a detection algorithm for detecting the corner and the first and second lines.

14. The system according to claim 13 , wherein when the candidate region is positioned on the corner, the processor is configured to calculate the score by detecting the relative shift in the first and second axes, and the combination.

15. The system according to claim 13 , wherein when the candidate region is positioned on the first line or the second line, the processor is configured to calculate the score by detecting the relative shift in at least one of the first and second axes.

16. The system according to claim 10 , wherein the DI comprises first and second color images, wherein the error comprises a color-to-color (C2C) registration error, which is a relative shift between the first and second color images, wherein the processor is configured to automatically select the regions: (i) by automatically selecting first and second color candidate regions in the first and second color images, respectively, and (ii) calculate the score by calculating a C2C gradient between the first and second color candidate regions, which is indicative of the relative shift between the first and second color images.

17. The system according to claim 16 , wherein the processor is configured to calculate the C2C gradient by calculating, in the geometrical gradient, a structure tensor indicative of the score.

18. The system according to claim 16 , wherein the processor is configured to calculate the C2C gradient by calculating at least one of: (i) a distance between the first and second color candidate regions, and (ii) a variation in the distance between the first and second color candidate regions.

Assignees

• Landa Corp Ltd

Inventors

• Levant Boris

Classifications

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06F3/121

  Facilitating exception or error detection and recovery, e.g. fault, media or consumables depleted · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10024

  Color image · CPC title

• G06F3/1234 Primary

  Errors handling and recovery, e.g. reprinting (G06F3/1261 takes precedence) · CPC title