Image inspection method, image inspection device, program, and image recording system

Patent metadata

Field	Value
Publication number	US-10311561-B2
Application number	US-201715717947-A
Country	US
Kind code	B2
Filing date	Sep 28, 2017
Priority date	Sep 30, 2016
Publication date	Jun 4, 2019
Grant date	Jun 4, 2019

Abstract

The image inspection method includes: a step of acquiring data of an inspection image obtained by capturing an image of a recorded matter recorded by an image recording system that performs a compensation process of compensating for a defect caused by a failure in an image formation element, using an imaging apparatus; a step of acquiring data of a reference image; and a step of comparing the data of the inspection image with the data of the reference image to determine whether there is a defect at each position of the inspection image. The defect detection step includes a process that makes a defect detection performance different in a compensation application region and a compensation non-application region other than the compensation application region, on the basis of compensation position information of the failure in the image formation element to which the compensation process has been applied.

First claim

What is claimed is:

1. An image inspection method comprising:
an inspection image acquisition step of acquiring data of an inspection image obtained by capturing an image of a recorded matter recorded by an image recording system that comprises a plurality of image formation elements and performs a compensation process of compensating for a defect caused by a failure in the image formation element, using an imaging apparatus;
a reference image acquisition step of acquiring data of a reference image which is a reference for detecting a defect in the recorded matter; and
a defect detection step of comparing the data of the inspection image with the data of the reference image to determine whether there is a defect at each position of the inspection image,
wherein the defect detection step includes a process that makes a defect detection performance different in a compensation application region and a compensation non-application region other than the compensation application region, on the basis of compensation position information of the failure in the image formation element to which the compensation process has been applied,
wherein in the defect detection step, a plurality of defect detection methods with different detection performances are defined, and
the defect detection step includes a selection step of selecting a defect detection method to be applied to determine whether there is a defect at each position from the plurality of defect detection methods on the basis of the compensation position information,
wherein in a case in which a set of the compensation positions of the failure in the image formation element in the inspection image is a set T, a set of the compensation positions of the failure in the image formation element in the reference image is a set R, a set of positions that are included in the set T and the set R is a first position set, a set of positions that are included in the set T and are not included in the set R is a second position set, a set of positions that are not included in the set T and are included in the set R is a third position set, and a set of positions that are not included in the set T and the set R is a fourth position set, in the selection step, different defect detection methods are selected for at least the second position set and the fourth position set.

2. The image inspection method according to claim 1 ,
wherein the detection performance is defect detection accuracy determined by a combination of a correct detection performance that accurately determines a defect in the recorded matter and an erroneous detection avoidance performance that avoids erroneously determining a non-defect position of the recorded matter to be a defect, and
the defect detection step includes a process that sets the erroneous detection avoidance performance in the compensation application region to be higher than the erroneous detection avoidance performance in the compensation non-application region.

3. The image inspection method according to claim 1 ,
wherein the defect detection method includes
a region determination step of determining an arithmetic region for extracting a signal which is suspected as a defect,
a signal intensity determination step of determining intensity of the signal suspected as a defect from the arithmetic region determined in the region determination step, and
a defect presence/absence determination step of determining whether there is a defect, on the basis of the intensity of the signal determined in the signal intensity determination step, using a threshold value, and
the plurality of defect detection methods include defect detection methods in which at least arithmetic methods or parameters used in an arithmetic operation are different in at least one of the region determination step, the signal intensity determination step, or the defect presence/absence determination step.

4. The image inspection method according to claim 3 ,
wherein the plurality of defect detection methods include defect detection methods in which the arithmetic regions determined in the region determination step have different sizes.

5. The image inspection method according to claim 3 ,
wherein the plurality of defect detection methods include defect detection methods in which arithmetic methods used for the arithmetic operation in the signal intensity determination step or the parameters used for the arithmetic operation in the signal intensity determination step are different from each other.

6. The image inspection method according to claim 3 ,
wherein the plurality of defect detection methods include defect detection methods in which the threshold values used in the defect presence/absence determination step are different from each other.

7. The image inspection method according to claim 3 ,
wherein the defect presence/absence determination step includes a statistical determination process that finally statistically determines whether there is a defect on the basis of a determination data group for a defect and a non-defect determined at a plurality of positions, and
determination criteria of the statistical determination process are set to be different in the compensation application region and the compensation non-application region, on the basis of the compensation position information.

8. The image inspection method according to claim 1 ,
wherein, among the plurality of defect detection methods, the defect detection method used for the second position set has a higher erroneous detection avoidance performance than the defect detection method used for the fourth position set.

9. The image inspection method according to claim 1 ,
wherein the image recording system is a line-head-type ink jet printing system and the image formation element is a nozzle of a line head.

10. The image inspection method according to claim 9 ,
wherein the compensation process of compensating for the failure in the image formation element is a non-jetting correction process.

11. The image inspection method according to claim 1 ,
wherein the defect is a streak defect.

12. The image inspection method according to claim 1 ,
wherein the reference image is generated by capturing an image of a reference image generating recorded matter, which has been recorded in advance by the image recording system or other image recording systems, using the imaging apparatus or other imaging apparatuses.

13. The image inspection method according to claim 1 ,
wherein the reference image is generated on the basis of image data that is used to record the recorded matter using the image recording system.

14. An image inspection device comprising:
a first interface that acquires data of an inspection image obtained by capturing an image of a recorded matter recorded by an image recording system that comprises a plurality of image formation elements and performs a compensation process of compensating for a defect caused by a failure in the image formation element, using an imaging apparatus, wherein the first interface is formed by at least one of a data input terminal, a communication interface, or a media interface, or a plurality of combinations thereof;
a second interface that acquires data of a reference image which is a reference for detecting a defect in the recorded matter, wherein the second interface is formed by at least one of a data input terminal, a communication interface, or a media interface, or a plurality of combinations thereof; and
a detection circuit that compares the data of the inspection image with the data of the reference image to determine whether there is a defect at each position of the

Assignees

• Fujifilm Corp

Inventors

• Ukishima Masayuki

Classifications

• G06T2207/30108

  Industrial image inspection · CPC title

• G06T2207/30168

  Image quality inspection · CPC title

• B41J2/2139

  Compensation for malfunctioning nozzles creating dot place or dot size errors (generating single droplets or particles on demand by pressure, e.g. electromechanical transducers B41J2/045) · CPC title

• B41J2/2142

  Detection of malfunctioning nozzles (generating single droplets or particles on demand by pressure, e.g. electromechanical transducers B41J2/045, B41J2/05; jet deflection sensors B41J2/125; for cleaning purposes B41J2/16579) · CPC title

• G06T2207/10024

  Color image · CPC title