Image defect detection

• US 10,404,868 B2
• Filed: 07/15/2015
• Issued: 09/03/2019
• Est. Priority Date: 07/15/2015
• Status: Active Grant

• Current Assignee: HP Indigo B.V. (HP Inc.)
• Original Assignee: HP Indigo B.V. (HP Inc.)
• Inventors: Spivakovsky, Alexander, Perry, Oded, Haik, Oren, Malki, Avi
• Primary Examiner(s): Worku, Negussie
• Application Number:
  US15/569,262
• Publication Number:
  US 20180131815A1
• Time in Patent Office: 1,511 Days
• Field of Search: 382112, 382149, 382144, 382141, 382284, 382145, 382275, 382100, 382128, 382151, 382195, 382209, 382217, 382218, 382254, 382260, 382274, 382294, 358 114, 358 113, 358 19, 358 112, 358 18, 358 306, 358 327, 358 328, 358406, 358504, 358521, 399 15
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: H04N 1/00015 Reproducing apparatus
• CPC Class Codes: H04N 1/00034 Measuring, i.e. determining a quantity by comparison with a standard H04N1/00031 takes precedence
• CPC Class Codes: H04N 1/00037 Detecting, i.e. determining the occurrence of a predetermined state H04N1/00031 takes precedence
• CPC Class Codes: H04N 1/4097 Removing errors due external factors, e.g. dust, scratches

Abstract

Apparatus to detect a defect in a printed image and methods of detecting detects in a printed image are described. In some examples, a printing operation is initiated using image data to generate a printed image. The printed image is then scanned to generate a scanned image. A resolution of the scanned image is estimated, calculated or determined on the basis of a characteristic of the printing operation, and a reference image, having a resolution corresponding to the estimated, calculated or determined resolution, is generated from the image data. Whether defects are present in the printed image may be determined on the basis of a comparison of the reference image with the scanned image.

Claims

1. An apparatus to detect a defect in a printed image, the apparatus being to:

receive, by a processor, first image data representing a printable image;

receive, by the processor, second image data representing a scanned image of the printable image printed in a printing operation;

determine, by the processor, a resolution of the scanned image, the resolution of the scanned image being variable based on a characteristic of the printing operation;

generate, by the processor, a reference image using the first image data, the reference image having a resolution corresponding to the determined resolution of the scanned image; and

determine, by the processor, whether a defect is present in the image printed in the printing operation based on a comparison of the reference image with the scanned image.

2. The apparatus according to claim 1, wherein the characteristic of the printing operation is a speed at which printed print medium passes through a print mechanism in the printing operation, the resolution of the scanned image being variable based on the speed.

3. The apparatus according to claim 1, wherein the apparatus is to align the scanned image with the reference image by detecting a region of interest in each of the scanned image and the reference image and determining a transformation of the scanned image based on the regions of interest.

4. The apparatus according to claim 3, wherein the apparatus is to detect the regions of interest using an Oriented Features from Accelerated Segment Test (FAST) and Rotated Binary Robust Independent Elementary Features (BRIEF) (ORB) process, a Speeded Up Robust Features (SURF) process, a Scale-invariant Feature Transform (SIFT) process, a mean-shift clustering process, or a combination thereof.

5. The apparatus according to claim 1, wherein the apparatus is to detect a defect in the image printed in the printing operation using a structural similarity information measure.

6. The apparatus according to claim 5, wherein the apparatus is to generate down-sampled versions of the scanned image and of the reference image, and to generate a structural similarity information measure for the down-sampled versions of the scanned image and of the reference image.

7. An apparatus to detect a defect in a printed image, the apparatus comprising:

a processor to initiate a printing operation using image data to generate a printed image; and

a scanner to scan the printed image to generate a scanned image;

wherein the processor is to;

determine a resolution of the scanned image, the resolution of the scanned image being variable based on a characteristic of the printing operation;

generate a reference image using the image data, the reference image having a resolution corresponding to the determined resolution; and

compare the reference image with the scanned image to determine whether a defect is present in the printed image.

8. The apparatus according to claim 7, comprising a registration component to align the scanned image with the reference image.

9. The apparatus according to claim 8, wherein the registration component is to detect a region of interest in each of the scanned image and the reference image and determine a transformation of the scanned image based on the regions of interest.

10. The apparatus according to claim 7, wherein the processor comprises:

an image processor to receive first image data representing a printable image and to initiate the printing operation using the first image data; and

a defect processor to receive second image data representing the scanned image.

11. The apparatus according to claim 10, wherein the defect processor is to receive the first image data and to generate the reference image using the first image data and the characteristic of the printing operation.

12. The apparatus according to claim 7, wherein the processor is to identify an artefact in the scanned image that represents a false defect detection.

13. The apparatus according to claim 7, wherein the characteristic of the printing operation is a speed at which printed print medium passes through a print mechanism in the printing operation, the resolution of the scanned image being variable based on the speed.

14. A method of detecting a defect in a printed image, the method comprising:

initiating, by a processor, a printing operation using image data to generate a printed image;

scanning, by a scanner, the printed image to generate a scanned image;

determining, by the processor, a resolution of the scanned image, the resolution of the scanned image being variable based on a characteristic of the printing operation;

generating, by the processor, a reference image from the image data, the reference image having a resolution corresponding to the determined resolution of the scanned image; and

detecting, by the processor, a defect in the printed image based on a comparison of the reference image with the scanned image.

15. The method according to claim 14, comprising aligning the scanned image with the reference image using a global alignment process and/or a local alignment process.

16. The method according to claim 14, wherein the printing operation comprises printing the printed image using a web press.

17. The method according to claim 14, wherein the characteristic of the printing operation is a speed at which printed print medium passes through a print mechanism in the printing operation, the resolution of the scanned image being variable based on the speed.