Image evaluation device, image evaluation method and program storage medium

• US 9,727,805 B2
• Filed: 09/24/2013
• Issued: 08/08/2017
• Est. Priority Date: 09/28/2012
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Inventors: Yamagishi, Hideki
• Primary Examiner(s): Safaipour, Houshang
• Assistant Examiner(s): Shah, Bharatkumar S
• Application Number:
  US14/034,710
• Publication Number:
  US 20140092419A1
• Time in Patent Office: 1,414 Days
• Field of Search: 358 114
• CPC Class Codes: G06K 15/02 using printers
• CPC Class Codes: G06T 2207/30144 Printing quality
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: H04N 1/00005 relating to image data
• CPC Class Codes: H04N 1/00015 Reproducing apparatus
• CPC Class Codes: H04N 1/00018 Scanning arrangements
• CPC Class Codes: H04N 1/00029 Diagnosis, i.e. identifying a problem by comparison with a normal state
• CPC Class Codes: H04N 1/00031 Testing, i.e. determining the result of a trial H04N1/00029 takes precedence; using test signals for transmission mode changing H04N2201/33371
• CPC Class Codes: H04N 1/00045 using a reference pattern designed for the purpose, e.g. a test chart
• CPC Class Codes: H04N 1/00047 using an image not specifically designed for the purpose
• CPC Class Codes: H04N 1/0005 in service, i.e. during normal operation
• CPC Class Codes: H04N 1/00058 using a separate apparatus
• CPC Class Codes: H04N 1/00076 locally

Abstract

An image evaluation device includes: a reading unit that reads a sample image included in a sample printout recognized as a non-defective printout and that reads an inspection object image included in an inspection object printout obtained by printing an image corresponding to the sample image on a recording medium using a printing device based on image data representing the image; an extraction unit that extracts a line defect including a linear pattern formed in a specific direction from the inspection object image represented by inspection object image data, based on a difference value between sample image data obtained by reading the sample image and the inspection object image data; and an evaluation unit that evaluates a visibility of the line defect extracted by the extraction unit.

Claims

1. An image evaluation device, comprising a processor that causes the device to function as:

a reading unit that is configured to read a sample image included in a sample printout recognized as a non-defective printout and that reads an inspection object image included in an inspection object printout obtained by printing an image corresponding to the sample image on a recording medium using a printing device based on image data representing the image;

an extraction unit that is configured to extract a line defect including a linear pattern formed in a specific direction from the inspection object image represented by inspection object image data, based on a difference value between sample image data obtained by reading the sample image and the inspection object image data; and

an evaluation unit that is configured to evaluate a visibility of the line defect extracted by the extraction unit,

wherein an evaluation of the visibility at the evaluation unit includes deriving a level of visibility recognizable by a vision of a person,

wherein the evaluation unit is further configured to evaluate the visibility of the line defect using a mask effect-visual model,

wherein the evaluation unit is further configured to combine the line defect extracted by the extraction unit with the sample image represented by the sample image data, and evaluates the visibility of the line defect based on a combined image obtained by the combination and on the sample image, using the mask effect-visual model, and

wherein the mask effect-visual model comprises a method of modeling human visual characteristics.

2. The image evaluation device according to claim 1, wherein the line defect comprises at least one of a line defect of which spatial frequencies of human visual characteristics are considered, or a line defect of which a color space of human visual characteristics is considered.

3. The image evaluation device according to claim 1, wherein the extraction unit is further configured to extract the line defect from a predetermined region of the inspection object image that is represented by the inspection object image data.

4. The image evaluation device according to claim 3, wherein the predetermined region comprises an expected region in which the line defect is expected to be formed.

5. The image evaluation device according to claim 4, wherein the expected region is determined based on characteristics of at least one of the printing device or the reading unit.

6. The image evaluation device according to claim 5, wherein the characteristics of the printing device include time degradation characteristics of components of the printing device, and/or the characteristics of the reading unit include time degradation characteristics of components of the reading unit.

7. The image evaluation device according to claim 3, wherein the predetermined region corresponds to a region of the inspection object image in which a difference value between the inspection object image data and the sample image data exceeds a threshold value.

8. The image evaluation device according to claim 1, wherein the specific direction comprises a conveying direction of the recording medium in the printing device.

9. The image evaluation device according to claim 8, wherein a printing method of the printing device comprises a single-pass method.

10. The image evaluation device according to claim 1, wherein the printing device performs printing by dividing the inspection object image into a plurality of lines and recording each of the plurality of lines on the recording medium, and the specific direction is a main scanning direction of the printing device.

11. The image evaluation device according to claim 10, wherein a printing method of the printing device comprises a shuttle-scan method.

12. The image evaluation device according to claim 1, wherein the reading unit is further configured to read the inspection object image with a resolution of the inspection object image in the specific direction that is lower than a resolution of the inspection object image in a direction crossing the specific direction.

13. The image evaluation device according to claim 12, wherein the extraction unit is further configured to extract the line defect from the inspection object image after adjusting the resolution in the specific direction of the inspection object image represented by the inspection object image data so as to be the same as the resolution in the direction crossing the specific direction.

14. The image evaluation device according to claim 1, further comprising an exclusion section that is configured to eliminate an influence of characteristics of the reading unit from at least the inspection object image data,

wherein the extraction unit is further configured to extract the line defect from the inspection object image based on a difference value between the sample image data and the inspection object image data that are obtained after the exclusion section has eliminated the influence of the characteristics of the reading unit from at least the inspection object image data.

15. The image evaluation device according to claim 1, wherein the reading unit is further configured to read the inspection object image and the sample image with resolutions in the specific direction of the inspection object image and the sample image that are lower than resolutions in a direction crossing the specific direction, and

in a case in which the resolutions of the inspection object image and the sample image match, the evaluation unit combines the line defect with the sample image represented by the sample image data, adjusts the resolution of a combined image obtained by the combination to a predetermined resolution, and evaluates the visibility of the line defect based on the combined image obtained after the adjustment, using the mask effect-visual model.

16. The image evaluation device according to claim 1, wherein the evaluation unit is further configured to evaluate the line defect using the mask effect-visual model based on decomposed images that are obtained by respectively decomposing the combined image and the sample image into at least one of a plurality of spatial frequency components or a plurality of directional components.

17. The image evaluation device according to claim 16, wherein the evaluation unit is further configured to evaluate the visibility of the line defect using the mask effect-visual model in the specific direction based on the decomposed images.

18. The image evaluation device according to claim 1, wherein the evaluation unit is further configured to evaluate the visibility of the line defect using a statistical method.

19. The image evaluation device according to claim 18, wherein the evaluation using the statistical method is based on evaluation results obtained by having at least one tester perform in advance visual observation of a plurality of evaluation object images corresponding to the inspection object image and respectively including different line defects, and evaluating a level of the visibility of the line defects for each of the plurality of evaluation object images.

20. The image evaluation device according to claim 19, wherein the evaluation using the statistical method is based on a multiple regression equation determined according to the evaluation results.

21. The image evaluation device according to claim 1, further comprising a warning unit that is configured to provide a warning if the evaluation unit determines that the line defect is a visible line defect.

22. The image evaluation device according to claim 21, wherein the warning unit is further configured to provide the warning by directly processing the inspection object printout that includes the line defect determined to be a visible line defect.

23. The image evaluation device according to claim 22, wherein the warning unit is further configured to provide the warning by applying, to the inspection object printout, an identification aiding mark that facilitates identification of a position of the line defect in the inspection object printout.

24. The image evaluation device according to claim 23, wherein the warning unit is further configured to provide the warning by applying the identification aiding mark to a position on an extended line of the line defect of the inspection object printout in the specific direction.

25. The image evaluation device according to claim 23, wherein a type of the identification aiding mark is determined according to the level of the visibility of the line defect.

26. The image evaluation device according to claim 21, wherein the warning unit is further configured to provide the warning by causing a display unit to display predetermined information if the line defect is determined by the evaluation unit to be a visible line defect.

27. The image evaluation device according to claim 26, wherein the predetermined information includes at least one of identification information that identifies the inspection object printout including the line defect that is determined to be a visible line defect, or the inspection object image that includes the line defect and an identification aiding image that facilitates identification of a position of the line defect in the inspection object image.

30. The image evaluation device according to claim 1, wherein the line defect comprises a defect caused by the printing device.

31. The image evaluation device according to claim 1, wherein the mask effect-visual model comprises a visible difference predictor (VDP).

32. The image evaluation device according to claim 1, wherein the evaluation unit is configured to be input with two images of the inspection object image and the sample image to evaluate a difference between the two images.

28. An image evaluation method, comprising:

reading a sample image included in a sample printout recognized as a non-defective printout and reading an inspection object image included in an inspection object printout obtained by printing an image corresponding to the sample image on a recording medium using a printing device based on image data representing the image;

extracting a line defect including a linear pattern formed in a specific direction from the inspection object image represented by inspection object image data, based on a difference value between sample image data obtained by reading the sample image and the inspection object image data; and

evaluating a visibility of the line defect that is extracted by the extracting,

wherein an evaluation of the visibility at the evaluating includes deriving a level of visibility recognizable by a vision of a person,

wherein evaluating is further configured to evaluate the visibility of the line defect using a mask effect-visual model,

wherein the evaluating is further configured to combine the line defect extracted by the extracting with the sample image represented by the sample image data, and evaluates the visibility of the line defect based on a combined image obtained by the combination and on the sample image, using the mask effect-visual model, and

wherein the mask effect-visual model comprises a method of modeling human visual characteristics.

29. A non-transitory computer-readable storage medium storing a program that causes a computer to execute image evaluation processing, the image evaluation processing comprising:

reading a sample image included in a sample printout recognized as a non-defective printout and reading an inspection object image included in an inspection object printout obtained by printing an image corresponding to the sample image on a recording medium using a printing device based on image data representing the image;

extracting a line defect including a linear pattern formed in a specific direction from the inspection object image represented by inspection object image data, based on a difference value between sample image data obtained by reading the sample image and the inspection object image data; and

evaluating a visibility of the line defect that is extracted by the extracting,

wherein an evaluation of the visibility at the evaluating includes deriving a level of visibility recognizable by a vision of a person,

wherein evaluating is further configured to evaluate the visibility of the line defect using a mask effect-visual model,

wherein the evaluating is further configured to combine the line defect extracted by the extracting with the sample image represented by the sample image data, and evaluates the visibility of the line defect based on a combined image obtained by the combination and on the sample image, using the mask effect-visual model, and

wherein the mask effect-visual model comprises a method of modeling human visual characteristics.