JP2015108522A - Inspection device, inspection method and inspection program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an inspection device, an inspection method and an inspection program that can detect even a minute defect in an image.SOLUTION: An inspection device includes: a first acquisition unit that acquires an image obtained by ripping print data, as a reference image; a second acquisition unit that acquires a read image of an image printed using the print data, as an image to be inspected; a first calculation unit that calculates a first difference quantity which is a relative difference from each pixel value of surrounding pixels, with respect to each pixel in the reference image; a second calculation unit that calculates a second difference quantity which is a relative difference from each pixel value of the surrounding pixels, with respect to each pixel in the image to be inspected corresponding to a position of each pixel in the reference image; and a determination unit that determines whether or not the image to be inspected has abnormality, on the basis of an absolute value of difference between the first difference quantity and the second difference quantity.

Description

  The present invention relates to an inspection apparatus, an inspection method, and an inspection program.

  In order to inspect the print quality of printed matter, the image data to be inspected generated by reading the printed matter with an image input device such as a scanner is converted so that the print data is ripped and approximated to the output image by the image output device A technique for determining a defect generated in a printed material by comparing with image data is known.

  Japanese Patent Laid-Open No. 2004-228561 analyzes an analysis unit that acquires a read image as an image to be inspected, acquires an image obtained by ripping print data as a reference image, and flatness that represents a change in pixel value in the acquired reference image. Based on the analysis means and the flatness of the analysis result, the inspection threshold is switched for each type of image area, and the difference in pixel values obtained from the comparison between the reference image and the inspection target image exceeds the inspection threshold. An inspection apparatus is disclosed that includes a control unit that controls to inspect the print quality for each area type based on the determination result of whether or not the image is printed.

  However, in the conventional printed matter inspection method, even if there is a minute density unevenness that occurs in the gradation part of the image to be inspected, or a part that appears darker or thinner than the surrounding area in the area where the density should change smoothly, it can be detected. There was a problem that it was difficult to be done. Further, as in Patent Document 1, when the threshold value is determined based on the flatness of the reference image, the threshold value can be increased if it is a uniform halftone part, but in the gradation part (depending on the width of the range), Compared with the uniform halftone portion, the flatness is low, and the threshold value needs to be increased. Further, when the gradation unevenness occurs in the gradation portion, the density difference from the case where the gradation unevenness does not occur at the position where the gradation unevenness occurs and changes smoothly is as small as several gradations. Therefore, in the inspection method that refers to the flatness of the reference image, it is difficult to detect gradation unevenness that occurs in the gradation portion of the inspection target image.

  The present invention has been made in view of the above, and an object thereof is to provide an inspection device, an inspection method, and an inspection program that can detect even a minute defect in an image.

  In order to solve the above-described problems and achieve the object, the present invention provides a first acquisition unit that acquires an image obtained by ripping print data as a reference image, and a read image of an image printed using the print data. A second acquisition unit that acquires an image to be inspected, a first calculation unit that calculates a first difference amount that is a relative difference between pixel values of surrounding pixels for each pixel of the reference image, and A second calculation unit that calculates a second difference amount that is a relative difference from a pixel value of a peripheral pixel for each pixel of the inspection target image corresponding to each pixel position; and the first difference amount and the And a determination unit that determines whether or not the inspection target image has an abnormality based on a magnitude of an absolute value of a difference from the second difference amount.

  According to the present invention, for each pixel of the reference image, for each pixel of the inspection target image corresponding to the first difference amount that is a relative difference from the pixel values of the surrounding pixels and the position of each pixel of the reference image. Since it is determined whether there is an abnormality in the inspection target image based on the magnitude of the absolute value of the difference from the second difference amount that is a relative difference from the pixel values of the surrounding pixels, Even if it is a defect, there exists an effect that it can detect.

FIG. 1 is a block diagram showing the configuration of the inspection system. FIG. 2 is a block diagram illustrating a hardware configuration of the inspection apparatus according to the embodiment. FIG. 3 is a functional block diagram showing an overview of the functions of the inspection apparatus. FIG. 4 is a flowchart illustrating processing performed when the inspection system inspects the print quality. FIG. 5 is a schematic diagram illustrating a gradation image in which gradation unevenness has occurred and a first calculation method of a pixel value difference amount. FIG. 6 is a schematic diagram illustrating a second calculation method of the pixel value difference amount. FIG. 7 is a graph schematically showing the pixel value difference amount calculated from the relationship between the pixel position and the pixel value. FIG. 8 is a flowchart illustrating a process in the case where the inspection system performs an inspection by limiting the image area where the pixel value difference amount is calculated.

  Embodiments of an inspection apparatus will be described below in detail with reference to the accompanying drawings. FIG. 1 is a block diagram showing the configuration of the inspection system 1. As shown in FIG. 1, the inspection system 1 includes an inspection device 100 and a scanner (reading device) 120. The inspection apparatus 100 and the scanner 120 are connected by a predetermined data transmission path N (for example, “network cable”, “serial parallel cable”, etc.). Note that the inspection apparatus 100 may be configured to have the function of the scanner 120.

  The scanner 120 is a reading device that optically reads a printed surface of a printed material and acquires a read image. On the other hand, the inspection apparatus 100 is an information processing apparatus that inspects the print quality of printed matter. Thereby, the user can use the following service (hereinafter referred to as “inspection service”) for inspecting the print quality of the printed matter.

  For example, the user inputs, into the inspection apparatus 100, an image obtained by ripping print data for obtaining a printed material as a reference image for inspecting print quality. Next, the user reads the printed surface of the printed material with the scanner 120. As a result, the scanned image is transmitted from the scanner 120 to the inspection apparatus 100. In the inspection apparatus 100, a difference between pixel values is detected by comparing the received read image with the input reference image, and based on the detected difference between pixel values and a set inspection threshold (defect determination criterion). A defect determination process is performed. Thereby, the user can obtain the print quality inspection result.

  As described above, the inspection system 1 according to the present embodiment can provide a printed matter inspection service with the above-described system configuration. The inspection system 1 may have a configuration in which a plurality of scanners 120 are connected to one inspection apparatus 100. Accordingly, when a large amount of printed matter such as commercial printing is inspected, a plurality of printed matters are simultaneously read by a plurality of scanners 120, and defect inspection processing is performed in parallel in the inspection apparatus 100, thereby efficiently inspecting print quality. Can be implemented.

  FIG. 2 is a block diagram illustrating a hardware configuration of the inspection apparatus 100 according to the embodiment. As shown in FIG. 2, the inspection apparatus 100 includes an input device 101, a display device 102, a drive device 103, a RAM (Random Access Memory) 104, a ROM (Read Only Memory) 105, a CPU (Central Processing Unit) 106, and an interface device. 107 and an HDD (Hard Disk Drive) 108, etc., which are connected to each other via a bus B.

  The input device 101 includes a keyboard and a mouse and is used to input each operation signal to the inspection device 100. The display device 102 includes a display and the like, and displays a processing result by the inspection device 100. The interface device 107 is an interface that connects the inspection device 100 to the data transmission path N. Thereby, the inspection apparatus 100 can perform data communication with other devices having a communication function including the scanner 120 via the interface device 107.

  The HDD 108 is a non-volatile storage device that stores programs and data. An information processing system (for example, an OS (Operating System) which is basic software such as “Windows (registered trademark)” or “UNIX (registered trademark))” and a system are included in the stored programs and data. There are applications that provide various functions (for example, “inspection function”).

  The HDD 108 manages stored programs and data by a predetermined file system and / or DB (Data Base). The drive device 103 is an interface with a removable recording medium 103a. Accordingly, the inspection apparatus 100 can read and / or write the recording medium 103a via the drive apparatus 103. Examples of the recording medium 103a include a floppy (registered trademark) disk, a CD (Compact Disk), a DVD (Digital Versatile Disk), an SD memory card, a USB memory (Universal Serial Bus memory), and the like. is there.

  The ROM 105 is a nonvolatile semiconductor memory (storage device) that can retain internal data even when the power is turned off. The ROM 105 stores programs and data such as BIOS (Basic Input / Output System), information processing system settings, and network settings that are executed when the inspection apparatus 100 is activated. The RAM 104 is a volatile semiconductor memory (storage device) that temporarily stores programs and data. The CPU 106 is an arithmetic device that realizes control and mounting functions of the entire apparatus by reading programs and data from the storage device (for example, “HDD” and “ROM”) onto the RAM and executing processing. As described above, the inspection apparatus 100 according to the present embodiment can provide the inspection service with the hardware configuration.

  FIG. 3 is a functional block diagram showing an overview of the functions of the inspection apparatus 100. The inspection apparatus 100 includes a first acquisition unit 10, a second acquisition unit 11, a first calculation unit 12, a second calculation unit 13, a storage unit 14, and a determination unit 15. Note that each function executed by the inspection apparatus 100 may be configured by hardware or software.

  The first acquisition unit 10 acquires reference image data (reference image) by ripping print data and performing a conversion process so as to approach the output image by the image output apparatus. The first acquisition unit 10 may acquire an image obtained by ripping print data from the outside as a reference image.

  The second acquisition unit 11 acquires inspection target image data (inspection target image). The image data to be inspected is data obtained by outputting an image based on the print image data onto a medium such as paper by an image forming apparatus and reading it by the scanner 120. Further, the second acquisition unit 11 may acquire a read image of an image printed using print data as an inspection target image from the outside.

  The first calculation unit 12 calculates a pixel value difference amount (first difference amount) that is a difference between a pixel value of each pixel and a pixel value of surrounding pixels in the reference image data acquired by the first acquisition unit 10. Specific contents of the calculation of the pixel value difference amount with the surrounding pixels will be described later. The first calculation unit 12 may be further configured to perform an operation for analyzing the flatness representing the change in the pixel value with respect to the reference image.

  The second calculation unit 13 includes a pixel value difference that is a difference between the pixel value of each pixel corresponding to the position of each pixel of the reference image and the pixel value of surrounding pixels in the inspection target image data acquired by the second acquisition unit 11. An amount (second difference amount) is calculated.

  The storage unit 14 stores determination criteria such as a threshold value for determining whether or not an image is normal. The memory | storage part 14 may memorize | store the threshold value used as a determination criterion previously, and may memorize | store the threshold value which the test | inspection system 1 determined.

  The determination unit 15 compares the pixel value difference amount with the surrounding pixels between the pixels at the same position in the reference image data and the inspection target image data. Further, the determination unit 15 determines whether or not the inspection target image is normal based on a determination criterion such as a threshold stored in the storage unit 14. For example, the determination unit 15 determines whether there is an abnormality in the inspection target image by comparing the magnitude of the absolute value of the difference between the first difference amount and the second difference amount with a predetermined threshold value. To do.

  The determination unit 15 further determines whether or not the flatness analyzed by the first calculation unit 12 is equal to or greater than the predetermined value B and is equal to or less than the predetermined value C, and the flatness is less than the predetermined value B. And when larger than the predetermined value C, the threshold value D of the pixel value corresponding to the flatness may be determined. When the determination unit 15 determines the threshold D, the determination unit 15 compares the pixel values of the pixels at the same position in the reference image and the inspection target image, and determines whether or not the difference between the pixel values is greater than or equal to the threshold D. It is determined whether or not the inspection target image is normal.

  That is, the determination unit 15 determines the third threshold value corresponding to the flatness when the flatness is less than the predetermined first threshold and greater than the second threshold. Then, the determination unit 15 determines whether the difference between the pixel value of each pixel of the reference image and the pixel value of each pixel of the inspection target image corresponding to the position of each pixel of the reference image is greater than or equal to the third threshold value, respectively. By determining whether or not there is an abnormality in the inspection target image.

  Further, the determination unit 15 may determine whether or not there is an abnormality in the inspection target image based on a threshold value (change threshold value) whose value is changed according to the pixel value. Here, it is assumed that the change threshold is at least one of the thresholds used by the determination unit 15 and is changed according to the pixel value. The change threshold value may be stored in the storage unit 14.

  Next, processing performed when the inspection system 1 inspects the print quality will be described. FIG. 4 is a flowchart showing processing performed when the inspection system 1 inspects the print quality. In step 101 (S101), the first acquisition unit 10 acquires reference image data, and the second acquisition unit 11 acquires inspection target image data.

  In step 102 (S102), the first calculation unit 12 calculates a pixel value difference amount that is a difference between a pixel value of each pixel and a pixel value of surrounding pixels in the reference image data. In addition, the second calculation unit 13 calculates a pixel value difference amount that is a difference between the pixel value of each pixel and the pixel value of surrounding pixels in the inspection target image data.

  In step 103 (S103), the determination unit 15 compares the pixel value difference amount between the reference image data and the inspection target image data at the same position with the surrounding pixels.

  In step 104 (S104), the determination unit 15 determines that the difference between the pixel value difference amount of a pixel at an arbitrary position in the reference image data and the pixel value difference amount of a pixel at the same position in the inspection target image data is a predetermined threshold A. It is determined whether it is above. If the difference is greater than or equal to the predetermined threshold A (S104: Yes), the determination unit 15 proceeds to the process of S106. If the difference is not greater than or equal to the predetermined threshold A (S104: No), the determination unit 15 proceeds to the process of S105.

  In step 105 (S105), the determination unit 15 determines that the inspection target image is normal.

  In step 106 (S106), the determination unit 15 determines that the inspection target image has an abnormality (defect) such as unevenness that is not present in the reference image.

  Next, the pixel value difference amount calculated by the first calculation unit 12 and the second calculation unit 13 will be described in detail. FIG. 5 is a schematic diagram illustrating a first calculation method of a gradation image in which gradation unevenness has occurred and a pixel value difference amount (difference from pixel values of surrounding pixels).

  With respect to the gradation image shown in FIG. 5, it is difficult to detect gradation unevenness by the conventional printed matter inspection method. Various kinds of images are included in the printed matter, but especially in photographs and graphics, there are gradation images in which the color tone (density, lightness, saturation, etc.) gradually changes smoothly in a certain image area. There are many cases. The direction in which the color tone changes varies depending on the image, but FIG. 5 shows a gradation image in which the density increases from the lower left to the upper right of the square.

  In such a gradation image, if the degree of change in color tone at a certain part is slightly different from the degree of change in color tone before and after that, it appears as a dark streak or conversely as a thin streak. In some cases, the original image data is originally such an image, but the original image data has a gradation that changes smoothly. However, depending on the state of the image forming apparatus, the print image may be in the middle of the gradation. Unevenness may occur. In the case of such gradation unevenness, the density difference between the gradation unevenness occurring at the position where the gradation unevenness occurs and the smooth change without gradation unevenness is several gradations. About small. Therefore, it is difficult to detect by the conventional method of comparing pixel values of pixels at the same position in the reference image and the inspection target image.

  When the flatness of the reference image is obtained and the threshold value is changed according to the flatness as in the prior art, even if the unevenness of the same density difference occurs in a uniform halftone image with a small density change. In this case, since the reference image is flat, the inspection threshold value becomes small, so that unevenness can be detected. However, in the gradation portion, the flatness is lowered (becomes less flat) than in the case of the uniform halftone, and the inspection threshold value is increased, so that the generated unevenness is difficult to detect.

  The figure shown on the right side of FIG. 5 is an enlarged view of an image up to a pixel unit. As described above, the first calculation unit 12 and the second calculation unit 13 calculate the amount of difference from the pixel value of the surrounding pixels for each pixel. The amount of difference between the pixel value of the pixel and the pixel values of the surrounding pixels is substantially opposite to the pixel value of the pixel at a predetermined number of pixels away from the pixel in the first direction and the first direction from the pixel. This is obtained by calculating the difference between the average pixel value of pixels located at a predetermined number of pixels away in the second direction, and the pixel value of the pixel.

  Specifically, in FIG. 5, the position of the pixel is represented by the i-th in the vertical direction and the j-th in the horizontal direction. Then, assuming that the pixel value (luminance, density, brightness, etc. of R, G, B) is v (i, j) and the peripheral pixel to be referred to is a pixel located 5 pixels away from the left and right, the position (i, The difference value of the pixel value of j) is calculated by the following formula 1.

Difference amount = v (i, j)-{v (i, j-5) + v (i, j + 5)} / 2
... (1)

  That is, the first calculation unit 12 and the second calculation unit 13 perform the calculation shown in the above equation 1 for all the pixels in the target image region. Then, the determination unit 15 compares the results calculated by the first calculation unit 12 and the second calculation unit 13 with the reference image and the inspection target image. If the difference in the pixel value difference between the reference image and the inspection target image and the surrounding pixels of each pixel is larger than a predetermined threshold value, the determination unit 15 causes gradation unevenness in the gradation portion of the inspection target image. Judge that there is.

  Here, as for the number of pixels away from the pixel, an appropriate number is selected according to conditions such as the resolution of the system performing the inspection. In addition, since there is an appropriate number depending on the size of the gradation range of the image and the difference between the minimum pixel value and the maximum pixel value, in order to improve the accuracy, it is determined from the analysis result of the above contents of the reference image. Also good. If the change in the pixel value of the reference image gradation portion is gradual, the interval between the numbers of pixels is increased, and if it is abrupt, the interval between the numbers of pixels is decreased.

  That is, the first calculation unit 12 and the second calculation unit 13 change the number of pixels from the pixel to the peripheral pixel to be referenced based on the change degree of the pixel value of the adjacent pixel in the reference image.

  As peripheral pixels, only one side of the pixel in the predetermined direction may be compared, but the gradient gradient may be different between the reference image and the inspection target image, so it is preferable to target both sides.

  FIG. 6 is a schematic diagram illustrating a second calculation method of the pixel value difference amount (difference from the pixel values of surrounding pixels). As shown in FIG. 6, the first calculation unit 12 and the second calculation unit 13 add 3 pixels of 3 × 3 as the surrounding pixels by adding 8 pixels around the pixel 5 pixels to the right from the pixel. Similarly, the pixel and the left side may be 9 pixels, and the difference between the average pixel value and the pixel value of the pixel may be obtained. As shown in FIG. 5, when the target peripheral pixels are one pixel each on the left and right, the target pixel may have a pixel value protruding from the periphery. Increasing the number of target peripheral pixels improves the accuracy of the difference amount.

  FIG. 7 is a graph schematically showing the pixel value difference amount calculated from the relationship between the pixel position and the pixel value. In the graphs shown in FIGS. 7A and 7B, the horizontal axis is the pixel position. Compared with FIG. 5, the point B is the position (i, j) and the point A is the position (i, j−5). ), Point C corresponds to (i, j + 5). The vertical axis represents the luminance value of any of R, G, and B as the pixel value. The graph in FIG. 7A is a reference image, and the graph in FIG. 7B is an inspection target image.

  In the reference image, the pixel value changes smoothly at points A to B to C. However, when the corresponding points A ′ to B ′ to C ′ are seen in the inspection target image, the pixel values are recessed downward at the point B ′. The pixel value at point B ′ is smaller than that of the reference image. This is a case where gradation unevenness that cannot be seen in the reference image appears in the inspection target image. Even in such a state, if there is no difference between the pixel value at point A and the pixel value at point C between the reference image and the image to be inspected and only the pixel value at point B is different, the difference between the pixel values at the corresponding positions The gradation unevenness at point B can be detected only by calculating.

  However, in practice, there may be a difference in the gradient of the pixel value such that there is a difference in the pixel value at point A or C, there is no difference at point A, and there is a difference at point C. , It is difficult to detect gradation unevenness only by the difference in pixel values at point B.

  Therefore, the difference between the pixel values at point B with respect to the average pixel value at points A and C is calculated. That is, in the pixel value, the position of the pixel (point B) with respect to the surrounding pixels is calculated, and if the difference between the reference image and the inspection target image is evaluated, the point A and the point C between the reference image and the inspection target image Even if there is a difference, the gradation unevenness at point B can be detected.

  Gradation unevenness occurs along a contour line in the change direction of the pixel value. 5 and 6, the pixel value difference amount is calculated only for one pixel line in the horizontal direction. However, the same pixel value difference amount is calculated for the upper and lower lines, and the analysis results of a plurality of lines are combined. If the determination is made, the gradation non-uniformity detection accuracy is also improved. In that case, the pixels having a large pixel value difference amount are not necessarily in the same position vertically. Therefore, even if the position where the maximum value of the same pixel value difference amount appears is different in the horizontal direction on the upper and lower lines, if the difference is several pixels, it is the same unevenness and the largest pixel in each vertical line The amount of value difference is totaled and the average value is compared with a threshold value.

  In the case of a gradation image in which the pixel value changes in the vertical direction instead of the diagonal direction as shown in FIG. 5, the gradation unevenness appears as a horizontal stripe in the horizontal direction. If the pixel value difference amount is calculated, gradation unevenness cannot be detected. As a countermeasure, if the calculation of the pixel value difference amount is performed not only in one direction but also in two orthogonal directions, gradation unevenness can be detected in at least one of the directions.

  Specifically, for each pixel of the reference image, the first calculation unit 12 includes a pixel value of a pixel located at a predetermined number of pixels away from the pixel in a third direction substantially orthogonal to the first direction, The difference between the average value of the pixel value of the pixel located at a predetermined number of pixels away from the pixel in the fourth direction, which is substantially opposite to the third direction, and the pixel value of the pixel is the third difference amount. As further calculated.

  Further, the second calculation unit 13 includes, for each of the pixels of the inspection target image corresponding to the position of each pixel of the reference image, a pixel value of a pixel at a position away from the pixel in a third direction by a predetermined number of pixels, The difference between the average value of the pixel value of the pixel located at a predetermined number of pixels away from the pixel in the fourth direction and the pixel value of the pixel is further calculated as a fourth difference amount.

  Then, the determination unit 15 further determines whether there is an abnormality in the inspection target image based on the magnitude of the absolute value of the difference between the third difference amount and the fourth difference amount.

  As described above, the inspection system 1 obtains a relative difference amount between the peripheral pixel value for each pixel in each of the reference image obtained by ripping the document data and the inspection target image obtained by reading the output image, and the reference image By comparing the pixel value difference amount with the pixel value difference amount of the inspection target image, unevenness on the inspection target image side is detected.

  Next, a process that is performed when the inspection system 1 limits the image area where the pixel value difference amount is calculated will be described. The inspection system 1 can inspect not only the gradation part but also all other image areas, and can detect defects with higher accuracy than the conventional method. However, since it takes a processing time to calculate the pixel value difference amount in the entire range of the image, in order to reduce the processing time load, it is more efficient to limit the gradation portion.

  In that case, by analyzing the flatness of the reference image, it is possible to roughly determine what kind of image region it is, and therefore the region to be inspected is determined by the flatness value. When the flatness is large or small, it is not considered to be gradation, so pixels that belong to an area having an area of a certain level or more in the middle flatness are pixels in both the reference image and the inspection target image. The value difference amount is calculated, and the inspection target image is inspected.

  FIG. 8 is a flowchart illustrating processing when the inspection system 1 performs inspection while limiting the image area in which the pixel value difference amount is calculated. In step 201 (S201), the first acquisition unit 10 acquires a reference image, and the second acquisition unit 11 acquires an inspection target image.

  In step 202 (S202), the first calculation unit 12 analyzes the flatness of the reference image.

  In step 203 (S203), the determination unit 15 determines whether or not the flatness of the reference image is greater than or equal to the predetermined value B or less than or equal to the predetermined value C. When the flatness of the reference image is greater than or equal to the predetermined value B or less than or equal to the predetermined value C (S203: Yes), the determination unit 15 proceeds to the process of S207. If the flatness is less than the predetermined value B and greater than the predetermined value C (S203: No), the determination unit 15 proceeds to the process of S204.

  In step 204 (S204), the determination unit 15 determines a threshold value D corresponding to the flatness.

  In step 205 (S205), the determination unit 15 compares pixel values of pixels at the same position in the reference image and the inspection target image.

  In step 206 (S206), the determination unit 15 determines whether or not the difference between the pixel values is greater than or equal to the threshold value D. If the difference is greater than or equal to the predetermined threshold D (S206: Yes), the determination unit 15 proceeds to the process of S212. Moreover, the determination part 15 progresses to the process of S210, when a difference is not beyond the predetermined threshold value D (S206: No).

  In step 210 (S210), the determination unit 15 determines that the inspection target image is normal.

  In step 212 (S212), the determination unit 15 determines that the inspection target image has an abnormality (defect) such as unevenness that is not present in the reference image.

  In step 207 (S207), the first calculation unit 12 calculates a pixel value difference amount that is a difference between the pixel value of each pixel and the pixel value of the surrounding pixels in the reference image data. In addition, the second calculation unit 13 calculates a pixel value difference amount that is a difference between the pixel value of each pixel and the pixel value of surrounding pixels in the inspection target image data.

  In step 208 (S208), the determination unit 15 compares the pixel value difference amounts between the reference image data and the inspection target image data at the same position with the surrounding pixels.

  In step 209 (S209), the determination unit 15 determines that the difference between the pixel value difference amount of a pixel at an arbitrary position in the reference image data and the pixel value difference amount of a pixel at the same position in the inspection target image data is a predetermined threshold A. It is determined whether it is above. If the difference is greater than or equal to the predetermined threshold A (S209: Yes), the determination unit 15 proceeds to the process of S214. If the difference is not greater than or equal to the predetermined threshold A (S209: No), the determination unit 15 proceeds to the process of S213.

  In step 213 (S213), the determination unit 15 determines that the inspection target image is normal.

  In step 214 (S214), the determination unit 15 determines that the inspection target image has an abnormality (defect) such as unevenness that does not exist in the reference image.

  As described above, the inspection apparatus 100 according to the embodiment corresponds to each pixel of the reference image, with respect to the first difference amount that is a relative difference from the pixel values of the surrounding pixels, and the position of each pixel of the reference image. For each pixel in the inspection target image, whether or not there is an abnormality in the inspection target image is determined based on the magnitude of the absolute value of the difference from the second difference amount that is a relative difference from the pixel values of the surrounding pixels. Therefore, even a minute defect in the image can be detected. Further, the inspection system 1 can detect even a minute defect in an image based on various criteria.

DESCRIPTION OF SYMBOLS 1 Inspection system 10 1st acquisition part 11 2nd acquisition part 12 1st calculation part 13 2nd calculation part 14 Storage part 15 Determination part 100 Inspection apparatus 120 Scanner

JP 2012-103225 A

Claims (9)

A first acquisition unit that acquires an image obtained by ripping print data as a reference image;
A second acquisition unit that acquires a read image of an image printed using the print data as an inspection target image;
A first calculation unit that calculates a first difference amount that is a relative difference from pixel values of surrounding pixels for each pixel of the reference image;
A second calculation unit that calculates a second difference amount that is a relative difference from a pixel value of a peripheral pixel for each pixel of the inspection target image corresponding to each pixel position of the reference image;
A determination unit that determines whether or not the inspection target image has an abnormality based on an absolute value of a difference between the first difference amount and the second difference amount;
An inspection apparatus comprising: The first calculation unit includes:
For each pixel of the reference image, a pixel value of a pixel located a predetermined number of pixels away from the pixel in the first direction and a second direction that is substantially opposite to the first direction from the pixel Calculating the difference between the average value of the pixel values of the pixels at a position away from the predetermined number of pixels and the pixel value of the pixel as the first difference amount;
The second calculator is
For each pixel of the inspection object image corresponding to each pixel position of the reference image, a pixel value of a pixel at a predetermined number of pixels away from the pixel in the first direction, and the second value from the pixel. 2. The inspection according to claim 1, wherein a difference between an average value of pixel values of pixels located at a predetermined number of pixels in the direction of and a pixel value of the pixel is calculated as the second difference amount. apparatus. The first calculation unit includes:
For each pixel of the reference image, pixel values of a plurality of pixels around a predetermined number of pixels away from the pixel in the first direction, and a first direction that is substantially opposite to the first direction from the pixel A difference between an average value of pixel values of a plurality of neighboring pixels at a position separated by a predetermined number of pixels in the direction of 2 and a pixel value of the pixel is calculated as the first difference amount;
The second calculator is
For each pixel of the inspection target image corresponding to each pixel position of the reference image, the pixel values of a plurality of pixels around a predetermined number of pixels away from the pixel in the first direction, and from the pixel The difference between an average value of pixel values of a plurality of pixels around a predetermined number of pixels in the second direction and a pixel value of the pixel is calculated as the second difference amount. The inspection apparatus according to 1. The first calculation unit includes:
Further calculating a flatness representing a change in pixel value with respect to the reference image,
The determination unit
When the flatness is less than a predetermined first threshold and greater than a second threshold, a third threshold corresponding to the flatness is determined, and a pixel value of each pixel of the reference image and each reference image Whether or not there is an abnormality in the inspection target image by determining whether or not a difference between each pixel value of the inspection target image corresponding to each pixel position is equal to or more than the third threshold value. The inspection apparatus according to claim 2, wherein the inspection device is determined. The determination unit
The inspection apparatus according to claim 2, wherein it is determined whether or not there is an abnormality in the inspection target image based on a threshold whose value is changed according to a pixel value. The first calculation unit includes:
For each pixel of the reference image, the pixel value of a pixel located a predetermined number of pixels away from the pixel in a third direction that is substantially orthogonal to the first direction and the third direction from the pixel are approximately A difference between the average value of the pixel value of the pixel located at a predetermined number of pixels away in the fourth direction, which is the opposite direction, and the pixel value of the pixel is further calculated as a third difference amount;
The second calculator is
For each pixel of the inspection target image corresponding to the position of each pixel of the reference image, the pixel value of the pixel at a predetermined number of pixels away from the pixel in the third direction, and the fourth pixel from the pixel. The difference between the average value of the pixel values of the pixels located at a predetermined number of pixels away in the direction of and the pixel value of the pixels is further calculated as a fourth difference amount,
The determination unit
6. The method according to claim 2, further comprising: determining whether or not the inspection target image has an abnormality based on a magnitude of an absolute value of a difference between the third difference amount and the fourth difference amount. The inspection device according to any one of the above. The first calculation unit and the second calculation unit are:
The inspection according to any one of claims 1 to 6, wherein the number of pixels from the pixel to a peripheral pixel to be referred to is changed based on a degree of change in a pixel value of an adjacent pixel in the reference image. apparatus. Acquiring a ripped image of print data as a reference image;
Acquiring a read image of an image printed using the print data as an inspection target image;
For each pixel of the reference image, calculating a first difference amount that is a relative difference from the pixel values of surrounding pixels;
Calculating a second difference amount, which is a relative difference from the pixel values of surrounding pixels, for each pixel of the inspection target image corresponding to each pixel position of the reference image;
Determining whether there is an abnormality in the inspection target image based on a magnitude of an absolute value of a difference between the first difference amount and the second difference amount;
Including inspection methods. Acquiring an image obtained by ripping print data as a reference image;
Obtaining a read image of an image printed using the print data as an inspection target image;
For each pixel of the reference image, calculating a first difference amount that is a relative difference from pixel values of surrounding pixels;
Calculating a second difference amount, which is a relative difference from the pixel values of surrounding pixels, for each pixel of the inspection target image corresponding to each pixel position of the reference image;
Determining whether there is an abnormality in the inspection target image based on the magnitude of the absolute value of the difference between the first difference amount and the second difference amount;
Inspection program to make computer execute.