Inspection device, image forming device, and inspection program

Abstract

To provide an inspection device, an image forming device and an inspection program, which can improve the accuracy of defect detection, as compared with the case where a threshold for detecting defects at edges is simply lowered and a correct-answer image is verified against a target image.SOLUTION: An inspection device includes: a correct-answer image acquisition unit 20 acquiring a correct-answer image; a target image acquisition unit 22 acquiring a target image of an inspection target; a correct-answer image edge extraction unit 24 extracting edge information of the correct-answer image; a target image edge extraction unit 26 extracting edge information of the target image; a comparison unit 28 deriving a difference image between the correct-answer image and the target image; a threshold setting unit 30 setting a threshold for detecting a defect, using the edge information of the correct-answer and target images and the brightness information of the correct-answer image; and a defect detection unit 32 detecting a defect in the target image using the difference image and the threshold.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an inspection apparatus, an image forming apparatus, and an inspection program. [Background technology]

[0002] Patent Document 1 proposes an image inspection device that inspects a read image obtained by reading an image formed and output on a paper surface by an image forming device having multiple image processing functions. In detail, it is proposed that the image inspection device performs image processing according to the information format of the output target image to generate an inspection image, and judges defects in the read image based on the difference between the generated inspection image and the read image. It also proposes extracting edges and changing a threshold value so as to expand the range in which the difference between the inspection image and the read image is allowed for the edge portion. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6007690 Summary of the Invention [Problem to be solved by the invention]

[0004] When comparing a target image with a genuine image to be inspected, if the threshold for detecting defects in the edge portion is lowered, there are cases where defects in the edge portion cannot be detected. Therefore, an object of the present invention is to provide an inspection device, an image forming device, and an inspection program that can improve the accuracy of defect detection compared to a case where the threshold for detecting defects in the edge portion is simply lowered to compare the genuine image with the target image. [Means for solving the problem]

[0005] In order to achieve the above object, an inspection device according to a first aspect includes a processor, and the processor acquires image information of each of a reference image and a target image to be inspected, extracts edge information of each of the reference image and the target image using the acquired image information, derives a difference image between the reference image and the target image, and uses the edge information and brightness information or color information of the reference image to A first threshold value is set to determine whether the image added to the target image is a defect, and a second threshold value is set to determine whether a missing image in the target image is a defect in the correct image. Then, a process of detecting defects in the target image is performed using the difference image and the threshold value.

[0006] In addition, in the inspection device of the second aspect, in the inspection device of the first aspect, when the processor uses the brightness information, it changes it to a predetermined threshold value depending on the presence or absence of edges in the correct image and the target image, and the predetermined brightness or darkness of the correct image.

[0007] In addition, in the inspection device of the third aspect, in the inspection device of the first aspect, when the processor uses the color information, it changes the color information to a predetermined threshold value depending on the presence or absence of edges in the correct image and the target image, and the predetermined brightness and darkness for each color area of ​​the color information.

[0008] Furthermore, in the inspection device according to a fourth aspect, in the inspection device according to the first or third aspect, when the processor uses the color information, it derives a color difference as the difference image.

[0009] In addition, the inspection device according to a fifth aspect is the inspection device according to the first or fourth aspect, wherein when the color information is used, the processor changes the threshold value when a predetermined specific color is present.

[0010] In addition, an inspection device according to a sixth aspect is an inspection device according to any one of the first to fifth aspects, wherein the processor further changes the threshold value using edge surrounding information of a predetermined range of the edges of the correct image and the target image.

[0011] In addition, an inspection device according to a seventh aspect is the inspection device according to any one of the first to sixth aspects, wherein the processor changes the threshold value by further using object information of the correct image.

[0012] In addition, an inspection device according to an eighth aspect is an inspection device according to any one of the first to seventh aspects, in which the processor extracts the edge information by changing an extraction threshold used when extracting the edge information using object information of the correct image.

[0013] In addition, in the inspection device according to a ninth aspect, in the inspection device according to the eighth aspect, the processor changes the extraction threshold to a value that is predetermined for each type of object.

[0014] In addition, an image forming apparatus according to a tenth aspect includes an inspection apparatus according to any one of the first to ninth aspects, an image forming unit that forms an image on a recording medium using image information of the correct image generated in advance, and a reading unit that reads the recording medium on which the image has been formed by the image forming unit and generates image information of the target image.

[0015] In addition, the shoulder chain program according to the eleventh aspect of the present invention is a program for causing a computer to acquire image information of a correct image and a target image of an object to be inspected, extract edge information of the correct image and the target image using the acquired image information, derive a difference image between the correct image and the target image, and calculate a difference between the correct image and the target image using the edge information and brightness information or color information of the correct image. A first threshold value is set to determine whether the image added to the target image is a defect, and a second threshold value is set to determine whether a missing image in the target image is a defect in the correct image. Then, a process of detecting defects in the target image is executed using the difference image and the threshold value. Effect of the Invention

[0016] According to the first aspect, it is possible to provide an inspection device that can improve the defect detection accuracy, compared to a case where a genuine image is matched with a target image by simply lowering a threshold value for detecting defects in edge portions.

[0017] According to the second aspect, it is possible to change the threshold value for detecting defects using edge information of the correct image and the target image, and brightness information of the correct image.

[0018] According to the third aspect, it is possible to change the threshold value for detecting defects using edge information of the correct image and the target image, and color information of the correct image.

[0019] According to the fourth aspect, it is possible to detect defects for each color region.

[0020] According to the fifth aspect, it is possible to change the threshold value for a specific color.

[0021] According to the sixth aspect, it is possible to improve the accuracy of defect detection as compared with the case where the threshold value is changed using only edge information.

[0022] According to the seventh aspect, it is possible to improve the accuracy of defect detection as compared with the case where the threshold value is changed using only edge information.

[0023] According to the eighth aspect, it is possible to extract edge information that matches the object in the correct image.

[0024] According to the ninth aspect, it is possible to change the edge information extraction threshold value to one suitable for the type of object.

[0025] According to the tenth aspect, it is possible to provide an image forming apparatus capable of improving the accuracy of defect detection, compared to a case in which a correct image and a target image are collated by simply lowering a threshold value for detecting defects in edge portions.

[0026] According to the eleventh aspect, it is possible to provide an inspection program capable of improving the accuracy of defect detection, compared to a case in which a genuine image is matched with a target image by simply lowering a threshold value for detecting defects in edge portions. [Brief description of the drawings]

[0027] [Figure 1]1 is a diagram showing a schematic configuration of an inspection device according to an embodiment of the present invention; [Diagram 2] FIG. 2 is a functional block diagram showing the functional configuration of the inspection device according to the present embodiment. [Diagram 3] 1A and 1B are diagrams for explaining erroneous detection of defects occurring near the edges of an image due to differences between a digital image and an analog image; [Figure 4] 13A and 13B are diagrams showing a case where there is an edge only in the target image, and a case where black and white points in the correct image have disappeared during printing and are not present in the target image. [Diagram 5] 1A and 1B are diagrams showing examples of detectable and undetectable defects in a conventional technique that makes it difficult to detect defects by increasing a threshold value for detecting defects in edge portions of a genuine image. [Figure 6] 5 is a flowchart showing an example of a flow of processing performed by the inspection device according to the present embodiment. [Figure 7] 11 is a flowchart showing an example of the flow of a defect determination threshold setting process. [Figure 8] FIG. 13 illustrates an example of a threshold table. [Figure 9] FIG. 13 is a diagram showing an example of a determination threshold value determined in advance for each color region for determining brightness. [Figure 10] FIG. 13 is a diagram illustrating an example of a threshold table when information about the periphery of an edge is used. [Figure 11] 1 is a block diagram showing an example of the configuration of an image forming apparatus having the functions of a printing device and a reading device, the image forming apparatus including an inspection device according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] An example of an embodiment of the present invention will be described in detail below with reference to the drawings. Fig. 1 is a diagram showing a schematic configuration of an inspection device according to this embodiment.

[0029] The inspection device 10 according to the present embodiment performs a process of inspecting an image for defects by comparing a correct image with an image to be inspected. In the following description, the image to be inspected is referred to as a target image.

[0030] Examples of image defects in this embodiment include missing images in the correct image of the target image, image addition due to dust, image distortion, etc. In this embodiment, the correct image is digital image information (e.g., a PDL (page description language) file converted / generated into a raster image) that is the basis of image formation, and the inspection device 10 is described as an example in which the target image for inspection is image information obtained by performing image formation based on the image information of the correct image and reading a recording medium such as paper. Among the defects in the target image, a defect in which an image that is not in the correct image is in the target image is referred to as an addition, and a defect in which an image that is in the correct image but not in the target image is referred to as a missing.

[0031] The inspection device 10 includes a CPU (Central Processing Unit) 10A as an example of a processor, a ROM (Read Only Memory) 10B, a RAM (Random Access Memory) 10C, a storage 10D, an operation unit 10E, a display unit 10F, and a communication line I / F (interface) unit 10G. The CPU 10A controls the overall operation of the inspection device 10. The ROM 10B stores various control programs and various parameters in advance. The RAM 10C is used as a work area when the CPU 10A executes various programs. The storage 10D stores various data and application programs. The operation unit 10E is used to input various information. The display unit 10F is used to display various information. The communication line I / F unit 10G is connectable to an external device and transmits and receives various data to and from the external device. The above-mentioned units of the inspection device 10 are electrically connected to each other by a system bus 10H. In the inspection device 10 according to the present embodiment, the storage 10D is used as a storage unit, but the present invention is not limited to this, and other non-volatile storage units such as a hard disk or a flash memory may be used.

[0032] With the above configuration, the inspection device 10 according to this embodiment executes, by the CPU 10A, access to the ROM 10B, the RAM 10C, and the storage 10D, acquisition of various data via the operation unit 10E, and display of various information on the display unit 10F. Also, the inspection device 10 executes, by the CPU 10A, control of transmission and reception of various data via the communication line I / F unit 10G.

[0033] Here, a description will be given of the functional configuration realized by the CPU 10A of the inspection device 10 executing the program stored in the ROM 10B. Fig. 2 is a functional block diagram showing the functional configuration of the inspection device 10 according to this embodiment.

[0034] As shown in FIG. 2, the inspection device 10 has the functions of a correct image acquisition unit 20, a target image acquisition unit 22, a correct image edge extraction unit 24, a target image edge extraction unit 26, a comparison unit 28, a threshold setting unit 30, a defect detection unit 32, and an output unit 34.

[0035] The correct image acquiring unit 20 acquires a correct image that is a reference for the target image. In this embodiment, the correct image is acquired by acquiring image information of the correct image generated by the print image generating device 12.

[0036] The target image acquisition unit 22 acquires a target image to be inspected. In this embodiment, the target image is acquired by acquiring image information representing the target image obtained by the reading device 16 reading a recording medium such as paper on which an image is formed by the printing device 14, based on image information of a correct image generated by the printing image generation device 12.

[0037] The correct image edge extraction unit 24 performs processing for extracting edges based on the image information of the correct image acquired by the correct image acquisition unit 20, and generates edge information.

[0038] The target image edge extraction section 26 performs processing to extract edges based on the image information of the target image acquired by the target image acquisition section 22, and generates edge information.

[0039] The comparison unit 28 compares the correct image with the target image to align the images, and also compares the correct image with the target image by calculating the difference between the correct image and the target image.

[0040] The threshold setting unit 30 sets a threshold for detecting defects from a difference image between the correct image and the target image. In this embodiment, the threshold setting unit 30 acquires brightness information of the correct image from the image information of the correct image acquired by the correct image acquisition unit 20. In addition, edge information is acquired from each of the correct image edge extraction unit 24 and the target image edge extraction unit 26. Then, the threshold for detecting defects is changed for each pixel using the edge information of the correct image and the target image, and the brightness information or color information of the correct image, and the threshold is set. For example, a predetermined threshold is set for each pixel according to the edge information of the correct image and the target image, and the brightness information or color information of the correct image. Alternatively, a predetermined threshold may be set for each pixel according to the presence or absence of an edge and a combination of light and dark.

[0041] The defect detection unit 32 uses the threshold value set by the threshold value setting unit 30 to perform a process of determining the presence or absence of a defect for each pixel in the difference image between the correct image and the target image.

[0042] The output unit 34 performs processing to obtain the detection result of the defect detection unit 32 and output the detection result of the defect in the target image.

[0043] Incidentally, when performing DA inspection using the inspection device 10 according to this embodiment, erroneous detection of defects is likely to occur near the edges of the images due to the difference between the digital image and the analog image. For example, as shown in Fig. 3, the target image is analog data compared to the digital image of the correct image, and so the edges are rounded. Therefore, when the difference between the correct image and the target image is calculated, the defect detection threshold may be exceeded, resulting in erroneous detection of defects.

[0044] In conventional technology, the threshold for detecting defects in the edge parts of the target image was set high, making it difficult to detect the defects. With conventional technology, as shown in the upper part of Figure 4, if edges (dotted part in the upper part of Figure 4) exist only in the target image, defects are detected without any problem. On the other hand, as shown in the lower part of Figure 4, if black and white dots in the target image disappear in printing and do not exist in the target image, the disappearance in printing cannot be detected if the threshold for the edge part is set high uniquely.

[0045] Specifically, as shown in the first row from the top of Fig. 5, if there is no missing or added image in the edge area indicated by the dotted line, changing the threshold value will prevent the edge from being erroneously detected as a defect. Also, the black dots in the dotted circle area in the second row from the top of Fig. 5 and the white dots in the dotted circle area in the fifth row from the top of Fig. 5 are detected even if the threshold value is high.

[0046] On the other hand, when black or white dots generated by printing in the target image are located near the edge region, such as the dotted circle regions in the third and fifth rows from the top of Figure 5, defects will not be detected if the edge threshold is uniquely increased.

[0047] Therefore, if the edge threshold is uniquely changed, there are cases where missing parts (e.g., characters such as dots), missing parts (e.g., white-filled characters), missing parts of an image in a light background near an edge, and added images in a dark background near an edge are not detected when the correct image has edges.

[0048] Therefore, the inspection device 10 according to the present embodiment performs processing to detect defects in the target image by changing a threshold for detecting defects using edge information of the original image and the target image, and brightness information of the original image. That is, the defect detection accuracy is improved by changing a threshold for defect detection using not only edge information but also brightness information of the original image.

[0049] As a result, as shown in the first row from the top of Figure 5, when edges are present in the reference image and the target image, false detection of the edges can be reduced by changing the defect detection threshold using not only the edge information but also the brightness information of the reference image.

[0050] Furthermore, as shown in the second row from the top of Figure 5 and onwards, even if black or white spots that occur during printing in the target image are located near the edges, in this embodiment, the detection accuracy is improved by setting a low threshold for removal in bright areas and a low threshold for addition in dark areas.

[0051] Next, a specific process performed in the inspection device 10 according to the present embodiment configured as described above will be described. Fig. 6 is a flow chart showing an example of the flow of the process performed in the inspection device 10 according to the present embodiment. Note that the process in Fig. 6 starts when an instruction to start inspection is given by operating the operation unit 10E or the like, for example.

[0052] In step 100, the CPU 10A acquires a correct image, and the process proceeds to step 102. That is, the correct image acquiring unit 20 acquires image information of the correct image generated by the print image generating device 12.

[0053] In step 102, CPU 10A acquires a target image and proceeds to step 104. That is, target image acquisition unit 22 acquires image information representing a target image obtained by reading, by reading device 16, a recording medium such as paper on which an image is formed by printing device 14, based on image information of a correct image generated by print image generation device 12. Note that steps 100 and 102 may be performed in the reverse order.

[0054] In step 104, the CPU 10A extracts edges of the reference image, and the process proceeds to step 106. That is, the reference image edge extraction unit 24 performs processing to extract edges based on the image information of the reference image acquired by the reference image acquisition unit 20, and generates edge information.

[0055] In step 106, CPU 10A extracts edges of the target image and proceeds to step 108. That is, target image edge extraction unit 26 performs processing to extract edges and generate edge information based on image information of the target image acquired by target image acquisition unit 22. Note that steps 104 and 106 may be performed in the reverse order.

[0056] In step 108, CPU 10A aligns the correct image with the target image, and proceeds to step 110. That is, comparison unit 28 aligns the images by comparing the correct image with the target image. Specifically, the image alignment may be surface processing in which the entire surfaces of the correct image and the target image are aligned, pixel processing in which alignment is performed for each pixel, or block processing in which the image is divided into blocks and aligned for each block. Moreover, image alignment may be performed after the images are acquired in steps 100 and 102.

[0057] In step 110, CPU 10A determines the brightness of the correct image and proceeds to step 112. That is, threshold setting unit 30 acquires brightness information of the correct image from the image information of the correct image acquired by correct image acquisition unit 20, and determines the brightness. The brightness of the correct image is determined, for example, by deriving the brightness as 0 to 100, and if the brightness is darker than 50, it is determined to be dark, and if the brightness is 50 or more, it is determined to be bright.

[0058] In step 112, CPU 10A performs a defect determination threshold setting process, and proceeds to step 114. That is, threshold setting unit 30 changes the threshold for detecting defects for each pixel using edge information of the correct image and the target image, and brightness information or color information of the correct image, and sets the threshold. In this embodiment, a process is performed to set a predetermined threshold for each pixel according to edge information of the correct image and the target image, and brightness information of the correct image. Details of the defect determination threshold setting process will be described later.

[0059] In step 114, CPU 10A compares the correct image with the target image, and proceeds to step 116. In this embodiment, comparison unit 28 compares the correct image with the target image by calculating the difference between the correct image and the target image.

[0060] In step 116, CPU 10A performs defect determination and proceeds to step 118. That is, defect detection unit 32 determines the presence or absence of a defect in the image based on the comparison result between the correct image and the target image. The defect determination uses the threshold value set in the defect determination threshold setting process in step 112 to determine the presence or absence of a defect in the image.

[0061] In step 118, CPU 10A judges whether defect judgment has been completed for all pixels. If the judgment is negative, the process returns to step 110 to repeat the above-mentioned process for other pixels. If the judgment is positive, the process proceeds to step 120.

[0062] In step 120, CPU 10A outputs the result of the defect determination in the target image, and ends the series of processes. That is, output unit 34 performs a process of acquiring the detection result of defect detection unit 32 and outputting the detection result of the defect in the target image.

[0063] Next, the above-mentioned defect determination threshold setting process will be described in detail with reference to a flowchart of FIG 7.

[0064] In step 200, the CPU 10A judges whether the correct image is bright or not. This judgment is made by the threshold setting unit 30 based on the result of the judgment of the brightness of the correct image in the above-mentioned step 110. If the judgment is affirmative, the process proceeds to step 202, and if the judgment is negative, the process proceeds to step 216.

[0065] In step 202, the CPU 10A judges whether or not the target image has an edge. The threshold setting unit 30 judges whether or not the target image corresponds to an edge based on the edge information of the target image generated in the above-mentioned step 104. If the judgment is affirmative, the process proceeds to step 204, and if the judgment is negative, the process proceeds to step 210.

[0066] In step 204, CPU 10A judges whether or not there is an edge in the target image. This judgement is made by threshold setting unit 30 judging whether or not the pixel of interest corresponds to an edge based on the edge information of the target image generated in the above-mentioned step 106. If the judgement is affirmative, the process proceeds to step 206, and if the judgement is negative, the process proceeds to step 208.

[0067] In step 206, the CPU 10A sets the drop threshold to a predetermined medium-low and the allocation threshold to a predetermined high. For example, in accordance with the predetermined threshold table shown in Fig. 8, the threshold setting unit 30 sets the drop threshold to 75, which is determined as a medium-low, and the allocation threshold to 150, which is determined as a high, and then proceeds to step 114 in Fig. 6.

[0068] In step 208, the CPU 10A sets the drop threshold to a predetermined medium value and the allocation threshold to a predetermined high value. For example, in accordance with the predetermined threshold table shown in Fig. 8, the threshold setting unit 30 sets the drop threshold to 100, which is determined as medium, and sets the allocation threshold to 150, which is determined as high, and then proceeds to step 114 in Fig. 6.

[0069] On the other hand, in step 210, CPU 10A judges whether or not there is an edge in the target image. In this judgment, threshold setting unit 30 judges whether or not the target pixel corresponds to an edge based on the edge information of the target image generated in the above-mentioned step 106. If the judgment is affirmative, the process proceeds to step 212, and if the judgment is negative, the process proceeds to step 214.

[0070] In step 212, CPU 10A sets the drop threshold to a predetermined low value, and sets the allocation threshold to a predetermined low value. For example, in accordance with the predetermined threshold table shown in Fig. 8, threshold setting unit 30 sets the drop threshold to 50, which is determined as low, and sets the allocation threshold to 50, which is determined as low, and proceeds to step 114 in Fig. 6.

[0071] In step 214, CPU 10A sets the missing threshold to a predetermined value and sets the assigned threshold to a predetermined value. For example, in accordance with the predetermined threshold table shown in Fig. 8, threshold setting unit 30 sets the missing threshold to 100, which is determined as a medium value, and sets the assigned threshold to 100, which is determined as a medium value, and proceeds to step 114 in Fig. 6.

[0072] On the other hand, in step 216, CPU 10A judges whether or not there is an edge in the target image. This judgment is made by threshold setting unit 30 judging whether or not the target image corresponds to an edge based on the edge information of the target image generated in the above-mentioned step 104. If the judgment is affirmative, the process proceeds to step 218, and if the judgment is negative, the process proceeds to step 224.

[0073] In step 218, CPU 10A judges whether or not there is an edge in the target image. This judgement is made by threshold setting unit 30 judging whether or not the pixel of interest corresponds to an edge based on the edge information of the target image generated in the above-mentioned step 106. If the judgement is affirmative, the process proceeds to step 220, and if the judgement is negative, the process proceeds to step 222.

[0074] In step 220, the CPU 10A sets the drop threshold to a predetermined high value and sets the allocation threshold to a predetermined medium-low value. For example, in accordance with the predetermined threshold table shown in Fig. 8, the threshold setting unit 30 sets the drop threshold to 150, which is determined as high, and sets the allocation threshold to 75, which is determined as medium-low, and then proceeds to step 114 in Fig. 6.

[0075] In step 222, the CPU 10A sets the drop threshold to a predetermined high value and sets the allocation threshold to a predetermined medium value. For example, in accordance with the predetermined threshold table shown in Fig. 8, the threshold setting unit 30 sets the drop threshold to 150, which is determined as high, and sets the allocation threshold to 100, which is determined as medium, and then proceeds to step 114 in Fig. 6.

[0076] On the other hand, in step 224, CPU 10A judges whether or not there is an edge in the target image. In this judgment, threshold setting unit 30 judges whether or not the target pixel corresponds to an edge based on the edge information of the target image generated in the above-mentioned step 106. If the judgment is affirmative, the process proceeds to step 226, and if the judgment is negative, the process proceeds to step 228.

[0077] In step 226, CPU 10A sets the drop threshold to a predetermined low value, and sets the allocation threshold to a predetermined low value. For example, in accordance with the predetermined threshold table shown in Fig. 8, threshold setting unit 30 sets the drop threshold to 50, which is determined as low, and sets the allocation threshold to 50, which is determined as low, and proceeds to step 114 in Fig. 6.

[0078] In step 228, CPU 10A sets the missing threshold to a predetermined value and sets the assigned threshold to a predetermined value. For example, in accordance with the predetermined threshold table shown in Fig. 8, threshold setting unit 30 sets the missing threshold to 100, which is determined as a medium value, and sets the assigned threshold to 100, which is determined as a medium value, and proceeds to step 114 in Fig. 6.

[0079] In the above embodiment, the threshold for detecting defects is changed using edge information of the correct image and the target image, and brightness information of the correct image, but color information may be used instead of brightness information. Here, color information includes brightness information.

[0080] When color information is used, for example, a RIP (Raster Image Processor) image is used as the correct image, and an image obtained by printing the correct image with a printing device 14 and reading the original with a reading device 16 is used as the target image. In addition, the correct image and the target image are assumed to be in the Lab color space, for example.

[0081] Then, edge extraction is performed on the L surface or all the Lab surfaces, and the brightness judgment in the processes of Figs. 6 and 7 is changed to a brightness judgment for each color region. For the brightness judgment, a judgment threshold value determined in advance for each color region is used, as shown in Fig. 9. In the example of Fig. 9, the Y (yellow) region uses the line connecting the brightness of K (black) at 50% and the saturation of Y at 50% as the brightness judgment threshold. Furthermore, the M (magenta) region uses the line connecting the brightness of K at 50% and the saturation of M at 50% as the brightness judgment threshold. Furthermore, the C (cyan) region uses the line connecting the brightness of K at 50% and the saturation of C at 50% as the brightness judgment threshold.

[0082] Furthermore, when comparing the correct image with the target image, the difference image is calculated using the color difference ΔE, and defect determination is performed in the same manner as in the above embodiment.

[0083] In this case, the predetermined threshold value may be changed for a specific color. That is, the threshold value may be changed for a specific Lab value. For example, the threshold value for white may be changed to a stricter threshold value than the other colors, the threshold value for red may be changed to a stricter threshold value, and the threshold value for blue may be changed to a looser threshold value.

[0084] In the above embodiment, the threshold for detecting defects is changed using edge information of the correct image and the target image, and brightness information of the correct image, but at least one of edge periphery information and object information may be used in addition to edge information. As edge periphery information, for example, information on an area extended from an edge portion by several pixels (for example, one or two pixels) is used. The number of pixels extended from an edge portion may be changed according to the resolution. For example, the number of pixels may be increased as the extended resolution becomes higher.

[0085] When edge periphery information is further used in addition to the above embodiment, the threshold is changed according to the threshold table shown in Fig. 10. Fig. 10 is a diagram showing an example of the threshold table when edge periphery information is used.

[0086] In the example of the threshold table in Figure 10, if the correct image has no edges, no extended edges, the target image has no edges, no extended edges, and the correct image is bright, the missing threshold is set to 100 and the addition threshold is set to 100.

[0087] In addition, when the correct image has no edges, no extended edges, the target image has no edges, no extended edges, and the correct image is dark, the missing threshold is set to 100 and the addition threshold is set to 100.

[0088] In addition, when the correct image has no edges, no extended edges, the target image has no edges, has extended edges, and the correct image is bright, the threshold for missing is set to 75 and the threshold for adding is set to 75.

[0089] In addition, when the correct image has no edges, no extended edges, the target image has no edges, has extended edges, and the correct image is dark, the threshold for missing is set to 75 and the threshold for adding is set to 75.

[0090] In addition, when the correct image has no edges and no extended edges, the target image has edges and extended edges, and the correct image is bright, the threshold for missing is set to 50 and the threshold for adding is set to 50.

[0091] In addition, if the correct image has no edges and no extended edges, the target image has edges and extended edges, and the correct image is dark, the missing threshold is set to 50 and the addition threshold is set to 50.

[0092] In addition, if the correct image has no edges and has extended edges, the target image has no edges and no extended edges, and the correct image is bright, the missing threshold is set to 100 and the addition threshold is set to 125.

[0093] In addition, if the correct image has no edges and has extended edges, the target image has no edges and no extended edges, and the correct image is dark, the missing threshold is set to 125 and the addition threshold is set to 100.

[0094] In addition, when the correct image has no edges and has extended edges, the target image has no edges and has extended edges, and the correct image is bright, the threshold for missing is set to 87.5 and the threshold for adding is set to 125.

[0095] In addition, when the correct image has no edges and has extended edges, the target image has no edges and has extended edges, and the correct image is dark, the threshold for missing is set to 125 and the threshold for adding is set to 87.5.

[0096] In addition, when the correct image has no edges, has extended edges, the target image has edges, has extended edges, and the correct image is bright, the threshold for missing is set to 81.25 and the threshold for adding is set to 137.5.

[0097] In addition, when the correct image has no edges, has extended edges, the target image has edges, has extended edges, and the correct image is dark, the threshold for missing is set to 137.5 and the threshold for adding is set to 81.25.

[0098] In addition, when the correct image has an edge and an extended edge, the target image has no edge and no extended edge, and the correct image is bright, the threshold for missing is set to 100 and the threshold for adding is set to 150.

[0099] In addition, when the correct image has edges and extended edges, the target image has no edges and no extended edges, and the correct image is dark, the threshold for missing is set to 150 and the threshold for adding is set to 100.

[0100] In addition, when the correct image has edges and extended edges, the target image has no edges and extended edges, and the correct image is bright, the threshold for missing is set to 81.25 and the threshold for adding is set to 137.5.

[0101] In addition, when the correct image has edges and extended edges, the target image has no edges, has extended edges, and the correct image is dark, the threshold for missing is set to 137.5 and the threshold for adding is set to 81.25.

[0102] In addition, when the correct image has an edge, an extended edge, the target image has an edge, an extended edge, and the correct image is bright, the threshold for missing is set to 75 and the threshold for adding is set to 150.

[0103] In addition, when the correct image has an edge, an extended edge, the target image has an edge, an extended edge, and the correct image is dark, the threshold for missing is set to 150 and the threshold for adding is set to 75.

[0104] Furthermore, when changing the threshold value using object information in addition to edge information, a predetermined threshold value may be set for each type of object, such as text, graphics, images, etc. For example, since false detection of defects is more likely to occur at the edges of text and graphics than images, a higher threshold value may be set for text and graphics than for images, making it more difficult to detect defects.

[0105] In addition, in each of the answer image edge extraction unit 24 and the target image edge extraction unit 26, when extracting edges, the extraction threshold used when extracting edges using object information may be changed. For example, the extraction threshold is changed to a value that is predetermined for each type of object. Specifically, when the object information is text and graphics, the edge extraction threshold is set to a higher threshold than that for images, and when the object information is images, the threshold is set to a lower threshold than that for text and graphics. In this way, edge extraction suited to the object is performed.

[0106] The inspection device 10 according to the present embodiment may be included in an image forming device having the functions of the printing device 14 and the reading device 16. Alternatively, the inspection device 10 may be included in an image forming device having the functions of the printing device 14 or the reading device 16.

[0107] Here, a configuration of an image forming apparatus will be described in a case where an inspection apparatus 10 is included in an image forming apparatus 50 having the functions of a printing apparatus 14 and a reading apparatus 16. Fig. 11 is a block diagram showing an example of a configuration of an image forming apparatus in a case where an inspection apparatus 10 according to this embodiment is included in an image forming apparatus 50 having the functions of a printing apparatus 14 and a reading apparatus 16.

[0108] As shown in FIG. 11, the image forming apparatus 50 includes a display operation unit 52, a control unit 54, an image generating unit 56, a forming unit 58, and a discharging unit 60.

[0109] The display operation unit 52 includes a display unit such as a liquid crystal display and an operation unit for making various settings related to image formation. For example, by operating the display operation unit 52, various settings such as various conditions for image formation and the type of recording medium on which the image is formed are made.

[0110] The control unit 54 comprehensively controls each part of the image forming apparatus 50, and controls each part of the image forming apparatus 50 according to the contents set on the display operation unit 52. The control unit 54 is composed of, for example, a microcomputer equipped with a CPU, a ROM, a RAM, and an input / output unit. A program for controlling the operation for forming an image is stored in the ROM in advance, and the operation of each part of the image forming apparatus 50 is controlled by the program being loaded into the RAM and executed by the CPU.

[0111] The image generating unit 56 generates image information representing the document image by reading the document image. Alternatively, the image generating unit 56 generates image information of the document image to be image-formed by acquiring image information transmitted from an external computer. Then, the inspection device 10 acquires the image information generated by the image generating unit 56 as a correct image.

[0112] The forming section 58 includes a paper feed section 62, a conveying section 64, an image processing section 66, an image forming section 68, a fixing section 70, and an image reading section 72 as a reading section.

[0113] The paper feed section 62 stores recording paper as a recording medium and supplies the recording paper to the transport section 64. For example, the paper feed section 62 stores recording paper wound in a roll, and the recording paper is pulled out and supplied to the transport section. Alternatively, the paper feed section 62 includes a plurality of storage sections for storing paper of different sizes and types, and the paper is pulled out from the main section and supplied to the transport section. In this case, the paper set on the display operation section 52 or the like is supplied from each storage section to the transport section 64. Also, when image information is obtained from the outside, the paper of the type specified from the outside is supplied from each storage section to the transport section 64.

[0114] The transport section 64 transports the recording paper or paper supplied by the paper feed section 62 to a position where an image is formed on the recording paper or paper, and transports the recording paper or paper with the image formed thereon to the discharge section 60.

[0115] The image processing unit 66 receives image information generated by the image generation unit 56 or received by the image generation unit 56 from outside, performs image processing for processing by the image forming unit 68, and outputs the image information after image processing to the image forming unit 68.

[0116] Image forming unit 68 receives image information from image processing unit 66 and forms an image represented by the image information on recording paper or paper. For example, image forming unit 68 may employ an electrophotographic method to transfer an image onto recording paper or paper, or may employ an inkjet method or the like to eject ink onto recording paper or paper to form an image.

[0117] The fixing unit 70 performs a process for fixing the image onto the recording paper by applying at least one of pressure and heat to the recording paper or paper on which the image has been formed, thereby fixing the image onto the recording paper or paper.

[0118] The image reading unit 72 reads the recording paper or paper on which an image is formed, and obtains image information for performing various corrections (e.g., misalignment correction, color correction, etc.). The image information obtained by reading the image reading unit 72 is also obtained by the inspection device 10.

[0119] The discharge section 60 also winds up the recording paper on which an image has been formed in a roll and stores it therein, or discharges the paper on which an image has been formed.

[0120] In the above embodiment, an example has been described in which digital image information on which image formation is based is used as a correct image, and the image to be inspected is image information obtained by performing image formation based on the image information of the correct image and reading a recording medium such as paper. However, the present invention may also be applied to an inspection device that performs AA (analog-analog) inspection in which image information obtained by reading a predetermined standard correct image is used as the correct image instead of a digital correct image.

[0121] In each of the above embodiments, the term "processor" refers to a processor in a broad sense, including general-purpose processors (e.g., CPU: Central Processing Unit, etc.) and dedicated processors (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

[0122] In addition, the operations of the processor in each of the above embodiments may be performed not only by one processor, but also by multiple processors located at physically separate locations working together. Furthermore, the order of the operations of the processor is not limited to the order described in each of the above embodiments, and may be changed as appropriate.

[0123] The processing performed by the inspection device 10 according to the above embodiment may be processing performed by software, processing performed by hardware, or a combination of both. The processing performed by each part of the inspection device 10 may be stored as a program in a storage medium and distributed.

[0124] Furthermore, the present invention is not limited to the above, and it goes without saying that various modifications can be made without departing from the spirit and scope of the present invention. [Explanation of symbols]

[0125] 10 Inspection equipment 10A CPU 12 Printing image generation device 14 Printing device 16 Reading device 20 Correct image acquisition section 22 Target image acquisition unit 24. Ground truth image edge extraction section 26 Target image edge extraction unit 28 Comparison section 30 Threshold setting unit 32 Defect detection section 50 Image forming device 68 Image forming section 72 Image reading unit

Claims

1. a processor, the processor comprising: Acquire image information of each of the correct image and the target image to be inspected; Extracting edge information of each of the original image and the target image using the acquired image information; Derive a difference image between the correct image and the target image; An inspection device that uses the edge information and brightness information or color information of the correct image to set a first threshold value used to determine whether the image assigned to the target image is defective, and a second threshold value used to determine whether an image gap in the target image compared to the correct image is a defect, and performs a process to detect defects in the target image using the difference image and the threshold values.

2. The inspection device according to claim 1 , wherein when the processor uses the brightness information, it changes the brightness information to a predetermined threshold value depending on the presence or absence of edges in the original image and the target image, and on a predetermined brightness or darkness of the original image.

3. The inspection device according to claim 1 , wherein when the processor uses the color information, it changes the threshold value to a predetermined value depending on the presence or absence of edges in the correct image and the target image, and on the brightness or darkness of each color area of ​​the color information.

4. The inspection apparatus according to claim 1 or 3, wherein the processor derives a color difference as the difference image when the color information is used.

5. 5. The inspection device according to claim 1, wherein the processor, when using the color information, changes the threshold value when a predetermined specific color is detected.

6. 6. The inspection device according to claim 1, wherein the processor changes the threshold value by further using edge peripheral information of a predetermined range of the edges of the original image and the target image.

7. 7. The inspection device according to claim 1, wherein the processor changes the threshold value by further using object information of the correct image.

8. 8. The inspection device according to claim 1, wherein the processor extracts the edge information by changing an extraction threshold used when extracting the edge information using object information of the correct image.

9. The inspection device according to claim 8 , wherein the processor changes the extraction threshold to a value that is predetermined for each type of object.

10. An inspection device according to any one of claims 1 to 9; an image forming unit that forms an image on a recording medium using image information of the correct image that has been generated in advance; a reading unit that reads the recording medium on which an image has been formed by the image forming unit and generates image information of the target image; An image forming apparatus comprising:

11. On the computer, Acquire image information of the correct image and the target image to be inspected, Extracting edge information of each of the original image and the target image using the acquired image information; Derive a difference image between the correct image and the target image; An inspection program for executing a process of detecting defects in the target image using the difference image and the thresholds, by using the edge information and brightness information or color information of the correct image to set a first threshold value used to determine whether an image assigned to the target image is defective, and a second threshold value used to determine whether an image gap in the target image compared to the correct image is defective, and

Images