Inspection apparatus, image forming apparatus, storage medium and inspection method

Abstract

This invention provides an inspection apparatus, an image forming apparatus, a storage medium, and an inspection method, which improve defect detection accuracy compared to simply lowering the threshold for detecting defects at the edges to verify a correct image and an object image. An inspection apparatus includes a processor that performs the following processing: acquiring image information of a correct image and an object image of the object to be inspected; extracting edge information of the correct image and the object image using the acquired image information; deriving a difference image between the correct image and the object image; changing the defect detection threshold using the edge information and brightness or color information of the correct image; and detecting defects in the object image using the difference image and the threshold.

Description

Technical Field

[0001] This invention relates to an inspection apparatus, an image forming apparatus, a storage medium, and an inspection method. Background Technology

[0002] Patent Document 1 discloses an image inspection device that inspects a read image obtained by reading an image output from an image forming apparatus on paper using multiple image processing functions. Specifically, the device performs image processing corresponding to the information format of the output object image to generate an inspection image, and determines defects in the read image based on the difference between the generated inspection image and the read image. Furthermore, it proposes that edges be extracted and thresholds be adjusted for edge portions to broaden the permissible range of difference between the inspection image and the read image.

[0003] Patent Document 1: Japanese Patent No. 6007690

[0004] When verifying a correct image against an object image of the object being inspected, lowering the threshold for detecting defects at the edges can sometimes prevent the detection of edge defects. Therefore, the object of this invention is to provide an inspection apparatus, image forming apparatus, storage medium, and inspection method that improves the accuracy of defect detection compared to simply lowering the threshold for detecting edge defects when verifying a correct image against an object image. Summary of the Invention

[0005] To achieve the above objectives, the inspection device according to the first method includes a processor that performs the following processing: acquiring image information of a correct image and an object image of the object to be inspected; extracting edge information of the correct image and the object image using the acquired image information; deriving a difference image between the correct image and the object image; changing a threshold for detecting defects using the edge information and the brightness or color information of the correct image; and detecting defects in the object image using the difference image and the threshold.

[0006] Furthermore, in the inspection apparatus according to the first method, in the inspection apparatus according to the second method, when the brightness information is used, the processor changes to a predetermined threshold based on the presence or absence of edges of the correct image and the object image, as well as the predetermined brightness of the correct image.

[0007] Furthermore, in the inspection apparatus according to the first method, in the inspection apparatus according to the third method, when the color information is used, the processor changes to a predetermined threshold based on the presence or absence of edges of the correct image and the object image, and the brightness or darkness predetermined for each color region of the color information.

[0008] Furthermore, in the inspection apparatus according to the first or third method, in the inspection apparatus according to the fourth method, when the color information is used, the processor outputs the color difference as the difference image.

[0009] Furthermore, according to the inspection apparatus of the first or fourth method, in the inspection apparatus of the fifth method, when the color information is used, the processor changes the threshold for a predetermined specific color.

[0010] Furthermore, in the inspection apparatus according to any of the first to fifth methods, in the inspection apparatus according to the sixth method, the processor further uses edge perimeter information of a predetermined range of the edges of the correct image and the object image to change the threshold.

[0011] Furthermore, in the inspection apparatus according to any of the first to sixth methods, in the inspection apparatus according to the seventh method, the processor also uses the object information of the correct image to change the threshold.

[0012] Furthermore, in the inspection apparatus according to any of the first to seventh methods, in the inspection apparatus according to the eighth method, the processor uses the object information of the correct image to change the extraction threshold when extracting the edge information, thereby extracting the edge information.

[0013] Furthermore, according to the inspection apparatus of the eighth method, in the inspection apparatus of the ninth method, the processor is changed to the extraction threshold of a value predetermined for each type of object.

[0014] Furthermore, the image forming apparatus according to the 10th method includes: the inspection device described in any one of the 1st to 9th methods; an image forming unit that forms an image on a recording medium using image information of the pre-generated correct image; and a reading unit that reads the image information of the recording medium on which the image has been formed by the image forming unit to generate the object image.

[0015] Furthermore, the storage medium involved in the 11th method stores an inspection program for causing a computer to perform the following processes: acquiring image information of a correct image and an object image of the object to be inspected, extracting edge information of the correct image and the object image using the acquired image information, deriving a difference image between the correct image and the object image, changing a threshold for detecting defects using the edge information and the brightness or color information of the correct image, and detecting defects in the object image using the difference image and the threshold.

[0016] Furthermore, the inspection method involved in the 12th method includes the following steps: acquiring image information of a correct image and an object image of the object to be inspected; extracting edge information of the correct image and the object image using the acquired image information; exporting a difference image between the correct image and the object image; and changing the threshold for detecting defects using the edge information and the brightness or color information of the correct image, and using the difference image and the threshold to detect defects in the object image.

[0017] Invention Effects

[0018] According to the first method, an inspection device can be provided that improves the detection accuracy of defects compared to simply lowering the threshold for detecting defects at the edge to verify the correct image against the object image.

[0019] According to the second method, the threshold for detecting defects can be changed using edge information of the correct image and the object image, as well as brightness information of the correct image.

[0020] According to the third method, the threshold for detecting defects can be changed using edge information of the correct image and the object image, as well as color information of the correct image.

[0021] According to method 4, defects can be detected for each color area.

[0022] According to method 5, it is possible to change the threshold for a specific color.

[0023] According to method 6, the detection accuracy of defects can be improved compared to using only edge information to change the threshold.

[0024] According to method 7, the detection accuracy of defects can be improved compared to using only edge information to change the threshold.

[0025] According to method 8, edge information corresponding to the object in the correct image can be extracted.

[0026] According to method 9, the threshold for extracting edge information can be changed to be suitable for the type of object.

[0027] According to the 10th method, an image forming apparatus can be provided that improves the detection accuracy of defects compared to simply lowering the threshold for detecting defects at the edge to verify the correct image against the object image.

[0028] According to the 11th method, a storage medium can be provided that improves the detection accuracy of defects compared to simply lowering the threshold for detecting defects at the edges to verify the correct image against the object image.

[0029] According to the 12th method, an inspection method can be provided that improves the detection accuracy of defects compared to simply lowering the threshold for detecting defects at the edges to verify the correct image against the object image. Attached Figure Description

[0030] The embodiments of the present invention will be described in detail with reference to the following figures.

[0031] Figure 1 This is a diagram showing the schematic structure of the inspection device according to this embodiment;

[0032] Figure 2 This is a functional block diagram illustrating the functional structure of the inspection device involved in this embodiment;

[0033] Figure 3 This is a diagram used to illustrate error detection of defects near the edges of an image caused by the difference between digital and analog images;

[0034] Figure 4 This is a diagram that represents the case where only edges exist in the object image and the case where black or white dots that exist in the correct image disappear in the print and do not exist in the object image.

[0035] Figure 5 This is a diagram illustrating examples of defects that can be detected and those that cannot be detected in existing techniques that raise the threshold for defects in the edge portions of correctly detected images, making defects difficult to detect.

[0036] Figure 6 This is a flowchart illustrating an example of the processing flow performed by the inspection apparatus according to this embodiment;

[0037] Figure 7 This is a flowchart illustrating an example of the process for setting defect judgment thresholds;

[0038] Figure 8 This is a diagram representing an example of a threshold table;

[0039] Figure 9 This is a diagram illustrating an example of a predetermined threshold for each color region used to determine brightness.

[0040] Figure 10 This is a diagram illustrating an example of a threshold table when using edge perimeter information;

[0041] Figure 11 This is a block diagram illustrating an example of the structure of an image forming apparatus that includes the inspection device according to this embodiment, and is equipped with a printing device and a reading device.

[0042] Symbol Explanation

[0043] 10-Inspection device, 10A-CPU, 12-Image generation device for printing, 14-Printing device, 16-Reading device, 20-Correct image acquisition unit, 22-Object image acquisition unit, 24-Correct image edge extraction unit, 26-Object image edge extraction unit, 28-Comparison unit, 30-Threshold setting unit, 32-Defect detection unit, 50-Image forming device, 68-Image forming unit, 72-Image reading unit. Detailed Implementation

[0044] Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the accompanying drawings. Figure 1 This is a diagram showing the schematic structure of the inspection device involved in this embodiment.

[0045] The inspection apparatus 10 according to this embodiment performs a process of detecting image defects by comparing a correct image with an image of the object to be inspected. Furthermore, in the following description, the image of the object to be inspected will be referred to as the object image.

[0046] As an example of image defects in this embodiment, there are defects such as missing images of the object image relative to the correct image, image addition caused by dust, and image distortion. Furthermore, in this embodiment, as an example, an inspection device 10 will be described. This inspection device 10 checks the digital image information (e.g., information obtained by transforming / generating a PDL (page description language) file into a raster image) that will form the basis of image formation, treating it as the correct image, and checks the object image being inspected as image information obtained by forming an image based on the image information of the correct image and reading it from a recording medium such as paper. In addition, among defects in the object image, the defect of having an image that is not present in the correct image but is present in the object image is called addition, and the defect of having an image that is present in the correct image but not in the object image is called missing.

[0047] The inspection device 10 includes, as an example, a CPU (Central Processing Unit) 10A, a ROM (Read Only Memory) 10B, a RAM (Random Access Memory) 10C, a memory 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 pre-stores various control programs and parameters. The RAM 10C serves as a working area when the CPU 10A executes various programs. The memory 10D stores various data or 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 can be connected to external devices to transmit and receive various data. All the components of the inspection device 10 are electrically connected to each other via a system bus 10H. In addition, in the inspection device 10 according to this embodiment, the memory 10D is used as the storage unit, but it is not limited to this, and other non-volatile storage units such as hard disks or flash memory can also be used.

[0048] Based on the above structure, the inspection device 10 according to this embodiment performs access to the ROM 10B, RAM 10C and memory 10D via the CPU 10A, acquires various data via the operation unit 10E, and displays various information on the display unit 10F. Furthermore, the inspection device 10 performs control over the transmission and reception of various data via the communication line I / F unit 10G via the CPU 10A.

[0049] Here, the functional structure implemented by the CPU 10A of the inspection device 10 executing the program stored in the ROM 10B will be described. Figure 2 This is a functional block diagram illustrating the functional structure of the inspection device 10 involved in this embodiment.

[0050] like Figure 2 As shown, the inspection device 10 has the functions of a correct image acquisition unit 20, an object image acquisition unit 22, a correct image edge extraction unit 24, an object image edge extraction unit 26, a comparison unit 28, a threshold setting unit 30, a defect detection unit 32, and an output unit 34.

[0051] The correct image acquisition unit 20 acquires a correct image that serves as a reference relative to the object image. In this embodiment, the correct image acquisition unit acquires image information of the correct image generated by the printing image generation apparatus 12.

[0052] The object image acquisition unit 22 acquires the object image that is the object to be inspected. In this embodiment, object image acquisition means that the object image information is obtained by reading the image information of the paper or other recording medium from which the image is formed by the printing device 14 based on the image information of the correct image generated by the printing image generation device 12, which is read by the reading device 16.

[0053] The correct image edge extraction unit 24 generates edge information by performing edge extraction processing based on the image information of the correct image acquired by the correct image acquisition unit 20.

[0054] The object image edge extraction unit 26 generates edge information by performing edge extraction processing on the image information of the object image acquired by the object image acquisition unit 22.

[0055] The comparison unit 28 compares the correct image with the target image to perform image alignment, and compares the correct image with the target image by calculating the difference between the correct image and the target image.

[0056] The threshold setting unit 30 sets a threshold for detecting defects based on the difference image between the correct image and the target image. In this embodiment, the threshold setting unit 30 obtains the brightness information of the correct image from the image information of the correct image obtained by the correct image acquisition unit 20. Furthermore, it obtains edge information from the correct image edge extraction unit 24 and the target image edge extraction unit 26, respectively. Then, using the edge information of the correct image and the target image, as well as the brightness information or color information of the correct image, the threshold for detecting defects is set by changing the threshold for each pixel. For example, a predetermined threshold is set for each pixel based on the edge information of the correct image and the target image, as well as the brightness information or color information of the correct image. Alternatively, a predetermined threshold can be set for each pixel based on the presence or absence of edges and the combination of brightness and darkness.

[0057] The defect detection unit 32 performs the following processing: using the threshold set by the threshold setting unit 30, it determines whether there is a defect in the difference image between the correct image and the object image for each pixel.

[0058] The output unit 34 performs the processing of acquiring the detection results of the defect detection unit 32 and outputting the defect detection results of the object image.

[0059] However, when performing DA inspection as described in the inspection apparatus 10 of this embodiment, erroneous detection of defects can easily occur near the edges of the image due to the difference between the digital and analog images. For example, as Figure 3 As shown, compared to the correct digital image, the object image is a simulated image and is deformed at the edges. Therefore, if the difference between the correct image and the object image is calculated, it will exceed the defect detection threshold, and sometimes the defect will be falsely detected.

[0060] In existing technologies, increasing the threshold for detecting defects in the edge regions of a correctly detected image makes defects harder to detect. In existing technologies, such as... Figure 4 As shown in the previous paragraph, when only the object image has an edge ( Figure 4 When examining the dotted line section above, defects will be detected without any issues. On the other hand, as... Figure 4 As shown in the next paragraph, when black or white dots that exist in the correct image disappear in the print and do not exist in the object image, if the threshold of the edge is increased only, the disappearance in the print cannot be detected.

[0061] Specifically, such as from Figure 5 As shown in the first paragraph above, when there are no missing or added images in the edge region indicated by the dotted line, changing the threshold will prevent the edge from being incorrectly detected as a defect. Furthermore, even with a high threshold, from Figure 5 The black dots in the circled area of ​​the second segment of the dotted line from the top and from... Figure 5 The white dots in the circled area of ​​the dotted line starting from the 5th segment on the top side will also be detected.

[0062] On the other hand, as from Figure 5 Similar to the circled area of ​​the dotted lines starting from the 3rd and 4th segments on the upper side, when black or white dots generated by printing in the object image exist near the edge area, if the edge threshold is uniquely increased, the defect will not be detected.

[0063] Therefore, if the threshold of the edge is changed only, sometimes missing edges (e.g., characters such as dots), fillings (e.g., hollow characters), missing images in a bright background near the edge, and images assigned to a dark background near the edge will not be detected when the edge exists in the correct image.

[0064] Therefore, the inspection apparatus 10 according to this embodiment performs the following processing: it detects defects in the object image by changing the defect detection threshold using edge information of the correct image and the object image, as well as brightness information of the correct image. That is, it changes the defect detection threshold not only using edge information but also using brightness information of the correct image, thereby improving the defect detection accuracy.

[0065] Therefore, as from Figure 5 As shown in the first paragraph above, when there are edges in both the correct image and the object image, not only edge information but also brightness information of the correct image is used to change the threshold for defect detection, thereby reducing false detection of edges.

[0066] Furthermore, as from Figure 5As shown from the second paragraph onwards from the top, even when black or white dots generated by printing exist near the edge in the object image, in this embodiment, the detection accuracy is improved by setting a lower threshold for missing dots in bright areas and a lower threshold for assigned dots in dark areas.

[0067] Next, the specific processing performed by the inspection device 10 according to this embodiment, configured as described above, will be explained. Figure 6 This is a flowchart illustrating an example of the processing flow performed by the inspection apparatus 10 according to this embodiment. Additionally, Figure 6 The process begins, for example, through the operation of the operation unit 10E, when the instruction to start the inspection is given.

[0068] In step S100, CPU 10A acquires the correct image and proceeds to step S102. That is, the correct image acquisition unit 20 acquires the image information of the correct image generated by the printing image generation device 12.

[0069] In step S102, CPU 10A acquires the object image and proceeds to step S104. That is, the object image acquisition unit 22 acquires image information representing the object image, which is obtained by the reading device 16 reading the image information of the correct image generated by the printing image generation device 12, and then using a recording medium such as paper from which the image is formed by the printing device 14. Furthermore, the order of steps S100 and S102 can be reversed.

[0070] In step S104, CPU 10A extracts the edges of the correct image and proceeds to step S106. That is, the correct image edge extraction unit 24 generates edge information by performing edge extraction processing based on the image information of the correct image acquired by the correct image acquisition unit 20.

[0071] In step S106, CPU 10A extracts the edges of the object image and proceeds to step S108. That is, the object image edge extraction unit 26 generates edge information by performing edge extraction processing based on the image information of the object image acquired by the object image acquisition unit 22. Furthermore, the order of steps S104 and S106 can be reversed.

[0072] In step S108, the CPU 10A performs alignment between the correct image and the target image and proceeds to step S110. That is, the comparison unit 28 compares the correct image and the target image to perform image alignment. Specifically, image alignment can be a face-by-face process that aligns the entire face of the correct image and the target image, a pixel-by-pixel process that aligns each pixel, or a block-by-block process that divides the image into blocks and aligns each block. Furthermore, image alignment can also be performed after the image has been acquired through steps S100 and S102.

[0073] In step S110, CPU 10A determines the brightness of the correct image and proceeds to step S112. That is, the threshold setting unit 30 obtains the brightness information of the correct image from the image information of the correct image acquired by the correct image acquisition unit 20 to determine the brightness. Regarding the determination of the brightness of the correct image, for example, the brightness is derived by setting the brightness to 0 to 100. When the brightness is less than 50, it is determined to be dark, and when the brightness is 50 or more, it is determined to be bright.

[0074] In step S112, the CPU 10A performs a defect determination threshold setting process and proceeds to step S114. That is, the threshold setting unit 30 uses edge information of the correct image and the object image, as well as brightness or color information of the correct image, to set a threshold by changing the defect detection threshold for each pixel. In this embodiment, the following process is performed: a predetermined threshold is set for each pixel based on the edge information of the correct image and the object image, and the brightness information of the correct image. Further details regarding the defect determination threshold setting process will be described later.

[0075] In step S114, CPU 10A compares the correct image with the object image and proceeds to step S116. In this embodiment, the comparison unit 28 compares the correct image with the object image by calculating the difference between the correct image and the object image.

[0076] In step S116, CPU 10A performs defect determination and proceeds to step S118. That is, the defect detection unit 32 determines whether there is an image defect based on the comparison result between the correct image and the object image. In the defect determination, the threshold set in the defect determination threshold setting process in step S112 is used to determine whether there is an image defect.

[0077] In step S118, CPU10A determines whether defect determination has been completed for all pixels. If the determination is negative, it returns to step S110 and repeats the above process for other pixels. If the determination is positive, it proceeds to step S120.

[0078] In step S120, the CPU 10A outputs the result of determining the defects in the object image and ends a series of processes. That is, the output unit 34 performs the process of acquiring the detection result of the defect detection unit 32 and outputting the detection result of the defects in the object image.

[0079] Next, the above-mentioned defect judgment threshold setting process will be explained in detail. Figure 7 This is a flowchart illustrating an example of the process for setting defect judgment thresholds.

[0080] In step S200, the CPU 10A determines whether the correct image is bright. In this determination, the threshold setting unit 30 makes the determination based on the brightness determination result of the correct image in step S110 above. When the determination is affirmative, the process proceeds to step S202; when it is negative, the process proceeds to step S216.

[0081] In step S202, CPU 10A determines whether an edge exists in the correct image. In this determination, the threshold setting unit 30 determines whether the pixel of interest corresponds to an edge based on the edge information of the correct image generated in step S104. If the determination is affirmative, the process proceeds to step S204; if it is negative, the process proceeds to step S210.

[0082] In step S204, CPU 10A determines whether an edge exists in the object image. In this determination, the threshold setting unit 30 determines whether the pixel of interest corresponds to an edge based on the edge information of the object image generated in step S106. If the determination is affirmative, the process proceeds to step S206; if it is negative, the process proceeds to step S208.

[0083] In step S206, CPU10A sets the missing threshold to a predetermined low-to-medium level and the assign threshold to a predetermined high level. For example, according to... Figure 8 The threshold setting unit 30 sets the missing threshold to 75 (determined to be low-medium) and assigns a threshold to 150 (determined to be high) and then moves to the threshold table shown. Figure 6 Step S114.

[0084] In step S208, CPU10A sets the missing threshold to a predetermined medium value and the assign threshold to a predetermined high value. For example, according to... Figure 8 The threshold setting unit 30 sets the missing threshold to 100 (which is determined to be in the middle) and assigns the high threshold to 150 (which is determined to be high) and then moves to the threshold table shown. Figure 6 Step S114.

[0085] On the other hand, in step S210, CPU 10A determines whether an edge exists in the object image. In this determination, threshold setting unit 30 determines whether the pixel of interest corresponds to an edge based on the edge information of the object image generated in step S106 above. If the determination is affirmative, the process proceeds to step S212; if it is negative, the process proceeds to step S214.

[0086] In step S212, CPU10A sets the missing threshold to a predetermined low value and sets the assign threshold to a predetermined low value. For example, according to... Figure 8The threshold setting unit 30 sets the missing threshold to 50, which is determined to be low, and then sets the assigned threshold to 50 and moves to the threshold setting. Figure 6 Step S114.

[0087] In step S214, CPU10A sets the missing threshold to a predetermined value and sets the assign threshold to a predetermined value. For example, according to... Figure 8 The threshold setting unit 30 sets the missing threshold to 100 (as determined in the predetermined threshold table) and then transfers the threshold to 100 (as determined in the predetermined threshold table). Figure 6 Step S114.

[0088] On the other hand, in step S216, CPU 10A determines whether an edge exists in the correct image. In this determination, the threshold setting unit 30 determines whether the image of interest corresponds to an edge based on the edge information of the correct image generated in step S104 above. If the determination is affirmative, the process proceeds to step S218; if it is negative, the process proceeds to step S224.

[0089] In step S218, CPU 10A determines whether an edge exists in the object image. In this determination, the threshold setting unit 30 determines whether the pixel of interest corresponds to an edge based on the edge information of the object image generated in step S106. If the determination is affirmative, the process proceeds to step S220; if it is negative, the process proceeds to step S222.

[0090] In step S220, CPU10A sets the missing threshold to a predetermined high value and the assign threshold to a predetermined medium-low value. For example, according to... Figure 8 The threshold setting unit 30 sets the missing threshold to 150 (determined to be high) and the assigned threshold to 75 (determined to be medium-low) and then transfers the assignment to the predetermined threshold table shown. Figure 6 Step S114.

[0091] In step S222, CPU10A sets the missing threshold to a predetermined high value and the assign threshold to a predetermined medium value. For example, according to... Figure 8 The threshold setting unit 30 sets the missing threshold to 150 (determined to be high) and assigns the threshold to 100 (determined to be medium) and then moves to the threshold table shown. Figure 6 Step S114.

[0092] On the other hand, in step S224, CPU 10A determines whether an edge exists in the object image. In this determination, the threshold setting unit 30 determines whether the pixel of interest corresponds to an edge based on the edge information of the object image generated in step S106 above. If the determination is affirmative, the process proceeds to step S226; if it is negative, the process proceeds to step S228.

[0093] In step S226, CPU10A sets the missing threshold to a predetermined low value and sets the assign threshold to a predetermined low value. For example, according to... Figure 8 The threshold setting unit 30 sets the missing threshold to 50, which is determined to be low, and then sets the assigned threshold to 50 and moves to the threshold setting. Figure 6 Step S114.

[0094] In step S228, CPU10A sets the missing threshold to a predetermined value and sets the assigned threshold to a predetermined value. For example, according to... Figure 8 The threshold setting unit 30 sets the missing threshold to 100 (as determined in the predetermined threshold table) and then transfers the threshold to 100 (as determined in the predetermined threshold table). Figure 6 Step S114.

[0095] Furthermore, in the above embodiment, the threshold for detecting defects was changed using edge information of the correct image and the object image, as well as the brightness information of the correct image. However, color information can also be used instead of brightness information. Here, it is assumed that color information includes brightness information.

[0096] When using color information, the correct image is, for example, a RIP (Raster Image Processor) image, and the object image is an image obtained by printing the correct image using the printing device 14 and reading the original using the reading device 16. Furthermore, the correct image and the object image are, for example, envisioned in the Lab color space.

[0097] Furthermore, edge extraction is performed on the face of L or all faces of Lab, and will Figure 6 , 7 The brightness determination in the processing has been changed to determine the brightness of each color region. For example... Figure 9 As shown, in determining brightness, a predetermined threshold value is used for each color region. Figure 9In the example, the line connecting K (black) at 50% lightness and Y at 50% chroma is used as the threshold for determining brightness in the Y (yellow) region. Similarly, the line connecting K (magenta) at 50% lightness and M at 50% chroma is used as the threshold for determining brightness in the M (magenta) region. And the line connecting K (cyan) at 50% lightness and C at 50% chroma is used as the threshold for determining brightness in the C (cyan) region.

[0098] Furthermore, in the calculation of the difference image when comparing the correct image with the object image, the color difference ΔE is used to calculate the difference image, and the defect determination is performed in the same manner as in the above-described implementation.

[0099] Furthermore, in this case, the predetermined threshold can be changed for a specific color. That is, the threshold can be changed for a specific Lab value. For example, only white can be changed to a strict threshold compared to other colors, or only red can be changed to a strict threshold, or blue can be changed to a lenient threshold.

[0100] Furthermore, in the above embodiments, the threshold for detecting defects was changed using edge information of the correct image and the object image, as well as brightness information of the correct image. However, in addition to edge information, at least one of edge perimeter information and object information may also be used. As edge perimeter information, for example, information about a region that has expanded from the edge by several pixels (e.g., 1 or 2 pixels) can be used. The number of pixels expanded from the edge can be varied depending on the resolution. For example, the higher the resolution of the expansion, the more pixels can be added.

[0101] When edge perimeter information is also used in the above implementation method, according to Figure 10 The threshold table shown indicates the threshold to be changed. Figure 10 This is a diagram illustrating an example of a threshold table when using edge perimeter information.

[0102] exist Figure 10 In the example of the threshold table, when the correct image has no edges, no extended edges, the object image has no edges, no extended edges, and the brightness of the correct image is bright, the missing threshold is set to 100, and the assigned threshold is set to 100.

[0103] Furthermore, when the correct image has no edges, no extended edges, the object image has no edges, no extended edges, and the brightness of the correct image is dark, the missing threshold is set to 100, and the assigned threshold is set to 100.

[0104] Furthermore, when the correct image has no edges, no extended edges, the object image has no edges, has extended edges, and the correct image is bright, the missing threshold is set to 75, and the assigned threshold is set to 75.

[0105] Furthermore, when the correct image has no edges, no extended edges, the object image has no edges, has extended edges, and the brightness of the correct image is dark, the missing threshold is set to 75, and the assigned threshold is set to 75.

[0106] Furthermore, when the correct image has no edges or extended edges, the object image has edges or extended edges, and the correct image is bright, the missing threshold is set to 50, and the assigned threshold is set to 50.

[0107] Furthermore, when the correct image has no edges or extended edges, the object image has edges or extended edges, and the correct image is dark, the missing threshold is set to 50, and the assigned threshold is set to 50.

[0108] Furthermore, when the correct image has no edges, has expanded edges, the object image has no edges, has no expanded edges, and the brightness of the correct image is bright, the missing threshold is set to 100, and the assigned threshold is set to 125.

[0109] Furthermore, when the correct image has no edges, has expanded edges, the object image has no edges, has no expanded edges, and the brightness of the correct image is dark, the missing threshold is set to 125, and the assigned threshold is set to 100.

[0110] Furthermore, when the correct image has no edges, has expanded edges, the object image has no edges, has expanded edges, and the brightness of the correct image is bright, the missing threshold is set to 87.5, and the assigned threshold is set to 125.

[0111] Furthermore, when the correct image has no edges, has expanded edges, the object image has no edges, has expanded edges, and the brightness of the correct image is dark, the missing threshold is set to 125, and the assigned threshold is set to 87.5.

[0112] Furthermore, when the correct image has no edges, has expanded edges, the object image has edges, has expanded edges, and the correct image is bright, the missing threshold is set to 81.25, and the assigned threshold is set to 137.5.

[0113] Furthermore, when the correct image has no edges, has expanded edges, the object image has edges, has expanded edges, and the brightness of the correct image is dark, the missing threshold is set to 137.5, and the assigned threshold is set to 81.25.

[0114] Furthermore, when the correct image has edges or expanded edges, the object image has no edges or expanded edges, and the correct image is bright, the missing threshold is set to 100, and the assigned threshold is set to 150.

[0115] Furthermore, when the correct image has edges, has expanded edges, the object image has no edges, has no expanded edges, and the correct image is dark, the missing threshold is set to 150, and the assigned threshold is set to 100.

[0116] Furthermore, when the correct image has edges, has expanded edges, the object image has no edges, has expanded edges, and the correct image is bright, the missing threshold is set to 81.25, and the assigned threshold is set to 137.5.

[0117] Furthermore, when the correct image has edges, has expanded edges, the object image has no edges, has expanded edges, and the correct image is dark, the missing threshold is set to 137.5, and the assigned threshold is set to 81.25.

[0118] Furthermore, when the correct image has edges, has expanded edges, the object image has edges, has expanded edges, and the correct image is bright, the missing threshold is set to 75, and the assigned threshold is set to 150.

[0119] Furthermore, when the correct image has edges, has expanded edges, the object image has edges, has expanded edges, and the brightness of the correct image is dark, the missing threshold is set to 150, and the assigned threshold is set to 75.

[0120] Furthermore, when object information is used to change the threshold in addition to edge information, a pre-determined threshold can be set for each type of object, such as text, graphics, and images. For example, compared to images, text and graphics are more prone to false detection of defects at the edges, so a higher threshold is set for them to make defects less likely to be detected.

[0121] Furthermore, when edges are extracted in the correct image edge extraction unit 24 and the object image edge extraction unit 26 respectively, the extraction threshold can be changed using object information. For example, the extraction threshold can be changed to a value predetermined for each type of object. Specifically, when the object information is text or graphics, the edge extraction threshold is set to a higher threshold than that for images, and when it is an image, it is set to a lower threshold than that for text or graphics. Thus, edge extraction corresponding to the object is performed.

[0122] Furthermore, the inspection device 10 according to this embodiment can be configured to be included in an image forming apparatus that has the functions of a printing device 14 and a reading device 16. Alternatively, it can be configured to include the inspection device 10 in an image forming apparatus that has the functions of a printing device 14 or a reading device 16.

[0123] Here, the structure of the image forming apparatus 50, which includes the inspection device 10, and which has the functions of the printing device 14 and the reading device 16, will be described. Figure 11This is a block diagram illustrating an example of the structure of an image forming apparatus 50 that includes the inspection device 10 according to this embodiment, and is equipped with the functions of a printing device 14 and a reading device 16.

[0124] like Figure 11 As shown, the image forming apparatus 50 includes a display operation unit 52, a control unit 54, an image generation unit 56, a forming unit 58, and an ejection unit 60.

[0125] 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, various settings such as image formation conditions or the type of recording medium used to form the image are made by operating the display operation unit 52.

[0126] The control unit 54 encompasses all parts of the image forming apparatus 50 and controls each part of the image forming apparatus 50 according to the settings configured in the display operation unit 52. The control unit 54 may be, for example, a microcomputer equipped with a CPU, ROM, RAM, and input / output units. A program for controlling the operations of image forming is pre-stored in the ROM, and the operation of each part of the image forming apparatus 50 is controlled by expanding this program into RAM and executing it through the CPU.

[0127] The image generation unit 56 generates image information representing the original image by reading the original image. Alternatively, it generates image information of the original image to be formed by acquiring image information sent from an external computer. Then, the inspection device 10 acquires the image information generated by the image generation unit 56 as the correct image.

[0128] The forming unit 58 includes a paper feeding unit 62, a transport unit 64, an image processing unit 66, an image forming unit 68, a fixing unit 70, and an image reading unit 72 as a reading unit.

[0129] The paper supply unit 62 holds recording paper, which serves as the recording medium, and supplies the recording paper to the transport unit 64. For example, the paper supply unit 62 holds recording paper wound into a roll, pulls it out, and supplies it to the transport unit. Alternatively, the paper supply unit 62 has multiple receiving sections for holding paper of different sizes or types, pulls paper out from the main section, and supplies it to the transport unit. In this case, the paper set by the display operation unit 52, etc., is supplied from each receiving section to the transport unit 64. Furthermore, when image information is acquired from the outside, paper of the type specified externally is supplied from each receiving section to the transport unit 64.

[0130] The transport unit 64 transports the recording paper or sheet supplied from the paper supply unit 62 to the position where an image is formed on the recording paper or sheet, and then transports the recording paper or sheet with the image formed to the discharge unit 60.

[0131] The image processing unit 66 receives image information generated by the image generation unit 56 or received from the outside by the image generation unit 56, performs image processing for processing by the image forming unit 68, and outputs the processed image information to the image forming unit 68.

[0132] The image forming unit 68 receives image information from the image processing unit 66 and forms an image represented by the image information onto recording paper or paper. For example, the image forming unit 68 may transfer the image onto the recording paper or paper using an electrophotographic method, or it may form an image by spraying ink onto the recording paper or paper using an inkjet method or the like.

[0133] The fixing unit 70 performs a process for fixing an image onto the recording paper. As a fixing process, the image is fixed onto the recording paper or sheet paper by applying pressure and heating at least one of these processes.

[0134] The image reading unit 72 reads the recording paper or sheet on which the image is formed to acquire image information for various corrections (e.g., position offset correction, color correction, etc.). Furthermore, the inspection device 10 acquires the image information obtained by the image reading unit 72.

[0135] Furthermore, the discharge section 60 rolls up the recording paper with the image formed and stores it. Alternatively, it discharges the paper with the image formed.

[0136] Furthermore, in the above embodiment, as an example, the case where the digital image information that will form the basis of the image is used as the correct image and the image of the object to be inspected is used as the image information obtained by performing image formation based on the correct image and reading the image from a recording medium such as paper is described. However, it is also possible to apply to the following inspection apparatus, which performs AA (analog-analog) inspection by using the image information obtained by reading the correct image of a predetermined reference as the correct image instead of the correct digital image.

[0137] In the above embodiments, processor refers to processor in a broad sense, including general-purpose processors (e.g., CPU: Central Processing Unit, etc.) or dedicated processors (e.g., GPU: Graphics Processing Unit, ASIC: Application Specific Integrated Circuit, FPGA: Field Programmable Gate Array, programmable logic device, etc.).

[0138] Furthermore, the operations of the processors in the above embodiments can be performed by a single processor or by a plurality of processors located in physically separate positions working together. Also, the order of the processors' operations is not limited to the order described in the above embodiments and can be appropriately modified.

[0139] Furthermore, the processing performed by the inspection device 10 according to the above embodiments can be software-based, hardware-based, or a combination of both. Moreover, the processing performed by each part of the inspection device 10 can be stored as a program in a storage medium and circulated.

[0140] Furthermore, the present invention is not limited to the above description, and various modifications can be made without departing from its spirit.

[0141] The embodiments of the present invention described above are provided for illustrative purposes. Furthermore, these embodiments do not encompass the entirety of the invention, nor do they limit the invention to the disclosed methods. It will be apparent to those skilled in the art that various modifications and variations will be readily understood. These embodiments were chosen and described to most readily explain the principles and applications of the invention. Thus, those skilled in the art can understand the invention through various modifications that are assumed to be optimized for specific uses of various embodiments. The scope of the invention is defined by the foregoing claims and their equivalents.

Claims

1. An inspection device comprising a processor, the processor performing the following processing: Obtain image information for both the correct image and the object image being inspected. The edge information of the correct image and the object image is extracted using the acquired image information. Export the difference image between the correct image and the object image. If an edge exists in the correct image based on the acquired edge information, a threshold for detecting defects is set using the edge information of the correct image, the edge information of the object image, and the brightness or color information of the correct image. The defect in the object image is then detected using the difference image and the threshold, wherein the threshold varies depending on the brightness of the correct image, whether the correct image has an edge, and whether the object image has an edge.

2. The inspection device according to claim 1, wherein, When the brightness information is used, the processor changes the threshold to a predetermined threshold based on the predetermined brightness of the correct image.

3. The inspection device according to claim 1, wherein, When the color information is used, the processor changes the threshold to a predetermined threshold based on the pre-determined brightness of each color region of the color information.

4. The inspection device according to claim 1, wherein, When the color information is used, the processor exports the color difference as the difference image.

5. The inspection device according to claim 1, wherein, When the color information is used, the processor changes the threshold for a predetermined specific color.

6. The inspection device according to any one of claims 1 to 5, wherein, The processor also uses edge perimeter information of a predetermined range of the edges of the correct image and the object image to change the threshold.

7. The inspection device according to any one of claims 1 to 5, wherein, The processor also uses object information from the correct image to change the threshold.

8. The inspection device according to any one of claims 1 to 5, wherein, The processor uses the object information of the correct image to change the extraction threshold when extracting the edge information, thereby extracting the edge information.

9. The inspection device according to claim 8, wherein, The processor is changed to the extraction threshold, which is a pre-determined value for each type of object.

10. An image forming apparatus comprising: The inspection device according to any one of claims 1 to 9; The image forming unit forms an image on a recording medium using image information from the pre-generated correct image; and The reading unit reads image information generated by the recording medium through which the image is formed by the image forming unit to generate the object image.

11. A storage medium storing a checking program for causing a computer to perform the following processes: Obtain image information for both the correct image and the object image being inspected. The edge information of the correct image and the object image is extracted using the acquired image information. Export the difference image between the correct image and the object image. If an edge exists in the correct image based on the acquired edge information, a threshold for detecting defects is set using the edge information of the correct image, the edge information of the object image, and the brightness or color information of the correct image. The defect in the object image is then detected using the difference image and the threshold, wherein the threshold varies depending on the brightness of the correct image, whether the correct image has an edge, and whether the object image has an edge.

12. An inspection method comprising the following steps: Obtain image information for both the correct image and the object image of the object being inspected; Use the acquired image information to extract the edge information of the correct image and the object image respectively; Export the difference image between the correct image and the object image; and If an edge exists in the correct image based on the acquired edge information, a threshold for detecting defects is set using the edge information of the correct image, the edge information of the object image, and the brightness or color information of the correct image. The defect in the object image is then detected using the difference image and the threshold, wherein the threshold varies depending on the brightness of the correct image, whether the correct image has an edge, and whether the object image has an edge.

Images