Image processing device, image processing method and program

Abstract

To provide a process for improving the accuracy of inspection of the vicinity of an area including a feature in an image to be inspected.SOLUTION: An image processing device acquires image data representing an image to be inspected, acquires a first inspection sensitivity for defects specified by a user, inspects a first region in the image corresponding to a specific pattern similar to the defects with a second inspection sensitivity lower than the first inspection sensitivity, and inspects a second region in the image not corresponding to the specific pattern with the first inspection sensitivity.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an image processing technique for inspecting printed matter. [Background technology]

[0002] Printed materials output by a printing device may be stained due to the adhesion of coloring materials such as ink or toner to unintended locations. Alternatively, insufficient coloring materials may be applied to areas where an image is to be formed, resulting in a lighter color than intended. Defects in printed materials, such as stains and coloring, degrade the quality of printed materials. Therefore, it is necessary to inspect printed materials for defects to ensure their quality. Visual inspections of printed materials for defects are costly, so automated inspection systems have been developed. Such inspection systems determine the presence or absence of defects based on, for example, the difference between a pre-registered reference image serving as an inspection standard for printed materials and an inspection target image obtained by scanning the printed material to be inspected. Patent Document 1 discloses a technology for correcting an inspection threshold to relax the inspection threshold in areas near edges extracted from the reference image, and inspecting printed materials based on the difference between the reference image and the inspection target image and the corrected inspection threshold. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2018-155736 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the technique of Patent Document 1, there are cases where defects present near areas containing features such as edges cannot be detected in the image to be inspected.

[0005] SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide a process for improving the accuracy of inspection of the vicinity of an area containing a feature in an image to be inspected. [Means for solving the problem]

[0006] In order to solve the above problem, an image processing apparatus according to the present invention includes a first acquisition means for acquiring image data representing an image of an inspection object, and a user-specified Linear First inspection sensitivity to defects and the second inspection sensitivity to point defects. a second acquisition means for acquiring the image; Linear A first area corresponding to the pattern is subjected to a second inspection sensitivity lower than the first inspection sensitivity. 3 Test sensitivity and the second test sensitivity. Inspect the image with Supports point patterns The second region is the first inspection sensitivity and a fourth inspection sensitivity lower than the second inspection sensitivity. and an inspection means for inspecting the [Effects of the Invention]

[0007] According to the present invention, it is possible to improve the accuracy of inspection of the vicinity of an area containing a feature in an image to be inspected. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing the configuration of a printing system including an image processing apparatus. [Figure 2] Block diagram showing the functional configuration of an image processing device [Figure 3] 1 is a flowchart showing a process executed by an image processing apparatus; [Figure 4] FIG. 1 is a diagram showing an example of a reference image and an image to be inspected; [Figure 5] A diagram showing an example of an inspection area [Figure 6] Example of detection sensitivity [Figure 7] 10 is a flowchart showing a process for extracting a local pattern area. [Figure 8] A diagram showing an example of a local pattern area [Figure 9] Flowchart showing a process for adjusting detection sensitivity [Figure 10] An example of adjusted detection sensitivity [Figure 11] Flowchart showing inspection processing [Figure 12] Diagram showing an overview of the inspection process [Figure 13] 10 is a flowchart showing a process for extracting a local pattern area. [Figure 14] A diagram showing an example of a local pattern area [Figure 15] Flowchart showing a process for adjusting detection sensitivity [Figure 16] An example of adjusted detection sensitivity DETAILED DESCRIPTION OF THE INVENTION

[0009] The present embodiment will be described below with reference to the drawings. Note that the following embodiment does not necessarily limit the present invention. Furthermore, not all of the combinations of features described in the present embodiment are necessarily essential to the solution of the present invention.

[0010] [First embodiment] In this embodiment, an area corresponding to a local pattern is extracted from a reference image, and the detection sensitivity for defects similar to the local pattern is reduced before performing inspection processing. Note that the inspection in this embodiment is performed based on the absolute value of the difference between an image representing a target print result (reference image) and an image to be inspected (inspection target image).

[0011] <Printing system configuration> FIG. 1 is a diagram showing an example of the overall configuration of a printing system that outputs and inspects printed materials, including an image processing device 100. The printing system in this embodiment includes the image processing device 100, a printing server 180, and a printing device 190. The printing server 180 generates a print job for a document to be printed and submits the print job to the printing device 190. The printing device 190 forms an image on a recording medium (printing paper) based on the print job submitted from the printing server 180. The printing device 190 has a paper feed unit 191, and a user loads printing paper into the paper feed unit 191 in advance. When a print job is submitted, the printing device 190 transports the printing paper loaded in the paper feed unit 191 along a transport path 192, forms an image on the surface (one side or both sides) of the paper, and sends it to the image processing device 100. The printing device 190 in this embodiment is an electrophotographic printing device, but may also be an offset printing or inkjet printing device.

[0012] The image processing device 100 inspects a printed object to be inspected for defects after printing. The printed object to be inspected, obtained by forming an image on printing paper by the printing device 190, is transported along a transport path 192 and inspected by the image processing device 100. The image processing device 100 functions as an inspection processing device. The image processing device 100 has a CPU 101, a RAM 102, and a ROM 103. The image processing device 100 also has a storage device 104, an image reading device 105, a printing interface (I / F) 106, a general-purpose interface (I / F) 107, a user interface (UI) panel 108, and a main bus 109. The image processing device 100 also has a transport path 110 for printed objects connected to the transport path 192 of the printing device 190, an output tray 111 for printed objects that have passed inspection, and an output tray 112 for printed objects that have been found to have defects and failed inspection. Note that the printed objects may be classified not only into two categories, pass and fail, but also into more detailed categories. In the printing system, the storage device 104 , the image reading device 105 , the UI panel 108 , the conveying path 110 , the output tray 111 , and the output tray 112 may be provided outside the image processing device 100 .

[0013] The CPU 101 is a processor that comprehensively controls each unit of the image processing device 100. The RAM 102 functions as the main memory, work area, etc. of the CPU 101. The ROM 103 stores a group of programs executed by the CPU 101. The storage device 104 stores applications executed by the CPU 101, data used for image processing, etc. The image reading device 105 is a scanner that reads one or both sides of a printed material sent from the printing device 190 on the conveying path 110 and acquires the data as image data.

[0014] The print I / F 106 is connected to the printing device 190 and is an interface for synchronizing the timing of print processing between the image processing device 100 and the printing device 190 and for communicating each other's operating status. The general-purpose I / F 107 is a serial bus interface such as USB or IEEE 1394, allowing the user to carry data such as logs. The UI panel 108 is a display device such as an LCD display, and functions as a user interface for informing the user of the current status and settings of the image processing device 100. The UI panel 108 may also have an input device such as a touch panel or buttons, and can accept instructions from the user regarding inspections, etc. The input device, such as a mouse or keyboard, may be provided separately from the UI panel 108. The main bus 109 is a transmission path connecting each module of the image processing device 100.

[0015] The image processing device 100 transports the printed matter sent from the printing device 190 along the transport path 110, while performing the inspection process described below based on the image data of the printed matter read by the image reading device 105. If the printed matter passes the inspection, it is transported to a pass output tray 111, and if it fails the inspection, it is transported to a fail output tray 112. This allows only printed matters that have been confirmed to meet the quality standards to be collected in the output tray 111 as printed matters for delivery.

[0016] <Functional configuration of image processing device> 2 shows the functional configuration of the image processing device 100. The image processing device 100 has a reference image setting unit 201, an area setting unit 202, a detection sensitivity setting unit 203, a local pattern extraction unit 204, a detection sensitivity adjustment unit 205, an image acquisition unit 206, and an inspection processing unit 207.

[0017] The reference image setting unit 201 sets an image represented by image data stored in the RAM 102 or the storage device 104 as a reference image. The area setting unit 202 sets an inspection area for the reference image based on instructions from the user acquired via the UI panel 108. The detection sensitivity setting unit 203 sets the detection sensitivity for defects in each inspection area based on instructions from the user acquired via the UI panel 108. In this embodiment, the detection sensitivity is set for each defect type. In this embodiment, there are two types of defects: point-like defects (hereinafter referred to as point defects) and line-like defects (hereinafter referred to as line defects). The local pattern extraction unit 204 extracts an area corresponding to a specific local pattern from the reference image. In this embodiment, the local pattern to be extracted is a line pattern, and the local pattern extraction unit 204 extracts an area corresponding to the line pattern from the reference image. The detection sensitivity adjustment unit 205 reduces the detection sensitivity for defects similar to the local pattern in the area corresponding to the local pattern. In this embodiment, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for linear defects in an area corresponding to a linear pattern. The image acquisition unit 206 acquires inspection target image data representing the inspection target image, which is obtained by the image reading device 105 reading a printed material on the conveying path 110. The acquired inspection target image data is stored in the RAM 102 or the storage device 104. The inspection processing unit 207 performs inspection processing on the inspection target image based on the difference between the reference image and the inspection target image and the detection sensitivity, and outputs the inspection results.

[0018] <Processing performed by the image processing device> FIG. 3 is a flowchart showing the processing executed by the image processing device 100. Hereinafter, each step (process) is represented by adding an S before the reference number. In S301, the reference image setting unit 201 sets a reference image. An example of the reference image is shown in FIG. 4(a). The reference image data representing the reference image is created in advance based on a scanned image obtained by reading a printed material output by the printing device 190, and is recorded in the RAM 102 or the storage device 104.

[0019] In S302, the area setting unit 202 sets an inspection area in the reference image based on instructions from the user acquired via the UI panel 108. An example of an inspection area is shown in FIG. 5. In this embodiment, the area setting unit 202 sets inspection area A and inspection area B in the reference image. In S303, the detection sensitivity setting unit 203 sets the detection sensitivity for defects in each inspection area based on instructions from the user acquired via the UI panel 108. In this embodiment, the detection sensitivity setting unit 203 sets the detection sensitivity for point defects and line defects in each inspection area to one of three levels: high, medium, and low. The higher the detection sensitivity, the more defects with low contrast with the background and small defects can be detected. An example of detection sensitivity is shown in FIG. 6. In inspection area A, the detection sensitivity for point defects and line defects is set to high, and in inspection area B, the detection sensitivity for point defects and line defects is set to medium.

[0020] In S304, the local pattern extraction unit 204 extracts an area corresponding to a local pattern in the reference image. FIG. 7 is a flowchart illustrating the process of extracting an area corresponding to a local pattern. The process of extracting an area corresponding to a local pattern will be described in detail below. In S701, the local pattern extraction unit 204 applies a line enhancement filter to the reference image to enhance linear patterns contained in the reference image. The line enhancement filter increases the pixel value of pixels corresponding to linear patterns. Hereinafter, an image obtained by applying the line enhancement filter to the reference image is referred to as a line enhancement image. In this embodiment, the line enhancement filter is a known Sobel filter, but a known two-dimensional filter such as a Prewitt filter may also be used. In S702, the local pattern extraction unit 204 extracts an area corresponding to a linear pattern in the line enhancement image. In this embodiment, an edge area is extracted as the area corresponding to the linear pattern. FIG. 8(a) shows an example of an edge area. Specifically, the local pattern extraction unit 204 performs threshold processing on each pixel in the line enhancement image and extracts pixels with pixel values ​​greater than a threshold as edge pixels constituting the edge area. The extracted edge area may be corrected by applying known morphological processing or the like to the edge area.

[0021] In S305, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for defects similar to the local pattern in an area corresponding to the local pattern. FIG. 9 is a flowchart showing the process of adjusting the detection sensitivity. Details of the process of adjusting the detection sensitivity will be described below. In S901, the detection sensitivity adjustment unit 205 divides the inspection area based on the edge area. FIG. 8(b) shows an example of the divided inspection area. In this embodiment, the edge area in inspection area A is referred to as area Ae, and the non-edge area in inspection area A is referred to as area An. Furthermore, the edge area in inspection area B is referred to as area Be, and the non-edge area in inspection area B is referred to as area Bn. In S902, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for linear defects, which are defects similar to a linear pattern, in the edge area. Specifically, the detection sensitivity adjustment unit 205 sets the detection sensitivity for linear defects in area Ae to be lower than the detection sensitivity set for inspection area A, and sets the detection sensitivity for point defects to be the same as the detection sensitivity set for inspection area A. Furthermore, the detection sensitivity adjustment unit 205 sets the detection sensitivity for line defects in the region Be to be lower than the detection sensitivity set for the inspection region B, and sets the detection sensitivity for point defects to be the same as the detection sensitivity set for the inspection region B. The detection sensitivity for the region An is set to be the same as the detection sensitivity set for the inspection region A, and the detection sensitivity for the region Bn is set to be the same as the detection sensitivity set for the inspection region B. An example of the adjusted detection sensitivity is shown in Fig. 10(a).

[0022] In S306, the image acquisition unit 206 acquires inspection target image data representing the inspection target image. An example of the inspection target image is shown in FIG. 4(b). In S307, the inspection processing unit 207 performs inspection processing on the inspection target image based on the difference between the reference image and the inspection target image and the detection sensitivity, and outputs the inspection result. Details of the inspection processing will be described later. In S308, the inspection processing unit 207 determines whether or not to end the processing based on print information from the printing device 190, instructions from the user obtained via the UI panel 108, etc. If it is determined not to end the processing, the process proceeds to S306.

[0023] <Inspection processing> FIG. 11 is a flowchart showing the inspection process. FIG. 12 is a diagram showing an overview of the inspection process. Details of the inspection process will be described below. In S1101, the inspection processing unit 207 calculates the absolute value of the difference in brightness between corresponding pixels in the reference image and the image to be inspected based on the reference image and the image to be inspected, and generates a difference image in which each pixel has the absolute value of the difference in brightness. In S1102, the inspection processing unit 207 generates a defect-enhanced image by emphasizing the defect to be processed contained in the difference image. If the defect to be processed is a line defect, a line enhancement filter is applied to the difference image. A Sobel filter is used as the line enhancement filter. If the defect to be processed is a point defect, a point enhancement filter is applied to the difference image. A known two-dimensional LoG (Laplacian of Gaussian) filter is used as the point enhancement filter. Note that a known two-dimensional filter such as a DoG (Difference of Gaussian) filter may also be used as the point enhancement filter.

[0024] In S1103, the inspection processing unit 207 sets a threshold value to be used for inspection based on the detection sensitivity corresponding to the inspection area to be processed and the defect to be processed. In this embodiment, defective pixels constituting the defect area are detected by comparing pixel values ​​of the defect-enhanced image with the threshold value Th1. Furthermore, to determine whether the defect area has a sufficient area, the area of ​​the defect area consisting of a group of connected defective pixels is compared with the threshold value Th2. Therefore, in S1103, the inspection processing unit 207 sets the threshold values ​​Th1 and Th2. Specifically, the inspection processing unit 207 sets the threshold values ​​so that the higher the detection sensitivity, the more easily defects with low contrast with the background and small defects can be detected. The inspection processing unit 207 sets the threshold value Th1 to a smaller value as the detection sensitivity increases, and sets the threshold value Th2 to a smaller value as the detection sensitivity increases. For example, in this embodiment, the detection sensitivity for linear defects is higher in area An than in area Ae, so the threshold value Th1 is set smaller in area An than in area Ae, and the threshold value Th2 is set smaller in area An than in area Ae.

[0025] In S1104, the inspection processing unit 207 performs threshold processing on the pixel values ​​of the defect-enhanced image using a threshold value Th1. Through this threshold processing, the inspection processing unit 207 detects pixels in the defect-enhanced image whose pixel values ​​are equal to or greater than the threshold value Th1 as defective pixels. In S1105, the inspection processing unit 207 performs threshold processing on the area of ​​the defective region in the defect-enhanced image using a threshold value Th2. Through this threshold processing, the inspection processing unit 207 removes pixels in the defective region whose pixel connectivity count is less than the threshold value Th2 from the defective pixels detected in S1104.

[0026] In S1106, the inspection processing unit 207 identifies an area common to the inspection area to be processed and the defective area. This makes it possible to detect only the defective area in the inspection area to be processed. In S1107, the inspection processing unit 207 determines whether or not there is an unprocessed inspection area. If there is an unprocessed inspection area, the inspection area to be processed is updated and the process proceeds to S1103. If there is no unprocessed inspection area, the process proceeds to S1108.

[0027] In S1108, the inspection processing unit 207 integrates the defect areas of each inspection area. This makes it possible to obtain the defect area corresponding to the defect to be processed. In S1109, the inspection processing unit 207 determines whether there are any unprocessed defect types. If there are any unprocessed defect types, the defect to be processed is updated and the process proceeds to S1102. If there are no unprocessed defect types, the process proceeds to S1110. In S1110, the inspection processing unit 207 outputs the inspection result. The inspection result is considered to be pass if there are no defect areas for all defect types, and is considered to be fail if there are defect areas for any defect type.

[0028] <Effects of the first embodiment> As described above, the image processing apparatus of this embodiment sets a reference image, which is a target print result. Sets detection sensitivity for multiple types of defects. Extracts an area corresponding to a local pattern from the reference image. Adjusts the detection sensitivity in the area corresponding to the local pattern so as to lower the detection sensitivity for defects similar to the local pattern. Obtains image data representing the image to be inspected. Inspects the image to be inspected based on the reference image and the adjusted detection sensitivity. This makes it possible to improve the accuracy of inspection of the vicinity of an area containing features in the image to be inspected.

[0029] <Modification> In this embodiment, the area setting unit 202 sets two areas, inspection area A and inspection area B, as inspection areas, but the method for setting the inspection areas is not limited to this. For example, the entire reference image may be set as a single inspection area. Also, three or more areas may be set as inspection areas. Also, a non-inspection area may be set in which defect detection is not performed. When setting a non-inspection area, it is possible to prevent defects in the non-inspection area from being detected by setting the pixel values ​​of the non-inspection area to 0 in the difference image generated in S1101.

[0030] Furthermore, although the detection sensitivity setting unit 203 in this embodiment sets the detection sensitivity in three stages, the method for setting the detection sensitivity is not limited to this. For example, the detection sensitivity may be set in two stages, or in four or more stages. Furthermore, the detection sensitivity for any defect may be fixed.

[0031] Although the local pattern extraction unit 204 in this embodiment extracts a region corresponding to a linear pattern as a region corresponding to a local pattern, it may also extract a region corresponding to a dot pattern. In this case, in S701, the local pattern extraction unit 204 applies a point emphasis filter to the reference image to emphasize the dot pattern contained in the reference image. The point emphasis filter increases the pixel value of pixels corresponding to dot patterns. Hereinafter, an image obtained by applying the point emphasis filter to the reference image is referred to as a point emphasis image. A two-dimensional Logarithmic Gain (LOG) filter is used as the point emphasis filter. In S702, the local pattern extraction unit 204 extracts a region corresponding to the dot pattern in the point emphasis image. A dot region is extracted as the region corresponding to the dot pattern. FIG. 8(c) shows an example of a dot region. Specifically, the local pattern extraction unit 204 performs threshold processing on each pixel in the point emphasis image and extracts pixels with pixel values ​​greater than the threshold as dot pixels constituting a dot region. Note that the extracted dot region may be corrected by applying a known morphological process or the like to the dot region.

[0032] In S901, the detection sensitivity adjustment unit 205 divides the inspection region based on the dot regions. An example of the divided inspection region is shown in FIG. 8(d). The dot regions in inspection region A are referred to as regions Ad, and the non-dot regions in inspection region A are referred to as regions An. Furthermore, the dot regions in inspection region B are referred to as regions Bd, and the non-dot regions in inspection region B are referred to as regions Bn. In S902, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for point defects, which are defects similar to dot patterns, in the dot regions. Specifically, the detection sensitivity adjustment unit 205 sets the detection sensitivity for point defects in region Ad to be lower than the detection sensitivity set for inspection region A, and sets the detection sensitivity for line defects to be the same as the detection sensitivity set for inspection region A. Furthermore, the detection sensitivity adjustment unit 205 sets the detection sensitivity for point defects in region Bd to be lower than the detection sensitivity set for inspection region B, and sets the detection sensitivity for line defects to be the same as the detection sensitivity set for inspection region B. The detection sensitivity for area An is set to be the same as the detection sensitivity set for inspection area A, and the detection sensitivity for area Bn is set to be the same as the detection sensitivity set for inspection area B. An example of the adjusted detection sensitivity is shown in Figure 10(b).

[0033] Furthermore, although there are two types of defects in this embodiment, point defects and line defects, line defects of different directions, such as vertical line defects and horizontal line defects, may also be detected as different defect types. If the defect to be processed is a vertical line defect, in S1102 the inspection processing unit 207 applies a vertical line emphasis filter that emphasizes vertical lines to the difference image. If the defect to be processed is a horizontal line defect, in S1102 the inspection processing unit 207 applies a horizontal line emphasis filter that emphasizes horizontal lines to the difference image.

[0034] In the inspection process of this embodiment, threshold processing is performed on pixel values ​​and on areas, but defective areas may be detected only by threshold processing on pixel values. In this case, the threshold corresponding to the detection sensitivity only needs to be set for pixel values.

[0035] Furthermore, in this embodiment, the user is notified whether the inspection target image passes or fails, but the defective area of ​​the inspection target image that fails may be displayed on the UI panel 108.

[0036] [Second embodiment] In the first embodiment, an area corresponding to a linear pattern was extracted from the reference image as an area corresponding to a local pattern, and the detection sensitivity for linear defects was reduced. In this embodiment, areas corresponding to each of multiple types of local patterns are extracted from the reference image, and the detection sensitivity for defects similar to each local pattern is reduced. Note that the configuration of the printing system and the functional configuration of the image processing device 100 in this embodiment are the same as those in the first embodiment, so their description will be omitted. The following mainly describes the processes of S304 and S305, which are different between this embodiment and the first embodiment. Note that the same components as in the first embodiment will be described using the same reference numerals.

[0037] <Process for extracting areas corresponding to local patterns> In S304, the local pattern extraction unit 204 extracts regions corresponding to each of the multiple types of local patterns in the reference image. In this embodiment, regions corresponding to line patterns and regions corresponding to dot patterns are extracted as the multiple types of local patterns. Fig. 13 is a flowchart showing the process of extracting regions corresponding to each of the multiple types of local patterns. Details of the process of extracting regions corresponding to each of the multiple types of local patterns will be described below.

[0038] In S1301, the local pattern extraction unit 204 enhances a local pattern to be processed that is included in the reference image. If the local pattern to be processed is a line pattern, the local pattern extraction unit 204 applies a line enhancement filter to the reference image. If the local pattern to be processed is a point pattern, the local pattern extraction unit 204 applies a point enhancement filter to the reference image. In S1302, the local pattern extraction unit 204 extracts an area corresponding to the local pattern in the image in which the local pattern has been enhanced. If the local pattern to be processed is a line pattern, the local pattern extraction unit 204 performs threshold processing on each pixel of the line-enhanced image, and extracts pixels having pixel values ​​greater than the threshold as edge pixels. If the local pattern to be processed is a point pattern, the local pattern extraction unit 204 performs threshold processing on each pixel of the point-enhanced image, and extracts pixels having pixel values ​​greater than the threshold as dot pixels.

[0039] In S1303, the local pattern extraction unit 204 determines whether or not there is an unprocessed local pattern. If there is an unprocessed local pattern, the local pattern to be processed is updated and the process proceeds to S1301; if there is no unprocessed local pattern, the process proceeds to S1304. In S1304, the local pattern extraction unit 204 integrates regions corresponding to multiple types of local patterns. Specifically, the local pattern extraction unit 204 replaces pixels included in both an edge region and a dot region with pixels belonging to either one of the regions. In this embodiment, the local pattern extraction unit 204 replaces pixels included in both an edge region and a dot region with edge pixels that constitute the edge region. An example of a region corresponding to a local pattern extracted by the process of S1304 is shown in FIG. 14(a).

[0040] <Process to adjust detection sensitivity> In S305, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for line defects in edge regions and reduces the detection sensitivity for point defects in dot regions. FIG. 15 is a flowchart showing the process of adjusting the detection sensitivity. Details of the process of adjusting the detection sensitivity will be described below. In S1501, the detection sensitivity adjustment unit 205 divides the inspection region based on the region corresponding to the local pattern to be processed. FIG. 14(b) shows an example of the divided inspection region. The detection sensitivity adjustment unit 205 defines the edge region in inspection region A as region Ae, the dot region as region Ad, and the other region as An. Furthermore, the detection sensitivity adjustment unit 205 defines the edge region in inspection region B as region Be, the dot region as region Bd, and the other region as Bn.

[0041] In S1502, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for defects similar to the local pattern to be processed in a region corresponding to the local pattern to be processed. If the local pattern to be processed is a linear pattern, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for linear defects in the edge region. Specifically, the detection sensitivity adjustment unit 205 sets the detection sensitivity for linear defects in the region Ae to be lower than the detection sensitivity set for the inspection region A, and sets the detection sensitivity for linear defects in the region Be to be lower than the detection sensitivity set for the inspection region B. If the local pattern to be processed is a dot pattern, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for point defects in the dot region. Specifically, the detection sensitivity adjustment unit 205 sets the detection sensitivity for point defects in the region Ad to be lower than the detection sensitivity set for the inspection region A, and sets the detection sensitivity for point defects in the region Bd to be lower than the detection sensitivity set for the inspection region B. FIG. 16(a) shows an example of the adjusted detection sensitivity.

[0042] In S1503, the detection sensitivity adjustment unit 205 determines whether or not there is an unprocessed local pattern. If there is an unprocessed local pattern, the local pattern to be processed is updated and the process proceeds to S1502. If there is no unprocessed local pattern, the process of S305 ends.

[0043] <Effects of the second embodiment> As described above, the image processing apparatus in this embodiment extracts regions corresponding to each of a plurality of types of local patterns and adjusts the detection sensitivity in accordance with the extracted regions, thereby improving the accuracy of inspection of the vicinity of a region containing a feature in the image to be inspected.

[0044] <Modification> In this embodiment, edge regions and dot regions are extracted as regions corresponding to local patterns, but local patterns are not limited to these. For example, local patterns of the same type but with different contrasts with the background may be extracted separately. In this case, adjustment is made so that the detection sensitivity becomes lower for regions corresponding to local patterns with higher contrasts with the background. As an example, a case where high-contrast edge regions and low-contrast edge regions are extracted separately will be described. First, a threshold Th corresponding to high-contrast edge regions is set. EH and a threshold Th corresponding to low-contrast edge regions. EL and is set. EH Th EL The value is set to be larger than

[0045] In S1302, if the local pattern to be processed is a high-contrast edge, the local pattern extraction unit 204 performs threshold processing on each pixel of the line-enhanced image to obtain a threshold Th EH If the local pattern to be processed is a low-contrast edge, a threshold process is performed on each pixel of the line-enhanced image, and the pixel with the larger pixel value is extracted as a pixel in a high-contrast edge region. EL In step S1304, the local pattern extraction unit 204 replaces pixels in the low-contrast edge region that overlap with pixels in the high-contrast edge region with pixels in the high-contrast edge region.

[0046] In S1501, the detection sensitivity adjustment unit 205 defines a high-contrast edge area in the inspection area A as an area Ae Hand the low contrast edge region is Ae L The other areas are denoted as An. The high contrast edge area in the inspection area B is denoted as area Be. H The low contrast edge region is defined as Be L In step S1502, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for linear defects in the edge region. Specifically, when the local pattern to be processed is a high-contrast edge, the detection sensitivity adjustment unit 205 reduces the detection sensitivity for linear defects in the region Ae H In the inspection area B, the detection sensitivity for the linear defect is set lower than the detection sensitivity set for the inspection area A. H In the inspection area Ae, the detection sensitivity for the linear defect is set lower than the detection sensitivity set for the inspection area B. When the local pattern to be processed is a low-contrast edge, the detection sensitivity adjustment unit 205 L In the inspection area B, the detection sensitivity for the linear defect is set lower than the detection sensitivity set for the inspection area A. L In this case, the detection sensitivity for line defects is set lower than the detection sensitivity set for inspection area B. An example of the adjusted detection sensitivity is shown in FIG.

[0047] [Other embodiments] The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) that realizes one or more functions. [Explanation of symbols]

[0048] 100 Image processing device 201 Reference image setting unit 203 Detection sensitivity setting unit 204 Local Pattern Extraction Unit 205 Detection sensitivity adjustment unit 206 Image acquisition unit 207 Inspection Processing Unit

Claims

1. a first acquisition means for acquiring image data representing an image of an object to be inspected; a second acquisition means for acquiring a first inspection sensitivity for line defects and a second inspection sensitivity for point defects, both of which are specified by a user; an inspection means for inspecting a first region in the image corresponding to a linear pattern with a third inspection sensitivity lower than the first inspection sensitivity and the second inspection sensitivity, and for inspecting a second region in the image corresponding to a dot pattern with the first inspection sensitivity and a fourth inspection sensitivity lower than the second inspection sensitivity; 1. An image processing device comprising:

2. 2. The image processing apparatus according to claim 1, wherein the inspection means inspects the image to be inspected using a reference image that is a standard for inspection.

3. further comprising an extraction means for extracting an area corresponding to the linear pattern in a reference image that is a standard for inspection; 3. The image processing device according to claim 1, wherein the first area is set based on the extracted area.

4. 4. The image processing apparatus according to claim 3, wherein said extracting means extracts an area corresponding to said linear pattern in said reference image using a filter for enhancing said linear pattern.

5. 5. The image processing device according to claim 1, wherein the inspection means inspects the image of the inspection object using pixel values ​​of a difference image representing a difference between the image of the inspection object and a reference image that is a standard for inspection, and a threshold value.

6. 6. The image processing apparatus according to claim 5, wherein the inspection means sets the threshold to a smaller value as the inspection sensitivity increases.

7. a print control means for performing printing based on the original; a reading control means for reading the printed matter obtained by the printing, 7. The image processing apparatus according to claim 1, wherein the image data is data obtained by scanning a printed matter.

8. The printed matter that passes the inspection by the inspection means is output to a first tray, 8. The image processing apparatus according to claim 1, wherein printed matter that has failed the inspection by the inspection means is output to a second tray different from the first tray.

9. 9. The image processing apparatus according to claim 1, further comprising a display control unit that displays a user interface for specifying the inspection sensitivity for each of a plurality of types of defects.

10. A program for causing a computer to function as the image processing device according to any one of claims 1 to 9.

11. acquiring image data representing an image of an object to be inspected; acquiring a first inspection sensitivity for line defects and a second inspection sensitivity for point defects, both specified by a user; inspecting a first region in the image corresponding to a linear pattern with a third inspection sensitivity lower than the first inspection sensitivity and the second inspection sensitivity, and inspecting a second region in the image corresponding to a dot pattern with the first inspection sensitivity and a fourth inspection sensitivity lower than the second inspection sensitivity; An image processing method comprising:

Images