Image processing device, image processing method and program

Abstract

To provide processing for positioning an image of an inspection object and a reference image with high accuracy even in the case that the image of the inspection object includes local deformation.SOLUTION: An image processing device acquires reference image data being a reference of inspection of a printed matter and scan image data obtained by reading the printed matter, acquires object information on an object included in a document image of the printed matter, sets a reference point for positioning a reference image represented by the reference image data and a scan image represented by the scan image data on the basis of the object information, and positions the reference image and the scan image on the basis of the set reference point.SELECTED DRAWING: Figure 5

Description

[Technical field]

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

[0002] In the printing industry, prints are inspected for defects to ensure that they are free of defects and of acceptable quality. In recent years, automation technology for inspection work has also been developed. Print inspection involves the use of the difference between two types of images: an image that serves as a quality standard (hereafter referred to as the reference image) and an image of the object to be inspected (hereafter referred to as the object image) obtained by scanning the print with a sensor or the like. The data for the reference image is either image data generated by RIP (Raster Image Processor) processing during printing, or image data generated by synthesizing data obtained by scanning multiple prints.

[0003] In order to accurately compare a reference image with a target image, it is necessary to align the images. Patent Document 1 discloses aligning a reference image with a scanned image in an in-line inspection system for printed matter. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2013-36815 A Summary of the Invention [Problem to be solved by the invention]

[0005] In Patent Document 1, a patch image containing feature points in a reference image is aligned with a patch image in a scanned image. However, since the scanned image may be locally deformed during printing, scanning, or other processes, the image may end up being associated with the wrong feature points.

[0006] Therefore, an object of the present invention is to provide a process for aligning an image to be inspected and a reference image with high accuracy even when the image to be inspected includes local deformation. [Means for solving the problem]

[0007] In order to solve the above problems, the image processing device of the present invention is characterized in having a first acquisition means for acquiring reference image data, which is a standard for inspecting a printed matter, and scanned image data obtained by reading the printed matter, a second acquisition means for acquiring object information regarding objects contained in an original image of the printed matter, a setting means for setting a reference point for aligning a reference image represented by the reference image data and a scanned image represented by the scanned image data based on the object information, and a processing means for aligning the reference image and the scanned image based on the set reference point. Effect of the Invention

[0008] According to the present invention, even if the image of the inspection object contains a local deformation, it is possible to align the image of the inspection object and the reference image with high accuracy. [Brief description of the drawings]

[0009] [Figure 1] A diagram showing the configuration of a printing system [Diagram 2] Block diagram showing the functional configuration of an image processing device [Diagram 3] 1 is a flowchart showing a process executed by an image processing device; [Figure 4] Flowchart showing the process of setting the alignment reference point [Diagram 5] A flowchart showing a process for setting a search area for a registration reference point. [Figure 6] 1 shows an example of alignment reference points detected in a scanned image. [Figure 7] FIG. 13 is a diagram for explaining a process for setting an area for searching for a registration reference point; [Figure 8] A flowchart showing a process for setting a search area for a registration reference point. [Figure 9] Flowchart showing the process of setting print paper [Figure 10] FIG. 1 shows a scanned image, a search area for alignment reference points, and feature points. [Figure 11] A diagram showing an example of manuscript data. [Figure 12] FIG. 1 shows an example of alignment reference points obtained on a scanned image. [Figure 13] A flowchart showing a process for setting a search area for a registration reference point. [Figure 14] A diagram showing an overlapping area where an object on the front side and an object on the back side overlap. [Figure 15] FIG. 1 shows a search area and an exclusion area for alignment reference points. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Each embodiment will be described below with reference to the drawings. Note that the following embodiments do not necessarily limit the present invention. Furthermore, not all of the combinations of features described in each embodiment are necessarily essential to the solution of the present invention.

[0011] [First embodiment] In this embodiment, in the process of setting a reference point for alignment, the search range for the reference point is limited based on object information obtained from the manuscript data. This makes it possible to prevent the reference point from being obtained from an area where the alignment reference point is likely to be erroneously detected.

[0012] <Printing system configuration> FIG. 1 is a diagram showing an example of the configuration of a printing system that outputs and inspects a printed matter. The printing system in this embodiment includes an 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 inputs the print job to the printing device 190. The printing device 190 forms an image on a printing sheet (recording medium) based on the print job input from the printing server 180. The printing device 190 has a paper feed unit 191, and a user sets printing sheets in the paper feed unit 191 in advance. When a print job is input, the printing device 190 forms an image on one or both sides of the printing sheet while conveying the printing sheet set in the paper feed unit 191 along a conveying path 192, and sends the sheet to the image processing device 100.

[0013] The image processing device 100 performs an inspection process to check for defects on a printed material on which an image has been formed and which has been transported along a transport path 192. That is, the image processing device 100 functions as an inspection processing device. The image processing device 100 has a CPU 101, a RAM 102, a ROM 103, a main memory device 104, an image reading device 105, a printing device interface (I / F) 106, a general-purpose I / F 107, a user interface (UI) panel 108, and a main bus 109. Furthermore, the image processing device 100 has a transport path 110 for printed materials connected to the transport path 192 of the printing device 190, an output tray 111 for printed products which have passed the inspection, and an output tray 112 for printed products which have failed the inspection due to the detection of defects.

[0014] The CPU 101 is a processor that controls each part of the image processing device 100. The RAM 102 is a memory that functions as a work area of ​​the CPU 101. The ROM 103 is a memory that stores a group of programs executed by the CPU 101. The main storage device 104 stores applications executed by the CPU 101, data used in image processing, and the like. The image reading device (scanner) 105 reads one side or both sides of a printed matter sent from the printing device 190 on a conveying path 410, and obtains the read result as image data. The printing device I / F 106 is connected to the printing device 190, and the image processing device 100 and the printing device 190 can synchronize the processing timing of the printed matter and share each other's operating status. The general-purpose I / F 107 is a serial bus interface such as USB or IEEE1394, and allows a user to take out data such as logs. The UI panel 108 is, for example, a liquid crystal display, and functions as a user interface of the image processing device 100, and can display the current status and settings. The UI panel 108 receives instructions from the user via a touch panel or by pressing a button. A main bus 109 connects the various components of the image processing apparatus 100 together.

[0015] The image processing device 100 and each part of the printing system operate in response to instructions from the CPU 101. For example, in response to instructions from the CPU 101, it is possible to synchronously operate a plurality of transport paths, and to switch between sending printed matter to a pass output tray 111 or a fail output tray 112 in response to an inspection result. The image processing device 100 performs an inspection process based on image data of the printed matter read by the image reading device 105 while transporting the printed matter sent from the printing device 190 along the transport path 110. If the printed matter passes the inspection, it is transported to the pass output tray 111, and if not, it is transported to the fail output tray 112. This allows only those whose quality has been confirmed to be collected in the output tray 111 for delivery.

[0016] Although the image processing device 100 in this embodiment includes the image reading device 105 and the UI panel 108, the image processing device 100 is not limited to the above-mentioned configuration. For example, the image processing device 100 is a device having a CPU 101, a RAM 102, a ROM 103, a printing device I / F 106, a general-purpose I / F 107, and a main bus 109, and the image reading device 105, the UI panel 108, etc. may be separate devices.

[0017] <Functional configuration of image processing device> Fig. 2 is a block diagram showing an example of the functional configuration of the image processing device 100. The CPU 101 functions as the functional configuration shown in Fig. 2 by using the RAM 102 as a work memory and reading and executing a program stored in the ROM 103 or the main storage device 104. Note that it is not necessary for all of the processes shown below to be executed by the CPU 101, and the image processing device 100 may be configured so that part or all of the processes are executed by one or more processing circuits other than the CPU 101.

[0018] The image processing device 100 includes a manuscript data acquisition unit 201, an image acquisition unit 202, an object information acquisition unit 203, a positioning reference point setting unit 204, and an inspection processing unit 205. The manuscript data acquisition unit 201 acquires manuscript data for printing. The image acquisition unit 202 acquires scan image data obtained by reading a printed matter printed based on the manuscript data as image data to be inspected. The image acquisition unit 202 also acquires reference image data that is a reference for inspecting the printed matter. The object information acquisition unit 203 acquires object information using the manuscript data acquired by the manuscript data acquisition unit 201. The positioning reference point setting unit 204 sets a positioning reference point using the scan image data acquired by the image acquisition unit 202 and the object information set by the object information setting unit 203. The inspection processing unit 205 performs inspection processing of the scan image using a difference image generated based on a reference image represented by the reference image data and a scan image represented by the scan image data.

[0019] <Processing performed by the image processing device> The flow of processing executed by the image processing device 100 in this embodiment will be described with reference to the flowchart in Fig. 3. The processing shown in the flowchart in Fig. 3 starts when a user inputs an instruction via the UI panel 108 and the CPU 101 accepts the input instruction. Hereinafter, each step (process) will be represented by adding an S before the reference number.

[0020] In S301, the manuscript data acquisition unit 201 acquires manuscript data stored in advance in the main storage device 104 or the like. In S302, the image acquisition unit 202 acquires scan image data and reference image data stored in advance in the main storage device 104 or the like. The image acquisition unit 202 may generate scan image data and reference image data based on manuscript data, instead of acquiring scan image data and reference image data stored in advance. The scan image data can be generated by causing the printing device 190 to print based on the manuscript data, and causing the image reading device 105 to read the printed matter obtained by printing. The reference image data can be generated by performing RIP processing on the manuscript data, or by synthesizing data obtained by reading multiple printed matters printed based on the manuscript data.

[0021] In S303, the object information acquisition unit 203 acquires object information from the manuscript data. The object information represents area information and attribute information of each object included in the manuscript image of the manuscript data. The area information indicates the position of each object in the manuscript image. The attribute information indicates attributes of the object, such as an image, a character, a fixed print area, and a variable print area. The object information acquisition unit 203 in this embodiment acquires object information using manuscript data described in PPML (Personalized Printing Markup Language). PPML is a language for describing a manuscript image by dividing it into a fixed print area and a variable print area. The fixed print area indicates an area that does not change for each print. The variable print area indicates an area whose contents may change for each print, such as a date and time or a name. Note that the above method of acquiring object information is an example, and other known methods may be used.

[0022] In S304, the alignment reference point setting unit 204 sets an alignment reference point for aligning the reference image and the scanned image using the scanned image data acquired in S301 and the object information acquired in S303. The process of setting the alignment reference point will be described with reference to the flowchart in FIG.

[0023] In S401, the alignment reference point setting unit 204 performs initial alignment between the reference image and the scanned image. The initial alignment is performed by matching the coordinates of the four corners of the paper, but the initial alignment may be performed by other methods. In S402, the alignment reference point setting unit 204 sets an area for searching for the alignment reference point using the object information acquired in S303. The process of setting the area for searching for the alignment reference point will be described with reference to the flowchart in FIG.

[0024] In S501, the alignment reference point setting unit 204 sets one piece of object information from the object information acquired in S303 as a processing target. In S502, the alignment reference point setting unit 204 determines whether the object information to be processed indicates a fixed print area. FIG. 7A is a diagram showing an example of object information included in manuscript data. A manuscript image 701 has a fixed print area 702 and a variable print area 703. If the object information indicates a fixed print area, the process transitions to S504, and if the object information does not indicate a fixed print area, the process transitions to S503.

[0025] In S503, the alignment reference point setting unit 204 excludes the area indicated by the object information to be processed from the search area for the alignment reference point. FIG. 7B is a diagram showing an example of a scanned image. In the example of FIG. 7B, the alignment reference point setting unit 204 performs processing to exclude the area of ​​the scanned image 704 corresponding to the area information of the variable print area 703 from the search area for the alignment reference point. In S504, the alignment reference point setting unit 204 sets the area indicated by the object information to be processed as the search area for the alignment reference point. In the example of FIG. 7B, the alignment reference point setting unit 204 performs processing to set the area of ​​the scanned image 704 corresponding to the area information of the fixed print area 702 as the search area for the alignment reference point.

[0026] In S505, the alignment reference point setting unit 204 determines whether or not there is any object information remaining that has not yet been determined as indicating a fixed print area. If there is any object information remaining, the object information to be processed is updated and the process proceeds to S502. If there is no object information remaining, the process of S402 ends and the process proceeds to S403.

[0027] In S403, the alignment reference point setting unit 204 detects feature points in the scanned image within the search area for the alignment reference point set in S402, and sets the detected feature points as alignment reference points. FIG. 6 shows an example of alignment reference points detected in a scanned image. The alignment reference point setting unit 204 detects feature point 602 as the alignment reference point based on a corner feature amount in a scanned image 601. The well-known Harris corner detection algorithm is used to derive the corner feature amount, but other methods may also be used to derive the corner feature amount. In addition, the method of detecting feature points is not limited to the method using corner features, and pixels having other features may be used as feature points.

[0028] In S305, the inspection processing unit 205 performs alignment processing between the reference image and the scanned image so as to align the coordinates of the alignment reference point set in S304. In S306, the inspection processing unit 205 generates a difference image that represents the difference between the aligned reference image and the scanned image. If a pixel value equal to or greater than a threshold exists in the difference image, the inspection processing unit 205 determines that the print has failed the inspection, displays a notice of failure on the UI panel 108, and causes the print to be output to the output tray 112 for failure. If a pixel value equal to or greater than a threshold exists in the difference image, the inspection processing unit 205 determines that the print has passed the inspection, displays a notice of pass on the UI panel 108, and causes the print to be output to the output tray 111 for failure. Note that the criteria for passing and failing the inspection are not limited to the above example, and may be, for example, a failure when a predetermined number of defects are detected.

[0029] As described above, the image processing device 100 in this embodiment sets the search area for the alignment reference point using object information included in the manuscript data. Specifically, the image processing device 100 sets an area such as a fixed print area where it is difficult to erroneously detect the alignment reference point as the search area, and sets an area such as a variable print area or a printed area where it is easy to erroneously detect the alignment reference point as the non-search area. As shown in FIG. 7B, the scanned image 704 may include a printed area 705 and an area 706 including contaminants such as paper waste depending on the influence of the printing paper and the printing conditions. FIG. 7C is a diagram showing an example of the search area for the alignment reference point in the scanned image. A search area 707 and a non-search area 708 are set by the process of setting the search area for the alignment reference point. This makes it possible to detect the alignment reference point without using an area such as a variable print area, a printed area, or an area of ​​contaminants where it is easy to erroneously detect the alignment reference point. Therefore, even if the image to be inspected includes a local deformation, the image to be inspected and the reference image can be aligned with high accuracy.

[0030] <Variation 1> In the process of setting the search area for the alignment reference point in S402 of this embodiment, only the fixed print area is set as the search area for the alignment reference point, but the method of setting the search area is not limited to this. In this modified example, it is determined whether or not the scanned image contains a printed area and an area of ​​impurities, and if not, an area other than the variable print area is set as the search area for the alignment reference point. This makes it possible to use information on the four corners of the paper that are not included in the fixed print area indicated by the object information for alignment. The process of setting the area for searching for the alignment reference point will be described using the flowchart in FIG. 8.

[0031] In S801, the alignment reference point setting unit 204 performs a setting process for the print paper. The setting process for the print paper will be described with reference to the flowchart of FIG. 9. In S901, the alignment reference point setting unit 204 determines whether the scanned image 704 includes a printed area 705. Specifically, the alignment reference point setting unit 204 performs the determination using a user instruction, received via the UI panel 108, indicating whether the scanned image includes a printed area. If there is no printed area, the process proceeds to S902, and if there is a printed area, the process proceeds to S903. Note that the determination of whether the scanned image includes a printed area is not limited to the above method, and may be performed based on information about the printed area included in the manuscript data, for example. Also, instead of transitioning to S903 when there is a printed area, the process may transition to S902 by excluding the printed area from the search area.

[0032] In S902, the alignment reference point setting unit 204 determines whether or not the scanned image 704 includes an area 706 of impurities. Specifically, the alignment reference point setting unit 204 determines whether or not the area 706 of impurities is included using type information of the printing paper. If there is an area of ​​impurities, the process proceeds to S903, and if there is no area of ​​impurities, the process proceeds to S904. In S903, the alignment reference point setting unit 204 performs print setting A for setting only the fixed print area as the search area of ​​the alignment reference point. In S904, the alignment reference point setting unit 204 performs print setting B for setting the area other than the variable print area as the search area of ​​the alignment reference point. Note that the print setting A is a setting in which the fixed print area is set as the search area in S802 to S804 from a state in which the search area of ​​the alignment reference point has not been set. Moreover, print setting B is a setting in which the entire area of ​​the scanned image is set as the search area for the alignment reference point, and then the variable print area is excluded from the search area in steps S802 to S804.

[0033] In S802, the alignment reference point setting unit 204 sets one piece of object information among the object information acquired in S303 as a processing target. In S803, the alignment reference point setting unit 204 sets a search area for the alignment reference point based on the print setting in S801. Specifically, in the case where the object information indicates a fixed print area in the print setting A, the alignment reference point setting unit 204 sets the fixed print area as the search area for the alignment reference point. In the case where the object information indicates a variable print area in the print setting A, the alignment reference point search area is not set. In the case where the object information indicates a fixed print area in the print setting B, the alignment reference point is not excluded from the search area. In the case where the object information indicates a variable print area in the print setting B, the variable print area is excluded from the search area for the alignment reference point.

[0034] In S804, the alignment reference point setting unit 204 determines whether or not there is any object information remaining that has not yet been determined as indicating a fixed print area. If there is any object information remaining, the object information to be processed is updated and the process proceeds to S803. If there is no object information remaining, the process of S402 is terminated and the process proceeds to S403.

[0035] As described above, the image processing device 100 in this modified example switches the setting method of the search area of ​​the alignment reference point according to the setting process of the print paper. FIG. 10 is a diagram showing a scanned image, a search area of ​​the alignment reference point, and feature points. The scanned image 1001 includes a fixed print area 1002 and a variable print area 1003. Since the scanned image 1001 does not include a printed area or an area of ​​impurities, the print setting B is set in S904. In other words, an area other than the variable print area 1006 is set as the search area of ​​the alignment reference point. This allows information that improves alignment accuracy, such as not only the alignment reference point 1005 but also the paper corners 1004 that are not included in the fixed print area, to be used as the alignment reference point.

[0036] <Variation 2> In the detection of the alignment reference point in S403 of this embodiment, the alignment reference point setting unit 204 may determine the priority of the alignment reference point setting for each object information. FIG. 11 is a diagram showing an example of manuscript data. For example, the alignment reference point setting unit 204 sets a high priority to the object information 1102 indicating the fixed print area in the manuscript data 1101, and sets a low priority to the object information 1103. The alignment reference point setting unit 204 acquires more reference points from the fixed print area indicated by the object information 1102 than from the fixed print area indicated by the object information 1103 according to the set priority. The priority may be set based on a user instruction, or may be set according to the area occupied by the object in the manuscript image. This modified example makes it possible to acquire more alignment reference points from the area that requires focused alignment.

[0037] <Variation 3> In the detection of the alignment reference point in S403 of this embodiment, the alignment reference point setting unit 204 may divide the scan image into a grid and detect a predetermined number of feature points in each grid. FIG. 12 is a diagram showing an example of the alignment reference point acquired on the scan image. The alignment reference points 1202 and 1203 in the scan image 1201 indicate feature points detected based on the corner feature amount in the search area. In the scan image 1201 divided into a grid, if there are more than a predetermined number of feature points in each grid, the feature points are set as alignment reference points in descending order of the corner feature amount until the predetermined number is satisfied. Note that the number of divisions of the scan image and the number of alignment reference points in the grid can be set to any value. In addition, the method of selecting the feature points is not limited to comparing the size of the corner feature amount. In addition, after detecting the feature points in the scan image, the scan image may be divided into a grid and the alignment reference points may be selected from the grid. In addition, the division method is not limited to the grid as long as the scan image can be divided into a plurality of regions. According to this modification, the alignment reference points can be set without bias in their positions within the scanned image, thereby improving the alignment accuracy.

[0038] [Second embodiment] In this embodiment, the purpose is to prevent the printing on the back side from being seen through from the front side in double-sided printing, resulting in erroneous detection of feature points, and a search area for the alignment reference point is set using object information for each of the front and back sides. Note that the hardware configuration and functional configuration of the image processing device in this embodiment are the same as those in the first embodiment, so a description will be omitted. The following mainly describes the processing of S303 and S402, which are different between this embodiment and the first embodiment.

[0039] <Getting object information> In S303, the object information acquisition unit 203 acquires object information for the front and back sides of the printing paper. The determination as to whether it is the back side or not is made based on whether the page of the printing side is an even page or an odd page. In this embodiment, in S402, the size information of the printing paper is used to derive in which area the back side of the printing paper exists when observed from the front side, but it may be derived in S303.

[0040] <Setting the search area for the alignment reference point> In S402, the alignment reference point setting unit 204 sets an area for searching for the alignment reference point, using the object information acquired in S303. The process of setting the area for searching for the alignment reference point will be described with reference to the flowchart in FIG.

[0041] In S1301, the alignment reference point setting unit 204 sets a search area for the alignment reference point by the processes of S501 to S505 described in the first embodiment. Note that the object information used in the processes of S501 to S505 is the object information of the front side. In S1302, the alignment reference point setting unit 204 uses the object information of the back side of the printing paper to specify an overlap area where an object on the front side of the printing paper and an object on the back side that is visible through the front side overlap. Fig. 14 is a diagram showing an overlap area where an object on the front side and an object on the back side overlap.

[0042] The alignment reference point setting unit 204 acquires area information of an object 1402 in a front document image 1401 and area information of an object 1404 in a back document image 1403. When the object on the back side is viewed from the front side, the position of the area is reversed left to right. The alignment reference point setting unit 204 derives the coordinates of the object on the back side that is reversed left to right using the size information of the printing paper and the coordinates of the four corners indicated by the area information of the object on the back side. The area that overlaps with the area of ​​the object on the front side when the area surrounded by the derived coordinates is viewed from the front side is set as an overlap area 1405. Note that the setting of the overlap area is not limited to the above method, and for example, a mask process may be used.

[0043] In this case, a mask image may be generated so that area information of the object on the back side can be obtained, the mask image may be inverted left to right, and the generated mask image may be used to perform masking processing on the front side to set the overlap area.

[0044] In S1303, the alignment reference point setting unit 204 excludes the overlapping area from the search area for the alignment reference point set in S1301. FIG. 15 is a diagram showing the search area for the alignment reference point and the excluded area. An overlapping area 1502 in a search area 1501 for the alignment reference point is excluded from the search area 1501. As a result, a feature point 1503 detected from an area that does not overlap with an area where the back surface is see-through is set as the alignment reference point, and a feature point 1504 detected from an area that overlaps with an area where the back surface is see-through is not set as the alignment reference point. Note that in this embodiment, the overlapping area is excluded before detecting the feature point, but a feature point present in the overlapping area after detecting the feature point may be excluded from candidates for the alignment reference point.

[0045] As described above, the image processing device 100 in this embodiment sets the area for searching for the alignment reference point by using the object information on the front and back sides. This makes it possible to suppress erroneous detection of the alignment reference point on the front side even when the printing on the back side is visible depending on the type of printing paper.

[0046] [Other embodiments] The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) that implements one or more of the functions. [Explanation of symbols]

[0047] 100 Image processing device 202 Image acquisition unit 203 Object Information Acquisition Unit 204 Positioning reference point setting section 205 Inspection Processing Unit

Claims

1. a first acquisition means for acquiring reference image data that is a standard for inspecting a printed matter and scanned image data obtained by reading the printed matter; a second acquisition means for acquiring object information relating to an object included in a document image of the printed matter; a setting means for setting a reference point for aligning a reference image represented by the reference image data and a scanned image represented by the scanned image data based on the object information; a processing means for performing registration between the reference image and the scanned image based on the set reference point; 13. An image processing device comprising:

2. 2. The image processing apparatus according to claim 1, wherein the object information is information indicating an attribute of the object.

3. 2. The image processing apparatus according to claim 1, wherein the object information is information for identifying a fixed print area and a variable print area.

4. 2. The image processing apparatus according to claim 1, wherein the setting means sets an area in the scanned image for searching for the reference point based on the object information.

5. 5. The image processing apparatus according to claim 4, wherein the setting means sets a fixed print area in the scanned image as the area for searching for the reference point, based on the object information.

6. 5. The image processing apparatus according to claim 4, wherein the setting means excludes a variable print area in the scanned image from the area for searching for the reference point, based on the object information.

7. 5. The image processing apparatus according to claim 4, wherein the setting means sets an area other than a variable print area in the scanned image as the area for searching for the reference point, based on the object information.

8. the second acquisition means acquires the object information for each of the front and back sides of the printed matter, 2. The image processing apparatus according to claim 1, wherein said setting means sets said reference point based on object information of the front and back sides.

9. The image processing device according to claim 1, characterized in that the setting means sets a priority to the object information, and sets the reference points so that the number of reference points in a first object is greater than the number of reference points of a second object having a lower priority than the first object.

10. 2. The image processing apparatus according to claim 1, wherein said setting means divides said scanned image into a plurality of regions, and sets said reference point in each of the regions obtained by division.

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

12. Obtaining reference image data that is a standard for inspecting a printed matter and scanned image data obtained by reading the printed matter; Obtaining object information regarding an object included in a document image of the printed matter; setting a reference point for aligning a reference image represented by the reference image data and a scanned image represented by the scanned image data based on the object information; aligning the reference image with the scanned image based on the set reference point; 13. An image processing device comprising:

Images