Image processing device, image forming device, and image processing method

Abstract

To obtain an image processing apparatus and the like with which appropriate actions can be easily selected and image quality can be easily improved at the occurrence of an image quality abnormality.SOLUTION: An abnormality detection unit 12 detects an abnormal object in target images that are repeatedly acquired. An abnormal classification selection unit 13 selects, for every target image, any one abnormal classification from among a plurality of predetermined abnormal classifications based on the values of at least two basic feature amounts for the abnormal object. A feature amount monitoring unit 14 monitors the values of the basic feature amounts and the value of an auxiliary feature amount corresponding to an abnormal classification selected at the present time by the abnormality classification selection unit 13. An adjustment processing unit 15 executes adjustment processing corresponding to the auxiliary feature amount monitored by the feature amount monitoring unit 14. The abnormal classification selection unit 13 changes an abnormal classification to be selected according to a change in the above-mentioned value of the basic feature amount.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] In general, in image processing devices such as multifunction peripherals and printers, abnormal images (abnormal objects) may occur in printed products or scanned images due to specific causes in the image processing device. Examples of abnormal images include unintended streaks or dots, and unevenness that spreads across the entire printed product or scanned image.

[0003] One image processing device determines whether image quality has improved after performing a certain action on poor image quality, and if the image quality has improved, saves the relationship between the image features and the action as statistical data, and uses the statistical data to estimate the action corresponding to the image features when the image quality is poor (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2016-25646 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the above-mentioned image processing device, if an action is taken to address poor image quality but the image quality does not improve, a notification to that effect is displayed, and the image features and the action (the action that did not improve the image quality) are associated and stored in a database, but as a result, the image quality is not improved.

[0006] The present invention has been made in consideration of the above problems, and aims to provide an image processing device, an image forming device, and an image processing method that make it easier to select appropriate measures and improve image quality in the event of an image quality abnormality. [Means for solving the problem]

[0007] The image processing device according to the present invention includes an anomaly detection unit that detects an abnormal object in a target image that is repeatedly acquired, an anomaly type selection unit that selects, for each of the target images, one of a plurality of predetermined anomaly types based on values ​​of at least two basic feature values ​​for the abnormal object, and a feature amount monitoring unit that monitors the values ​​of the basic feature amounts and the values ​​of auxiliary feature amounts corresponding to the anomaly type currently selected by the anomaly type selection unit. and an adjustment processing unit that executes an adjustment process corresponding to the auxiliary feature monitored by the feature monitoring unit. The abnormality type selection unit changes the selected abnormality type in response to a change in the value of the basic feature. The device further includes the following configuration (A) or (B): (A) when the value of the basic feature amount belongs to one of a plurality of defect feature areas corresponding to the plurality of defect types, the anomaly type selection unit selects the anomaly type of the defect feature area to which the value of the basic feature amount belongs, and when the value of the basic feature amount does not belong to any of the plurality of defect feature areas, the anomaly type selection unit selects an anomaly type based on a distance from a coordinate indicated by the value of the basic feature amount in a coordinate system of the at least two basic feature amounts to the defect feature area. (B) when the anomaly type selected by the anomaly type selection unit is changed, the adjustment processing unit executes the adjustment processing after the change while keeping the adjustment processing before the change applied.

[0008] An image forming apparatus according to the present invention includes the image processing apparatus described above and an internal device that generates the target image.

[0009] The image processing method according to the present invention includes an abnormality detection step of detecting an abnormal object in a target image repeatedly acquired, an abnormality type selection step of selecting one of a plurality of predetermined abnormality types for each target image based on values ​​of at least two basic feature amounts for the abnormal object, a feature amount monitoring step of monitoring the values ​​of the basic feature amounts and the auxiliary feature amounts corresponding to the abnormality type currently selected by the abnormality type selection step, and an adjustment processing step of executing an adjustment processing corresponding to the auxiliary feature amount monitored by the feature amount monitoring step.The abnormality type selection step changes the selected abnormality type in response to a change in the value of the basic feature amount. The method further includes the following configuration (A) or (B): (A) in the anomaly type selection step, when the value of the basic feature amount belongs to any one of a plurality of defect feature areas corresponding to the plurality of anomaly types, an anomaly type of the defect feature area to which the value of the basic feature amount belongs is selected, and when the value of the basic feature amount does not belong to any one of the plurality of defect feature areas, an anomaly type is selected based on a distance from a coordinate indicated by the value of the basic feature amount in a coordinate system of the at least two basic feature amounts to the defect feature area. (B) in the adjustment processing step, when the selected anomaly type is changed, the adjustment processing after the change is executed while the adjustment processing before the change is applied. Effect of the Invention

[0010] According to the present invention, an image processing device, an image forming device, and an image processing method can be obtained that facilitate the selection of an appropriate measure and the improvement of image quality in the event of an image quality abnormality.

[0011] The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram showing a configuration of an image processing device according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram illustrating the feature amount of an abnormal object. [Diagram 3] FIG. 3 is a diagram for explaining normality determination regions and defect feature regions in a coordinate system of basic feature amounts for each abnormality type. [Figure 4] FIG. 4 is a diagram for explaining the movement of the coordinate position indicated by the measurement value of the basic feature amount in the coordinate system of the basic feature amount. [Diagram 5] FIG. 5 is a flowchart illustrating the operation of the image processing device shown in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] Fig. 1 is a block diagram showing the configuration of an image processing device according to an embodiment of the present invention. The image processing device shown in Fig. 1 is an information processing device such as a personal computer or a server, or an electronic device such as a digital camera or an image forming device (scanner, multifunction machine, etc.), and includes an arithmetic processing device 1, a storage device 2, a communication device 3, a display device 4, an input device 5, an internal device 6, etc.

[0015] The arithmetic processing device 1 includes a computer, and executes an image processing program on the computer to operate as various processing units. Specifically, the computer includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like, and operates as a specific processing unit by loading a program stored in the ROM or storage device 2 into the RAM and executing the program on the CPU. The arithmetic processing device 1 may also include an ASIC (Application Specific Integrated Circuit) that functions as a specific processing unit.

[0016] The storage device 2 is a non-volatile storage device such as a flash memory, and stores an image processing program and data necessary for the processing described below. The image processing program is stored in, for example, a non-transitory computer-readable recording medium, and is installed in the storage device 2 from the recording medium.

[0017] The communication device 3 is a device that performs data communication with an external device, such as a network interface, a peripheral device interface, etc. The display device 4 is a device that displays various information to the user, such as a display panel such as a liquid crystal display, etc. The input device 5 is a device that detects user operations, such as a keyboard, a touch panel, etc.

[0018] The internal device 6 is a device that executes a predetermined function of the image processing device. For example, if the image processing device is an image forming device, the internal device 6 is an image reading device that optically reads an original image from an original, a printing device that prints an image on a printing paper, or the like.

[0019] Here, the arithmetic processing device 1 operates as the target image acquisition unit 11, the abnormality detection unit 12, the abnormality type selection unit 13, the feature amount monitoring unit 14, and the adjustment processing unit 15, which are the above-mentioned processing units.

[0020] The target image acquisition unit 11 repeatedly acquires target images (image data) from the storage device 2, the communication device 3, the internal device 6, etc., and stores them in a RAM, etc. The target images are obtained, for example, by scanning a printout obtained by printing a predetermined reference image. The reference images (image data) are stored in the storage device 2 in advance.

[0021] The anomaly detection unit 12 compares the repeatedly acquired target image with a reference image to detect an abnormal object in the target image.

[0022] For example, the anomaly detection unit 12 (a) generates a first feature map obtained by performing a filter process on the target image and a second feature map obtained by performing the same filter process on the reference image, generates an image of the difference between the first feature map and the second feature map, and detects objects in the image of the difference as abnormal objects. This filter process is set according to the type of abnormal object (dot, line, etc.), such as streaks, dots, unevenness, etc. For example, a second derivative filter, a Gabor filter, etc. are used for this filter process.

[0023] The anomaly type selection unit 13 selects one of a plurality of predetermined anomaly types for each target image based on the values ​​of at least two basic feature amounts for the abnormal object. That is, the anomaly type selection unit 13 estimates the anomaly type corresponding to the abnormal object. Specifically, the anomaly type selection unit 13 selects the anomaly type corresponding to the abnormal object based on (a) the value of the basic feature amount and the positional relationship between the defect feature area corresponding to the plurality of anomaly types.

[0024] At this time, the abnormality type selection unit 13 changes the selected abnormality type in response to a change in the value of the basic characteristic amount described above.

[0025] In this embodiment, when the value of the basic feature amount belongs to any of the defect feature areas, the anomaly type selection unit 13 selects the anomaly type of the defect feature area to which the value of the basic feature amount belongs. In other words, when the value of the basic feature amount changes over time and the defect feature area to which the value of the basic feature amount belongs changes to another, the selected anomaly type is changed to another one.

[0026] In this embodiment, when the value of the basic feature does not belong to any of the defect feature regions, the anomaly type selection unit 13 selects an anomaly type based on the distance from the coordinate position indicated by the value of the basic feature in the coordinate system of the at least two basic feature values ​​to the defect feature region. Specifically, the anomaly type with the shortest distance is selected. In other words, when the value of the basic feature changes over time and the defect feature region with the shortest distance from the coordinate position of the basic feature changes to another one, the selected anomaly type is changed to another one.

[0027] In this embodiment, when the value of the basic feature does not belong to any of the defect feature regions, the anomaly type selection unit 13 selects an anomaly type based on the distance from the coordinates indicated by the value of the basic feature in the coordinate system of the at least two basic feature values ​​to the defect feature region, and then classifies the abnormal object as an unknown anomaly if the image quality based on the auxiliary feature is not improved even after performing an adjustment process described below. In other words, if the change in the value of the auxiliary feature does not indicate an improvement in image quality, the abnormal object is classified as an unknown anomaly.

[0028] For example, as described below, if the known (registered) anomaly types are drum leak, lure, and pattern, when an abnormal object occurs due to the adhesion of dust, the abnormal object may be classified as an unknown anomaly.

[0029] The feature amount monitoring unit 14 monitors the values ​​of the above-mentioned basic feature amounts and the values ​​of one or more auxiliary feature amounts corresponding to the abnormality type currently selected by the abnormality type selecting unit 13 .

[0030] In order to monitor the values ​​of the basic feature (or the basic feature and auxiliary feature), the target image acquisition unit 11 repeatedly acquires the target image at specific time intervals or measurement timing, the anomaly detection unit 12 detects abnormal objects from the target image at each acquisition time point, and the feature monitoring unit 14 identifies the values ​​of the basic feature (or the basic feature and auxiliary feature) of the detected abnormal object.

[0031] Here, the basic features and auxiliary features are pre-selected from a predetermined group of features for each abnormality type, the basic features are always subject to monitoring, and the auxiliary features are monitored only when the basic features satisfy specific conditions.

[0032] For example, the set of predetermined features may include the area, orientation, growth direction, density of the abnormal object, edge strength (edge ​​density difference) of the abnormal object, color of the abnormal object, period of the abnormal object, number of abnormal objects, etc.

[0033] 2 is a diagram illustrating the feature amounts of an abnormal object. For example, the abnormal objects 101, 102, and 103 in FIG. 2 are different from one another in terms of area, density, and edge strength.

[0034] Here, the orientation of the abnormal object is the longitudinal direction of the abnormal object, the growth direction is the growth direction of the abnormal object identified from the shape of the abnormal object obtained at a specific time interval, the density of the abnormal object is the average or median of the density of the abnormal object part in the target image or the difference between the average or median of the part other than the abnormal object in the target image and the average or median of the density of the object part, the edge strength of the abnormal object is the density gradient (density difference) of the edge of the abnormal object in the target image, the color of the abnormal object is the color of the abnormal object in the target image, the period of the abnormal object is the spatial period of multiple abnormal objects, and the number of abnormal objects is the number of abnormal objects of each object type.

[0035] The adjustment processing unit 15 automatically executes adjustment processing (such as print process conditions) corresponding to the auxiliary feature (or basic feature and auxiliary feature) monitored by the feature monitoring unit 14.

[0036] The adjustment processing unit 15 executes an adjustment process for the internal device 6 that generates the target image. Specifically, in the adjustment process, the setting values ​​of the internal device 6 and the setting values ​​of various processes (printing process, etc.) in the internal device 6 are changed. Here, the setting values ​​of the conditions of the electrophotographic print process in the printing device of the internal device 6 are adjusted. In other words, the adjustment processing unit 15 performs feedback control of the setting values ​​of the conditions of the print process.

[0037] Furthermore, when the abnormality type selected by the abnormality type selection unit 13 is changed, the adjustment processing unit 15 executes the adjusted adjustment process after the change (here, the setting value of the setting item among the print process conditions corresponding to the abnormality type before the change) while keeping the adjustment process before the change (here, the setting value of the setting item among the print process conditions corresponding to the abnormality type after the change) applied (i.e., without restoring the setting value before the adjustment process).

[0038] Fig. 3 is a diagram for explaining normality determination regions and defect feature regions in a coordinate system of basic feature amounts for each abnormality type. For example, as shown in Fig. 3, in the coordinate system of basic feature amounts (here, a planar space of basic feature amount A and basic feature amount B), normality determination regions and defect feature regions exist for each abnormality type. The normality determination regions are regions determined to not require adjustment processing, which will be described later, and the defect feature regions are regions determined to require adjustment processing, which will be described later.

[0039] FIG. 4 is a diagram for explaining the movement of the coordinate position indicated by the measurement value of the basic feature amount in the coordinate system of the basic feature amount.

[0040] For example, as shown in Fig. 4, for each of a plurality of anomaly types, a defect characteristic region and an auxiliary feature are set. Note that the list of the plurality of anomaly types and information on the defect characteristic region and the auxiliary feature associated with each anomaly type are stored in advance as data in the storage device 2, and are read out and used as necessary.

[0041] In the example shown in Fig. 4, in the initial state (t0), the coordinate position of the basic feature of the abnormal object belongs to the defect feature area of ​​anomaly type #1, and monitoring of the auxiliary feature C corresponding to anomaly type #1 is started. After a predetermined time has elapsed (measurement timing t1), if an abnormal object is detected again and the image quality has deteriorated rather than improved due to the increase in area, an adjustment process corresponding to the value of the auxiliary feature C is executed. Note that if the selection of the anomaly type is correct, the image quality is improved by the adjustment process (i.e., the coordinate position of the basic feature moves to the normal judgment area).

[0042] For example, if basic feature A is the area of ​​the abnormal object, basic feature B is the edge density difference, and abnormality type #1 is a drum leak, the abnormal object caused by the drum leak grows in the horizontal direction, so the horizontal length of the abnormal object is set as auxiliary feature C. Then, since the image quality has not improved after a predetermined time has elapsed (t1), the process conditions are adjusted to reduce the drum leak according to the measurement value of auxiliary feature C.

[0043] However, after the process conditions are adjusted (measurement timing t2), if the image quality deteriorates further and the coordinate position of the basic feature of the abnormal object moves out of the defect feature area of ​​anomaly type #1 and falls within the defect feature area of ​​anomaly type #2 and the defect feature area of ​​anomaly type #3, the selected anomaly type is changed from anomaly type #1 to anomaly type #2 or anomaly type #3.

[0044] At this time, the abnormality type #2 or the abnormality type #3 is selected, which has the shortest distance from the coordinate position of the basic feature to the defect feature region. This distance is the Mahalanobis distance or the Euclidean distance. Alternatively, the abnormality type corresponding to the coordinate position of the basic feature may be selected by the maximum likelihood method.

[0045] For example, abnormality type #2 is a scam (image defect caused by overcharging of toner), and abnormality type #3 is a print. In this case, when abnormality type #2 is selected, monitoring of auxiliary feature D is started and process conditions are adjusted to reduce the scam, and when abnormality type #3 is selected, monitoring of auxiliary feature E is started and process conditions are adjusted to reduce the print. Note that, since prints have the characteristic of changing from white dots to black dots, auxiliary feature E is treated as color information.

[0046] If the image quality is not improved even after the adjustment process and the coordinate position of the basic feature does not belong to any of the defect feature areas (i.e., it is difficult to determine the type of abnormality using basic feature A and B), then, in the same manner as described above, one of the abnormality types (e.g., the one with the shortest distance) is selected based on the distance from the coordinate position of the measurement value of the basic feature to the defect feature area.

[0047] Next, a description will be given of the operation of the image processing device shown in Fig. 1. Fig. 5 is a flow chart illustrating the operation of the image processing device shown in Fig. 1.

[0048] The target image acquisition unit 11 repeatedly acquires a target image (image data) at the measurement timing (step S1). When the target image is acquired, the abnormality detection unit 12 attempts to detect an abnormal object based on the target image and the reference image, and determines whether an abnormal object is detected (step S2).

[0049] If no abnormal object is detected, it is determined to be in a normal state, and no adjustment processing is performed. On the other hand, if an abnormal object is detected, the feature amount monitoring unit 14 identifies the measurement values ​​of the basic feature amounts of the detected abnormal object (the coordinate position in a coordinate system of the basic feature amounts consisting of the values ​​of a plurality of basic feature amounts) (step S3).

[0050] Next, the abnormality type selection unit 13 determines whether the abnormal object can be classified into a known abnormality type (step S4). Specifically, the abnormality type selection unit 13 determines whether the coordinate position of the basic feature in the coordinate system of the basic feature belongs to at least one of a predetermined number of defect feature regions.

[0051] If the abnormal object can be classified into a known abnormality type, the abnormality type selection unit 13 selects an abnormality type whose coordinate position of the basic feature belongs to a defect feature region (step S5). At this time, if the coordinate position of the basic feature belongs to defect feature regions of multiple abnormality types, the abnormality type is selected based on distance, etc., as described above.

[0052] On the other hand, if the abnormal object cannot be classified into a known abnormality type, the abnormality type selection unit 13 selects the abnormality type of the defect feature region near the coordinate position of the basic feature (step S6). At this time, as described above, the abnormality type is selected based on the distance, etc.

[0053] Then, the feature monitoring unit 14 identifies an auxiliary feature corresponding to the selected anomaly type and monitors the value of the auxiliary feature (step S7). Specifically, the value of the auxiliary feature of the abnormal object is measured. At this time, if the auxiliary feature is a feature regarding a change over time (such as the growth of the abnormal object in a specific direction), the value of the auxiliary feature is obtained from the measurement timing next to the start of monitoring.

[0054] The adjustment processing unit 15 identifies an adjustment item corresponding to the abnormality type among the process conditions, and adjusts the setting value of the adjustment item according to the measurement value of the auxiliary feature amount or the like (step S8).

[0055] Thereafter, if the adjustment limit condition is not satisfied (step S9), the process at the current measurement timing is terminated. The adjustment limit condition is, for example, that no image quality improvement is obtained even after a predetermined time has elapsed after the adjustment process. The image quality improvement is determined based on the values ​​of the basic feature amount and auxiliary feature amount. On the other hand, if the adjustment limit condition is satisfied, the current abnormality (abnormal object) is classified as an unknown abnormality, and is notified to the user, service person, etc. (step S10).

[0056] Thereafter, if the process conditions for the unknown anomaly are manually adjusted and an image quality improvement is obtained, the defect feature region, auxiliary feature, and adjustment process for the unknown anomaly are registered as a new anomaly, so that the adjustment process is automatically performed for the anomaly from the next time onwards.

[0057] If the anomaly type is selected correctly, the image quality is improved by an appropriate adjustment process, and the abnormal object is not detected at the next measurement timing. On the other hand, if the anomaly type is selected incorrectly, the image quality is not improved by the adjustment process, and the anomaly type is selected again. In this case, if the coordinates of the measurement value of the basic feature amount move to a defect feature region of another anomaly type, the other anomaly type is selected.

[0058] As described above, according to the above embodiment, the anomaly detection unit 12 detects an abnormal object in a target image that is repeatedly acquired. The anomaly type selection unit 13 selects one of a predetermined number of anomaly types based on the values ​​of at least two basic feature amounts for the abnormal object for each target image. The feature amount monitoring unit 14 monitors the value of the basic feature amount and the value of the auxiliary feature amount corresponding to the anomaly type currently selected by the anomaly type selection unit 13. The adjustment processing unit 15 executes an adjustment process corresponding to the auxiliary feature amount monitored by the feature amount monitoring unit 14. Then, the anomaly type selection unit 13 changes the anomaly type to be selected in response to a change in the value of the basic feature amount.

[0059] As a result, an abnormality type is appropriately selected at each point in time according to the value of the basic feature of the abnormal object, which changes over time as the abnormality progresses, an auxiliary feature corresponding to the selected abnormality type is selected, and an adjustment process corresponding to that auxiliary feature is executed. This makes it easier to select an appropriate measure (adjustment process) and to improve image quality in the event of an image quality abnormality.

[0060] It should be noted that various changes and modifications to the above-described embodiments will be apparent to those skilled in the art. Such changes and modifications may be made without departing from the spirit and scope of the subject matter and without diminishing its intended advantages. In other words, such changes and modifications are intended to be included within the scope of the claims.

[0061] For example, in the above embodiment, when the selected anomaly type has been changed a predetermined number of times, the anomaly of the abnormal object may be determined to be an unknown anomaly, and the process of step S10 described above may be executed.

[0062] Furthermore, in the above embodiment, if no improvement in image quality is obtained for a certain abnormality type despite the application of adjustment processing for a predetermined period of time to the abnormality type selection unit 13, the currently selected abnormality type may be forcibly changed to another abnormality type (an abnormality type other than the currently selected abnormality type, which is selected based on distance or the like as described above). [Industrial Applicability]

[0063] The present invention is applicable to, for example, detection of abnormalities in an image forming apparatus or the like. [Explanation of symbols]

[0064] 12 Anomaly detection section 13 Abnormality type selection section 14 Feature monitoring unit 15 Adjustment processing section

Claims

1. an anomaly detection unit that detects an abnormal object in the repeatedly acquired target images; an abnormality type selection unit that selects, for each of the target images, one of a plurality of predetermined abnormality types based on values ​​of at least two basic feature amounts of the abnormal object; a feature amount monitoring unit that monitors the value of the basic feature amount and the value of an auxiliary feature amount corresponding to the abnormality type currently selected by the abnormality type selection unit; an adjustment processing unit that executes an adjustment process corresponding to the auxiliary feature monitored by the feature monitoring unit, the abnormality type selection unit changes the selected abnormality type in response to a change in the value of the basic feature amount; the anomaly type selection unit, when the value of the basic feature amount belongs to any one of a plurality of defect feature areas corresponding to the plurality of anomaly types, selects the anomaly type of the defect feature area to which the value of the basic feature amount belongs; when the value of the basic feature amount does not belong to any of the plurality of defect feature areas, the abnormality type selection unit selects an abnormality type based on a distance from a coordinate indicated by the value of the basic feature amount in a coordinate system of the at least two basic feature amounts to the defect feature area; An image processing device comprising:

2. 2. The image processing device according to claim 1, wherein the anomaly type selection unit, when the value of the basic feature does not belong to any of the defect feature regions, selects an anomaly type based on a distance from the coordinates indicated by the value of the basic feature in a coordinate system of the at least two basic feature values ​​to the defect feature region, and then classifies the abnormal object as an unknown anomaly when image quality based on the auxiliary feature is not improved even after performing the adjustment process.

3. An anomaly detection unit that detects an abnormal object in a target image that is repeatedly acquired; an abnormality type selection unit that selects, for each of the target images, one of a plurality of predetermined abnormality types based on values ​​of at least two basic feature amounts of the abnormal object; a feature amount monitoring unit that monitors the value of the basic feature amount and the value of an auxiliary feature amount corresponding to the abnormality type currently selected by the abnormality type selection unit; an adjustment processing unit that executes an adjustment process corresponding to the auxiliary feature monitored by the feature monitoring unit, the abnormality type selection unit changes the selected abnormality type in response to a change in the value of the basic feature amount; the adjustment processing unit, when the abnormality type selected by the abnormality type selection unit is changed, executes the adjustment processing after the change while keeping the adjustment processing before the change applied.

4. An image processing device according to any one of claims 1 to 3, an internal device for generating the target image; An image forming apparatus comprising:

5. an anomaly detection step of detecting an abnormal object in the repeatedly acquired target images; an anomaly type selection step of selecting, for each of the target images, one of a plurality of predetermined anomaly types based on values ​​of at least two basic feature amounts of the abnormal object; a feature amount monitoring step of monitoring a value of the basic feature amount and a value of an auxiliary feature amount corresponding to the abnormality type currently selected in the abnormality type selection step; an adjustment processing step of executing an adjustment processing corresponding to the auxiliary feature monitored in the feature monitoring step, In the anomaly type selection step, the anomaly type to be selected is changed in response to a change in the value of the basic feature amount, in the anomaly type selection step, when the value of the basic feature amount belongs to any one of a plurality of defect feature areas corresponding to the plurality of anomaly types, an anomaly type of the defect feature area to which the value of the basic feature amount belongs is selected, and when the value of the basic feature amount does not belong to any one of the plurality of defect feature areas, an anomaly type is selected based on a distance from a coordinate indicated by the value of the basic feature amount in a coordinate system of the at least two basic feature amounts to the defect feature area; An image processing method comprising:

6. An anomaly detection step of detecting an abnormal object in a target image that is repeatedly acquired; an anomaly type selection step of selecting, for each of the target images, one of a plurality of predetermined anomaly types based on values ​​of at least two basic feature amounts of the abnormal object; a feature amount monitoring step of monitoring a value of the basic feature amount and a value of an auxiliary feature amount corresponding to the abnormality type currently selected in the abnormality type selection step; an adjustment processing step of executing an adjustment processing corresponding to the auxiliary feature monitored in the feature monitoring step, In the anomaly type selection step, the anomaly type to be selected is changed in response to a change in the value of the basic feature amount, In the adjustment processing step, when the selected abnormality type is changed, the adjustment processing after the change is executed while the adjustment processing before the change is applied; An image processing method comprising:

Images