JP2023005914A - Image processing apparatus, image forming apparatus, and image processing method - Google Patents

Abstract

To obtain an image processing apparatus, an image forming apparatus, and an image processing method in which when an abnormal object is detected, appropriate restoration is performed.SOLUTION: An abnormality detection unit 12 detects an abnormal object in a target image. A feature amount monitoring unit 13 (a) monitors the values of at least two basic feature amounts for the abnormal object, (b) determines whether the values of the basic feature amounts satisfy a predetermined monitoring determination condition of a specific abnormality classification, (c) when determining that the values of the basic feature amounts satisfy the monitoring determination condition, specifies a feature amount corresponding to the specific abnormality classification as an auxiliary feature amount for the abnormal object, and (d) starts monitoring the value of the auxiliary feature amount. A restoration processing unit 14 specifies a restoration method corresponding to part or all of the values of the basic feature amounts and the auxiliary feature amount monitored by the feature amount monitoring unit 13, and executes restoration processing corresponding to the abnormal object by using the specified restoration method.SELECTED DRAWING: Figure 1

Description

The present invention relates to an image processing apparatus, an image forming apparatus, and an image processing method.

2. Description of the Related Art Generally, in image processing apparatuses such as multifunction machines and printers, an abnormal image (abnormal object) may occur in a print product or a scanned image due to a specific cause in the image processing apparatus. Abnormal images are, for example, unintended streaks or dots, unevenness that spreads over the printed product or scanned image, and the like.

A certain image processing apparatus establishes a correspondence relationship between a difference between a reference feature amount obtained from a first chart and a feature amount obtained by scanning a second chart printed by the image processing apparatus, and a failure of the image processing apparatus. Based on this, the failure location of the image processing apparatus is estimated (see Patent Document 1, for example).

JP 2015-100080 A

However, in the image processing apparatus described above, there is a possibility that an incorrect failure location is estimated and an inappropriate repair method is selected in the repair work by the service person. In other words, there is a possibility that proper repair will not be performed. In particular, there is a possibility that the failure location of the image processing apparatus cannot be accurately estimated even if the difference in the feature amount at a certain point in time is referred to.

SUMMARY OF THE INVENTION It is an object of the present invention to provide an image processing apparatus, an image forming apparatus, and an image processing method that perform appropriate restoration when an abnormal object is detected.

An image processing apparatus according to the present invention comprises an anomaly detection unit for detecting an anomalous object in a target image; (a) monitoring at least two basic feature values of the anomalous object; determines whether or not a predetermined monitoring determination condition for a specific abnormality type is satisfied; (d) a feature monitoring unit that starts monitoring the value of the auxiliary feature, and the basic feature and the basic feature that are monitored by the feature monitoring unit. and a restoration processing unit that specifies a restoration method corresponding to part or all of the value of the auxiliary feature amount, and executes restoration processing corresponding to the abnormal object by the identified restoration method.

An image forming apparatus according to the present invention includes the image processing device described above and an internal device that generates the target image. Then, the restoration processing unit executes the restoration processing for the internal device.

An image processing method according to the present invention comprises the steps of detecting an abnormal object in a target image, (a) monitoring at least two basic feature values for said anomalous object, and (b) said basic feature values are: (c) when it is determined that the value of the basic feature quantity satisfies the monitoring judgment condition, the feature quantity corresponding to the specific abnormality type is determined; as an auxiliary feature for the abnormal object; identifying a repair method corresponding to the above, and performing a repair process corresponding to the abnormal object using the specified repair method.

According to the present invention, it is possible to obtain an image processing apparatus, an image forming apparatus, and an image processing method that perform appropriate restoration when an abnormal object is detected.

The above and other objects, features and advantages of the present invention will become further apparent from the following detailed description together with the accompanying drawings.

FIG. 1 is a block diagram showing the configuration of an image processing apparatus according to an embodiment of the invention. FIG. 2 is a diagram for explaining feature amounts of an abnormal object. FIG. 3 is a diagram illustrating the normality determination region, the monitoring determination region, and the usage limit determination region in the basic feature amount space for each abnormality type. FIG. 4 is a diagram for explaining selection of auxiliary feature values to be additionally monitored according to the value of the basic feature value. FIG. 5 is a diagram for explaining the start and end of monitoring of auxiliary features. FIG. 6 is a diagram for explaining setting value change patterns set for each of a plurality of repair conditions. FIG. 7 is a diagram for explaining the operation corresponding to the evaluation value after restoration processing. FIG. 8 is a flowchart for explaining the operation of the image processing apparatus shown in FIG. 1 (1/2). FIG. 9 is a flowchart explaining the operation of the image processing apparatus shown in FIG. 1 (2/2). 10A and 10B are diagrams for explaining the auxiliary feature amount evaluation processing in FIG. FIG. 11 is a diagram for explaining the repair method specifying process in FIG. 12A and 12B are diagrams for explaining the repair evaluation process in FIG. 9. FIG.

Embodiments of the present invention will be described below based on the drawings.

FIG. 1 is a block diagram showing the configuration of an image processing apparatus according to an embodiment of the invention. The image processing apparatus shown in FIG. 1 is an information processing apparatus such as a personal computer and a server, or an electronic device such as a digital camera, an image forming apparatus (scanner, multifunction machine, etc.). It includes a device 3, a display device 4, an input device 5, an internal device 6, and the like.

The arithmetic processing unit 1 includes a computer, and the computer executes an image processing program to operate as various processing units. Specifically, the computer includes a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc., and loads programs stored in ROM and storage device 2 into RAM, , it operates as a predetermined processing unit. Further, the arithmetic processing device 1 may include an ASIC (Application Specific Integrated Circuit) functioning as a specific processing unit.

The storage device 2 is a non-volatile storage device such as a flash memory, and stores image processing programs and data necessary for processing described later. The image processing program is stored, for example, in a non-temporary computer-readable recording medium, and installed in the storage device 2 from the recording medium.

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

The internal device 6 is a device that executes a predetermined function of the image processing device. For example, if the image processing apparatus is an image forming apparatus, the internal device 6 may be an image reading device that optically reads a document image from a document, a printing device that prints an image on printing paper, or the like.

Here, the arithmetic processing unit 1 operates as the target image acquisition unit 11, the abnormality detection unit 12, the feature amount monitoring unit 13, and the restoration processing unit 14 as the processing units described above.

The target image acquiring unit 11 acquires a target image (image data) from the storage device 2, the communication device 3, the internal device 6, etc., and stores it in a RAM or the like. Note that the target image is obtained, for example, by scanning a printed matter obtained by printing a predetermined reference image. Note that the reference image (image data) is stored in the storage device 2 in advance.

The anomaly detection unit 12 compares the target image and the reference image to detect an anomalous object in the target image.

For example, the abnormality detection unit 12 (a) generates a first feature map obtained by performing filtering on the target image and a second feature map obtained by performing the same filtering on the reference image. Then, an image of the difference between the first feature map and the second feature map is generated, and an object in the image of the difference is detected as an abnormal object. This filtering process is set according to the type of abnormal object (point, streak, etc.) such as streak, point, unevenness, and the like. As this filtering process, for example, a secondary differential filter, a Gabor filter, or the like is used.

The feature amount monitoring unit 13 (a) monitors at least two basic feature amount values for an abnormal object, and (b) whether or not the basic feature amount value satisfies a predetermined monitoring determination condition for a specific abnormality type. (c) when it is determined that the value of the basic feature value satisfies the monitoring determination condition, the feature value corresponding to the specific abnormality type is specified as an auxiliary feature value for the abnormal object; start monitoring the value of the auxiliary feature value.

The abnormality type is the type of abnormality cause (abnormal location). An abnormal point is, for example, a replaceable consumable unit.

In order to monitor the value of the basic feature amount (or basic feature amount and auxiliary feature amount), the target image acquisition unit 11 repeatedly acquires target images at specific time intervals or measurement timings, and the abnormality detection unit 12 An abnormal object is detected from the target image at each acquisition time, and the feature amount monitoring unit 13 specifies the value of the basic feature amount (or the basic feature amount and the auxiliary feature amount) of the detected abnormal object.

Here, the basic feature amount and the auxiliary feature amount are selected in advance from a predetermined feature amount group for each abnormality type, the basic feature amount is always monitored, and the auxiliary feature amount is the basic feature amount is monitored only when it meets certain conditions.

For example, this predetermined feature amount group includes feature amounts such as the area, orientation, growth direction, density of the abnormal object, edge strength of the abnormal object, color of the abnormal object, period of the abnormal object, number of abnormal objects, and the like. including.

FIG. 2 is a diagram for explaining feature amounts of an abnormal object. For example, the abnormal objects 101, 102, and 103 in FIG. 2 are abnormal objects of the abnormality type "point", and the abnormal objects 101, 102, and 103 have different areas, densities, and edge strengths.

Here, the direction of the abnormal object is the longitudinal direction of the abnormal object, and 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 is the average value or median value of the density of the abnormal object portion in the target image, or the difference value between the average value or median value of the portions other than the abnormal object in the target image and the average value or median value of the density of the object portion, The edge strength of an abnormal object is the density gradient 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, and the period of the abnormal object is the spatial period of the multiple abnormal objects. Yes, and the number of anomalous objects is the number of anomalous objects of each object type.

FIG. 3 is a diagram illustrating the normality determination region, the monitoring determination region, and the usage limit determination region in the basic feature amount space for each abnormality type.

For example, as shown in FIG. 3, in the basic feature amount space (here, a planar space formed by the basic feature amount A and the basic feature amount B), for each abnormality type, the normal determination area, the monitoring determination area, and the usage limit determination area exists. The usage limit determination area is an area where it is determined that the abnormality cannot be resolved by the repair process described later due to the service life or failure. The normal determination area is an area determined not to require repair processing, which will be described later, and the monitoring determination area is an area determined to require repair processing, which will be described later, depending on the situation. In the normal determination area, the value of the basic feature amount is monitored (the value of the auxiliary feature amount is not monitored), and in the monitoring determination area, the value of the auxiliary feature amount is monitored together with the value of the basic feature amount.

FIG. 4 is a diagram for explaining selection of auxiliary feature values to be additionally monitored according to the value of the basic feature value. When multiple types of abnormality to be judged are specified, there is a boundary (monitoring judgment boundary) between the normal judgment area and the monitoring judgment area for the multiple abnormality types, and the value of the basic feature amount exceeds the monitoring judgment boundary. When entering the monitoring determination area, monitoring of the value of the auxiliary feature is started. For example, as shown in FIG. 4, when the values of the basic feature amounts A and B are the measurement result #1, the values of the basic feature amounts A and B are within the monitoring determination region of the abnormality type #1, The auxiliary feature amount C corresponding to the abnormality type #1 and the auxiliary feature amount D corresponding to the abnormality type #2 are selected as the auxiliary feature amount which is within the monitoring determination area of the abnormality type #2 and whose monitoring should be started. For example, as shown in FIG. 4, when the values of the basic feature amounts A and B are the measurement result #2, the values of the basic feature amounts A and B are within the monitoring determination region of the abnormality type #3. , the auxiliary feature E corresponding to the abnormality type #3 is selected as the auxiliary feature for which monitoring should be started.

Monitoring of the auxiliary feature amount is started and ended according to the values of the basic feature amounts A and B. FIG. For example, a judgment formula corresponding to the monitoring judgment boundary r=f(A, B) (here, f is a function of A and B, A is the value of the basic feature A, and B is the value of the basic feature B is set, and the value r of the determination formula exceeds a predetermined threshold value TH1, it is determined that the value of the basic feature quantity has exceeded the monitoring determination boundary and entered the monitoring determination region. Note that the determination formula is specified in advance by experiments or the like, and may be approximately a linear formula (r=W1×A+W2×B+W3, where W1, W2, and W3 are constants). After that, when the value r of the determination formula becomes less than the predetermined threshold value TH2, it is determined that the value of the basic feature amount exceeds the monitoring determination boundary and is out of the monitoring determination area, and the monitoring of all auxiliary feature amounts is terminated. . Note that the threshold TH2 may be the same as or different from the threshold TH1.

Furthermore, it is determined whether or not to end monitoring for each auxiliary feature amount. That is, when there are a plurality of auxiliary feature values being monitored, it is individually determined whether or not to end monitoring for each auxiliary feature value. FIG. 5 is a diagram for explaining the start and end of monitoring of auxiliary features. For example, as shown in FIG. 5, when the value of the auxiliary feature being monitored deviates from the allowable error range σ from the specific prediction value V, the feature monitoring unit 13 monitors the value of the auxiliary feature. finish. This predicted value V is derived from the value of the basic feature amount at the start of monitoring by using a predetermined calculation formula, table, or the like. The predicted value V and the allowable error range σ are individually set for each auxiliary feature amount.

Further, the feature amount monitoring unit 13 (a) identifies a plurality of auxiliary feature amount sets as feature amounts corresponding to a specific abnormality type, and (b) selects one of the plurality of auxiliary feature amount sets. and specifying one or more feature amounts included in the selected auxiliary feature amount set as auxiliary feature amounts, and (c) monitoring of all one or more feature amounts included in the selected auxiliary feature amount set is completed. In that case, another auxiliary feature quantity set is selected from the plurality of auxiliary feature quantity sets, and one or more feature quantities included in the selected auxiliary feature quantity set are specified as auxiliary feature quantities. It should be noted that the plurality of auxiliary feature amount sets are selected in a predetermined order of priority.

For example, when measurement result #1 is obtained as shown in FIG. is set. At that time, the auxiliary feature associated with an abnormality type having a monitoring judgment boundary adjacent within a predetermined distance range from the value (coordinates) of the basic feature (here, the auxiliary feature associated with abnormality type #3 E), a set of auxiliary features C, D, and E, a set of auxiliary features E, and the like may also be set as the auxiliary feature set described above. Regarding the order of priority of these auxiliary feature quantity sets, priority is given to the auxiliary feature quantity set containing the auxiliary feature quantities C and D of both of the two abnormality types whose values of the basic feature quantities A and B fall within the monitoring determination region. The auxiliary feature quantity set having the highest priority, the auxiliary feature quantity set containing one of the auxiliary feature quantities C and D having the next highest priority, and containing the auxiliary feature quantity E corresponding to the adjacent monitoring decision boundary is given lower priority than the set that does not include the auxiliary feature E. For example, for this measurement result #1, a set of auxiliary features C and D, a set of auxiliary features D only, a set of auxiliary features C only, a set of auxiliary features C, D, and E, and an auxiliary feature E lower priority in the order of the set of

Further, for example, when measurement result #2 is obtained as shown in FIG. 4, a set of auxiliary feature amount E only and a set of auxiliary feature amount D and auxiliary feature amount E corresponding to the adjacent monitoring judgment boundary are set. be. For example, for this measurement result #2, the priority is lower in the order of the set of the auxiliary feature amount E only and the set of the auxiliary feature amounts D and E.

Returning to FIG. 1, the restoration processing unit 14 identifies a restoration method corresponding to some or all of the values of the basic feature amount and the auxiliary feature amount monitored by the feature amount monitoring unit 13, and with the identified restoration method, Execute the repair process corresponding to the anomalous object.

Note that the restoration processing unit 14 executes restoration processing for the internal device 6 that generates the target image. Specifically, in the restoration 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.

FIG. 6 is a diagram for explaining setting value change patterns set for each of a plurality of repair conditions. For example, as shown in FIG. 6, a plurality of restoration conditions #1, #2, #3, . . . are set in advance. is associated with a restoration condition, a restoration condition corresponding to the basic feature amount and the auxiliary feature amount is selected, and a predetermined setting value is changed according to a setting value change pattern specified by the restoration condition. At that time, for example, the change range of the setting value is determined according to the values of the basic feature amount and the auxiliary feature amount.

In this embodiment, the restoration processing unit 14 (a) specifies one or more restoration conditions corresponding to some or all of the values of the basic feature amount and the auxiliary feature amount monitored by the feature amount monitoring unit 13. do. If only one repair condition is specified, that repair condition is taken as the repair method. On the other hand, when a plurality of repair conditions are specified, and when the plurality of repair conditions do not include mutually contradictory parts, and when the plurality of repair conditions are all mutually conflicting, the repair processing unit 14 determines the plurality of repair conditions. A repair condition is selected as a repair method based on a predetermined priority from the conditions. In addition, when the plurality of repair conditions include mutually contradictory and non-conflicting portions, the restoration processing unit 14 selects the non-conflicting portions in the plurality of restoration conditions as the restoration method.

Furthermore, (a) after the restoration processing, the restoration processing unit 14 evaluates the restoration processing based on part or all of the values of the basic feature amount and the auxiliary feature amount after the restoration process; Based on the evaluation result of the evaluation, the application of the repair process (that is, the state in which the repair process was performed) is continued.

Specifically, the repair processing unit 14 evaluates each of a plurality of predetermined abnormality types, and (b) when the evaluation results for each of the plurality of abnormality types conflict, based on the order of priority, one of the plurality of failure types is selected, and the repair method is changed according to the selected failure type.

Here, the above-mentioned evaluation is performed based on the evaluation value s obtained from the basic feature amount and the auxiliary feature amount by a predetermined calculation formula, for example. Here, the rating value is specified whether it is constant (no change), increased, or decreased, and based on whether the rating value has changed and the direction of change (increase or decrease), the is determined. For example, if the change in evaluation value (difference between evaluation values before and after correction) is less than a predetermined value, it is determined to be constant (no change), and if the evaluation value increases by more than the predetermined value, it is determined to have increased. If the evaluation value has decreased by a predetermined value or more, it is determined that the evaluation value has decreased. Also, this evaluation value s is derived based on a predetermined function or table from the value of the feature quantity being monitored (basic feature quantity or basic feature quantity and auxiliary feature quantity). For example, the function may be a linear expression, and if the feature quantities being monitored are the basic feature quantities A and B and the auxiliary feature quantities C and D, s=Ws1×A+Ws2×B+Ws3×C+Ws4×D+Ws5(A˜ D is the value of each feature amount, and Ws1 to Ws5 are constants).

In addition, the priority of the plurality of abnormality types is determined by determining whether or not the value of the basic feature value at the boundary of whether or not the monitoring determination condition is satisfied for each of the plurality of abnormality types, and whether the predetermined usage limit determination condition is satisfied. It is set based on the difference from the value of the basic feature amount at the boundary between whether or not, and the smaller the difference, the higher the priority is set. The difference may be derived using the evaluation values described above. That is, in an experiment or the like, the value of the corresponding feature amount at the monitoring judgment boundary and the usage limit judgment boundary is specified, the evaluation values s1 and s2 corresponding to the values are derived, and the difference between the evaluation values is the relevant value. A difference may be used. Therefore, in the monitoring determination area, s1<s<s2.

Furthermore, the priority of the plurality of abnormality types may be set based on the change amount ds of the evaluation value s in the predetermined time T, instead of the difference described above, or in addition to the difference described above. In this case, the larger the amount of change, the higher the priority is set. Further, the predetermined time T in this case is the time from the start of monitoring of the basic feature amount, the evaluation value s is derived from the value of the basic feature amount (not including the auxiliary feature amount), and the change amount ds is the basic It is derived as the difference (s(t)-s0) between the evaluation value s0 at the start of monitoring of the feature amount and the evaluation value s(T) after the predetermined time T has elapsed.

FIG. 7 is a diagram for explaining the operation corresponding to the evaluation value after restoration processing. For example, as shown in FIG. 7, when there is only one abnormality type whose basic feature value is within the monitoring determination area, based on the presence or absence of change in the evaluation value for that abnormality type and the direction of change, The operation after the repair process (continuation of application of repair process, discontinuation of application of repair process, etc.) is determined. For example, as shown in FIG. 7, when the value of the basic feature amount falls within the monitoring determination area for a plurality of abnormality types, the combination of the presence or absence of change in the evaluation value and the direction of change for the plurality of abnormality types , the operation after the repair process is determined.

In addition, when the evaluation value s of a certain abnormality type satisfies a predetermined condition (here, when the evaluation value s is less than a predetermined threshold value), the repair processing unit 14 determines that the abnormality of the abnormality type has been resolved. Then, the monitoring of the auxiliary feature amount corresponding to the abnormality type may be terminated. In this case, the monitoring of the auxiliary feature amount corresponding to the abnormality type that is the auxiliary feature amount of the other abnormality type being monitored is not terminated. In addition, when the repair processing unit 14 determines that the abnormality of the abnormality type has been resolved, the repair processing unit 14 outputs the repair method (repair condition), the value of the feature amount (basic feature amount and auxiliary feature amount) before and after the repair, etc. as improvement information. You may make it

Next, the operation of the image processing apparatus shown in FIG. 1 will be described. 8 and 9 are flowcharts for explaining the operation of the image processing apparatus shown in FIG.

The target image acquisition unit 11 acquires a target image (image data) (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 or not an abnormal object has been detected (step S2).

If no abnormal object is detected, the state is determined to be normal, and repair processing and the like are not performed.

When an abnormal object is detected, the feature amount monitoring unit 13 specifies the value of the basic feature amount of the detected abnormal object (coordinate value in a basic feature amount space composed of a plurality of basic feature amount values) (step S3).

The feature amount monitoring unit 13 determines whether or not there is an abnormality type in which the value of the identified basic feature amount belongs to the usage limit region (step S4). If there is an abnormality type whose value of the specified basic feature value belongs to the usage limit region, the feature monitoring unit 13 determines that the specific part in the image processing apparatus has reached the usage limit such as life or failure, This is displayed, for example, on the display device 4 to inform the user or the service person (step S5). In this case as well, the restoration process, which will be described later, is not executed.

If there is no abnormality type in which the specified basic feature amount value belongs to the usage limit region, the feature amount monitoring unit 13 determines whether the specified basic feature amount value belongs to the monitoring target area based on, for example, the above-described determination formula. It is determined whether or not there is a type (step S6).

If there is no abnormality type whose value of the basic feature amount specified this time belongs to the monitoring target area, the feature amount monitoring unit 13 determines whether or not there is an auxiliary feature amount being monitored (step S7). If there is a feature amount, the monitoring of the auxiliary feature amount ends (step S8). In this case as well, the restoration process, which will be described later, is not executed.

On the other hand, if there is an abnormality type whose value of the basic feature amount identified this time belongs to the monitoring target area, the feature amount monitoring unit 13 identifies one or a plurality of auxiliary feature amount sets for that abnormality type as described above. , one auxiliary feature set is selected from the one or more auxiliary feature sets in accordance with a predetermined priority (step S9). At this time, the monitoring of auxiliary feature quantities other than the selected auxiliary feature quantity set is terminated.

Then, the feature amount monitoring unit 13 determines whether or not the selected auxiliary feature amount set (the auxiliary feature amount belonging to) is already being monitored (step S10). amount) is not being monitored, the monitoring is started (step S11).

The feature amount monitoring unit 13 executes auxiliary feature amount evaluation processing for the auxiliary feature amount being monitored (the auxiliary feature amount belonging to the selected auxiliary feature amount set) (step S12). In the auxiliary feature quantity evaluation process, it is determined whether or not to continue monitoring each auxiliary feature quantity being monitored.

10A and 10B are diagrams for explaining the auxiliary feature amount evaluation processing in FIG. As shown in FIG. 10, in the auxiliary feature quantity evaluation process, one auxiliary feature quantity is selected from auxiliary feature quantities belonging to the selected auxiliary feature quantity set (step S21), and the selected auxiliary feature quantity for the abnormal object is A quantity value is identified (step S22). On the other hand, the predicted value V for the auxiliary feature amount is derived as described above (step S23), and it is determined whether or not the value of the auxiliary feature amount is within the allowable error range (step S24). If the auxiliary feature value is within the allowable error range, the auxiliary feature value is continuously monitored (step S25). If not, the auxiliary feature value is monitored. It ends (step S26). Then, it is determined whether or not there are any unselected auxiliary feature amounts among the auxiliary feature amounts belonging to the selected auxiliary feature amount set (step S27), and the process returns to step S22 until there are no unselected auxiliary feature amounts. , one of the unselected auxiliary features is selected, and similar processing is performed.

Since the value of the auxiliary feature amount for an abnormality type different from the actual abnormality type tends to deviate from the predicted value V over time, such an auxiliary feature amount is excluded from monitoring, and in the restoration process described later. should not be taken into consideration. Therefore, it becomes easier to select an appropriate repair method.

Returning to FIG. 9, after the auxiliary feature amount evaluation process, the feature amount monitoring unit 13 determines whether or not there is an auxiliary feature amount to continue monitoring (step S13). If there is no auxiliary feature amount to continue monitoring, the feature amount monitoring unit 13 determines whether or not there is an unselected auxiliary feature amount set among the identified one or more auxiliary feature amount sets ( Step S14), if there is an unselected auxiliary feature quantity set, select one of the unselected auxiliary feature quantity sets (step S15), and process the selected auxiliary feature quantity set after step S10 in the same way.

On the other hand, if there is no unselected auxiliary feature quantity set, the feature quantity monitoring unit 13 determines that there is an unknown abnormality, and notifies the user or the service person by displaying it on the display device 4, for example (step S16). ). In this case as well, the restoration process, which will be described later, is not executed.

On the other hand, in step S13, if there is an auxiliary feature amount that should be monitored continuously, the restoration processing unit 14 executes restoration method identification processing (step S17). In the restoration method specifying process, a restoration method corresponding to the basic feature amount and the auxiliary feature amount being monitored is specified.

FIG. 11 is a diagram for explaining the repair method specifying process in FIG. As shown in FIG. 11, in the restoration method identification process, first, one or more restoration conditions are selected based on the basic feature amount and the auxiliary feature amount (step S31).

It is determined whether multiple repair conditions have been selected (step S32), and if multiple repair conditions have not been selected (that is, only one repair condition has been selected), the set value of the selected repair condition The change pattern is used as a repair method (step S33).

On the other hand, when a plurality of repair conditions are selected, it is determined whether or not there are conflicting portions in the set value change patterns of the plurality of repair conditions (step S34). When there is no contradicting part in the set value change patterns of the selected multiple repair conditions, the set value change pattern obtained by synthesizing the set value change patterns of the multiple repair conditions is used as the repair method. (step S35). On the other hand, if there are contradictory portions in the selected set value change patterns of the plurality of repair conditions, one of the set value change patterns of the plurality of repair conditions is selected based on a predetermined priority, The selected set value change pattern is used as the repair method (step S36).

Returning to FIG. 9, after the repair method specifying process, the repair processing unit 14 executes the repair process using the specified repair method (step S18). Thereafter, the repair processing unit 14 executes repair evaluation processing (step S19).

12A and 12B are diagrams for explaining the repair evaluation process in FIG. 9. FIG. As shown in FIG. 12, in the repair evaluation process, the target image acquisition unit 11 acquires a new target image (step S41), and the abnormality detection unit 12 detects an abnormal object in the new target image. Then, the values of the basic feature amount and the auxiliary feature amount being monitored are specified for the detected abnormal object (step S42). For each abnormality type, the evaluation value described above is calculated from the values of the basic feature amount and the auxiliary feature amount being monitored (step S43).

Then, it is determined whether or not the calculated evaluation value has increased outside the predetermined range for all of the abnormality types being monitored (step S44), and the evaluation values of all the abnormality types being monitored are out of the predetermined range. If it increases, the restoration is stopped and the set value is returned to the state before restoration (step S45).

On the other hand, if there is an abnormality type in which the calculated evaluation value is out of the predetermined range and has not increased, the calculated evaluation value for some of the abnormality types being monitored is out of the predetermined range. (step S46), and if there is no abnormality type whose evaluation value has increased outside the predetermined range among the abnormality types being monitored, repair is continued (step S47).

On the other hand, if the calculated evaluation value for some of the abnormality types being monitored is out of the predetermined range and increases, the repair method is changed based on the priority (step S48). ), the repair process is executed (step S49), the process returns to step S41, and the repair evaluation process is executed again.

As described above, according to the above embodiment, the abnormality detection unit 12 detects an abnormal object in the target image. The feature quantity monitoring unit 13 (a) monitors at least two basic feature quantity values for the abnormal object, and (b) whether or not the basic feature quantity value satisfies a predetermined monitoring determination condition for a specific abnormality type. (c) If it is determined that the value of the basic feature amount satisfies the monitoring determination condition, the feature amount corresponding to the specific abnormality type is specified as the auxiliary feature amount for the abnormal object, and ( d) Start monitoring the value of the auxiliary feature. The restoration processing unit 14 identifies a restoration method corresponding to some or all of the values of the basic feature amount and the auxiliary feature amount monitored by the feature amount monitoring unit 13, and uses the identified restoration method to handle the abnormal object. Run the repair process.

As a result, the value of the auxiliary feature amount is monitored according to the temporal change in the value of the basic feature amount of the abnormal object, and the restoration process is executed accordingly. Repair is done. As a result, since the defect and its cause are identified early before the service limit is reached, the service limit is less likely to occur and abnormalities are reduced until the service limit is reached.

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 its subject matter and without diminishing its intended advantages. It is therefore intended that such changes and modifications be covered by the claims.

For example, in the above-described embodiment, the restoration processing unit 14 (a) saves in an external device (such as a cloud server) the correspondence relationship between the values of the basic feature amount and the auxiliary feature amount described above and the specified restoration method, (b) The correspondence may be read from the external device, and the restoration method may be determined based on the read correspondence.

INDUSTRIAL APPLICABILITY The present invention is applicable, for example, to detection of abnormality in an image forming apparatus.

12 Abnormality detection unit 13 Feature amount monitoring unit 14 Restoration processing unit

Claims (11)

an anomaly detector that detects an anomalous object in the target image;
(a) monitoring at least two basic feature values for the abnormal object; (b) determining whether the basic feature value satisfies a predetermined monitoring criterion for a specific abnormality type; c) if it is determined that the value of the basic feature quantity satisfies the monitoring determination condition, specifying a feature quantity corresponding to the specific abnormality type as an auxiliary feature quantity for the abnormal object; a feature monitoring unit that starts monitoring the value of
Identifying a restoration method corresponding to part or all of the values of the basic feature amount and the auxiliary feature amount monitored by the feature amount monitoring unit, and performing restoration processing corresponding to the abnormal object using the identified restoration method. a repair processor that executes
An image processing device comprising: 4. The feature amount monitoring unit terminates monitoring of the value of the auxiliary feature amount when the value of the auxiliary feature amount being monitored falls outside an allowable error range from a specific predicted value. 1. The image processing apparatus according to 1. The feature amount monitoring unit (a) identifies a plurality of auxiliary feature amount sets as feature amounts corresponding to the specific abnormality type, and (b) selects one of the plurality of auxiliary feature amount sets. , specifying one or more feature amounts included in the selected auxiliary feature amount set as the auxiliary feature amounts, and (c) monitoring all of the one or more feature amounts included in the selected auxiliary feature amount set When finished, another auxiliary feature quantity set is selected from the plurality of auxiliary feature quantity sets, and one or more feature quantities included in the selected auxiliary feature quantity set are specified as the auxiliary feature quantity. 3. The image processing apparatus according to claim 2, wherein: The restoration processing unit (a) specifies a plurality of restoration conditions corresponding to some or all of the values of the basic feature amount and the auxiliary feature amount monitored by the feature amount monitoring unit; When the plurality of repair conditions do not include mutually conflicting portions and when the plurality of repair conditions are all mutually conflicting, a repair condition is selected as the repair method from the plurality of repair conditions based on a predetermined priority. 2. The image processing apparatus according to claim 1, wherein: 4. The repair processing unit, when the plurality of repair conditions include a mutually conflicting part and a mutually not conflicting part, selects the mutually not conflicting part in the plurality of repair conditions as the repair method. 1. The image processing apparatus according to 1. (a) after the restoration processing, the restoration processing unit evaluates the restoration processing based on part or all of the values of the basic feature amount and the auxiliary feature amount after the restoration process; 2. The image processing apparatus according to claim 1, wherein it is determined whether or not to continue applying the restoration processing based on the evaluation result of the evaluation. (b) when the evaluation results for each of the plurality of abnormality types conflict with each other, a predetermined priority order for the plurality of abnormality types; 7. The image processing apparatus according to claim 6, wherein one of the plurality of abnormality types is selected based on, and the restoration method is changed according to the selected abnormality type. The priority order for the plurality of abnormality types is determined by determining whether the value of the basic feature quantity and the predetermined usage limit judgment condition at the boundary of whether or not the monitoring judgment condition is satisfied for each of the plurality of abnormality types. It is set based on the difference from the value of the basic feature amount at the boundary of whether or not it is established,
The smaller the difference, the higher the priority is set;
8. The image processing apparatus according to claim 7, characterized by: The restoration processing unit (a) stores a correspondence relationship between the values of the basic feature amount and the auxiliary feature amount and the specified restoration method in an external device, and (b) reads the correspondence relationship from the external device. 9. The image processing apparatus according to any one of claims 1 to 8, wherein the restoration method is determined based on the read correspondence relationship. an image processing device according to any one of claims 1 to 9;
an internal device that generates the target image;
the repair processing unit executing the repair processing for the internal device;
An image forming apparatus characterized by: detecting an anomalous object in the target image;
(a) monitoring at least two basic feature values for the abnormal object; (b) determining whether the basic feature value satisfies a predetermined monitoring criterion for a specific abnormality type; c) if it is determined that the value of the basic feature quantity satisfies the monitoring determination condition, specifying a feature quantity corresponding to the specific abnormality type as an auxiliary feature quantity for the abnormal object; starting to monitor the value of
identifying a repair method corresponding to some or all of the values of the monitored basic feature amount and the auxiliary feature amount, and executing a repair process corresponding to the abnormal object using the specified repair method;
An image processing method comprising:

Images