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

Abstract

To obtain an image processing apparatus, an image forming apparatus, and an image processing method that accurately specify the cause of abnormality without extending the time required for detecting an abnormal image.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 any 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 abnormality classification in which the values of the basic feature amounts satisfy the monitoring determination condition as an auxiliary feature amount for the abnormal object, and (d) starts monitoring the value of the auxiliary feature amount. An abnormality classification specification unit 14 specifies an abnormality classification corresponding to the detected abnormal object based on the basic feature amounts and auxiliary feature amount being monitored.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 appear in printed products or scanned images due to specific causes in the image processing device. Abnormal images include, for example, unintended streaks or dots, or unevenness that spreads across the entire printed product or scanned image.

[0003] An image processing device outputs a test pattern of a plurality of toner colors and white, and identifies the cause of an abnormality based on an abnormal object in the shape of a point or a stripe in the test pattern (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2017-223892 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the image processing device described above requires outputting a large number of test patterns, which increases the time required to identify the cause of the abnormality. Also, referring to only test patterns taken at a certain point in time may not accurately identify the cause of the abnormality.

[0006] The present invention has been made in consideration of the above-mentioned problems, and aims to provide an image processing device, an image forming device, and an image processing method that can accurately identify the cause of an abnormality without increasing the time required to detect an abnormal image. [Means for solving the problem]

[0007] The image processing device according to the present invention comprises: A predetermined reference image is printed and scanned. The system includes an anomaly detection unit that detects an abnormal object in a target image, a feature monitoring unit that (a) monitors values ​​of at least two basic feature amounts for the abnormal object, (b) determines whether the value of the basic feature amount satisfies a predetermined monitoring judgment condition for any of a predetermined plurality of abnormality types, (c) when it is determined that the value of the basic feature amount satisfies the monitoring judgment condition, identifies a feature amount corresponding to the abnormality type for which the value of the basic feature amount satisfies the monitoring judgment condition as an auxiliary feature amount for the abnormal object, and (d) starts monitoring the value of the auxiliary feature amount, and an abnormality type identification unit that identifies the abnormality type corresponding to the abnormal object based on the basic feature amount and the auxiliary feature amount monitored by the feature monitoring unit. The basic feature amount and the auxiliary feature amount are selected in advance from a predetermined feature amount group for each abnormality type.

[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 comprises: A predetermined reference image is printed and scanned. The method includes the steps of: detecting an abnormal object in a target image; (a) monitoring values ​​of at least two basic feature quantities for the abnormal object; (b) determining whether the value of the basic feature quantities satisfies a predetermined monitoring judgment condition for any of a predetermined plurality of abnormality types; (c) when it is determined that the value of the basic feature quantities satisfies the monitoring judgment condition, identifying a feature quantity corresponding to the abnormality type for which the value of the basic feature quantity satisfies the monitoring judgment condition as an auxiliary feature quantity for the abnormal object; and (d) starting monitoring the values ​​of the auxiliary feature quantities; and identifying the abnormality type corresponding to the abnormal object based on the monitored basic feature quantities and auxiliary feature quantities. The basic feature amount and the auxiliary feature amount are selected in advance from a predetermined feature amount group for each abnormality type. [Effects of the Invention]

[0010] According to the present invention, an image processing apparatus, an image forming apparatus, and an image processing method can be provided that can accurately identify the cause of an abnormality without increasing the time required to detect an abnormal image.

[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 explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a block diagram showing the configuration of an image processing device according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram illustrating the feature amount of an abnormal object. [Figure 3] FIG. 3 is a diagram illustrating a normality determination region, a monitoring determination region, and a usage limit determination region in the basic feature amount space for each abnormality type. [Figure 4] FIG. 4 is a diagram illustrating selection of an auxiliary feature to be additionally monitored depending on the value of a basic feature. [Figure 5] FIG. 5 is a diagram illustrating the start and end of monitoring of auxiliary features. [Figure 6] FIG. 6 is a flowchart (1 / 2) illustrating the operation of the image processing device shown in FIG. [Figure 7] FIG. 7 is a flowchart (2 / 2) illustrating the operation of the image processing device shown in FIG. [Figure 8] FIG. 8 is a diagram for explaining the lifespan / failure determination process in FIG. [Figure 9] FIG. 9 is a diagram illustrating the auxiliary feature evaluation process in FIG. [Figure 10] FIG. 10 is a diagram illustrating the abnormality classification process in FIG. DETAILED DESCRIPTION OF THE INVENTION

[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 peripheral, 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, which executes an image processing program to function as various processing units. Specifically, the computer includes a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc., and functions as a predetermined processing unit by loading a program stored in the ROM or storage device 2 into the RAM and executing it 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 the image processing program and data required for the processing described below. The image processing program is stored, for example, in a non-transitory computer-readable recording medium, and is installed into the storage device 2 from the recording medium.

[0017] The communication device 3 is a device that performs data communication with external devices, such as a network interface or a peripheral device interface. 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. The input device 5 is a device that detects user operations, such as a keyboard or a touch panel.

[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 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 feature amount monitoring unit 13, and the abnormality type identification unit 14, which are the processing units described above.

[0020] The target image acquisition 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 RAM, etc. The target image is obtained, for example, by scanning a printout obtained by printing a predetermined reference image. The reference image (image data) is stored in the storage device 2 in advance.

[0021] The anomaly detection unit 12 compares the target image with the 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, streak, etc.), such as streak, dot, or unevenness. For example, a second-order differential filter, a Gabor filter, etc., is used for this filter process.

[0023] The feature monitoring unit 13 (a) monitors the values ​​of at least two basic feature values ​​for an abnormal object, (b) determines whether the value of the basic feature value satisfies a predetermined monitoring judgment condition for any of a predetermined plurality of abnormality types, (c) if it determines that the value of the basic feature value satisfies the monitoring judgment condition, identifies the feature value corresponding to the abnormality type for which the value of the basic feature value satisfies the monitoring judgment condition as an auxiliary feature value for the abnormal object, and (d) starts monitoring the value of the identified auxiliary feature value.

[0024] The abnormality type is the type of the cause of the abnormality (such as an abnormal location), etc. The abnormal location is, for example, a replaceable consumable unit.

[0025] To monitor the values ​​of the basic feature quantities (or the basic feature quantities and auxiliary feature quantities), the target image acquisition unit 11 repeatedly acquires the target image at specific time intervals or measurement timings, the abnormality detection unit 12 detects abnormal objects from the target image at each acquisition time point, and the feature quantity monitoring unit 13 identifies the values ​​of the basic feature quantities (or the basic feature quantities and auxiliary feature quantities) of the detected abnormal objects.

[0026] Here, the basic features and auxiliary features are pre-selected from a predetermined group of features for each abnormality type, and the basic features are always monitored, while the auxiliary features are monitored only when the basic features satisfy specific conditions.

[0027] For example, the predetermined set of features includes the area, orientation, growth direction of the abnormal object, density of the abnormal object, edge strength of the abnormal object, color of the abnormal object, period of the abnormal object, number of the abnormal object, etc.

[0028] 2 is a diagram illustrating the feature amounts of an abnormal object. For example, abnormal objects 101, 102, and 103 in Fig. 2 are abnormal objects with an abnormality type of "point," and the abnormal objects 101, 102, and 103 differ from one another in area, density, and edge strength.

[0029] 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 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.

[0030] FIG. 3 is a diagram illustrating a normality determination region, a monitoring determination region, and a usage limit determination region in the basic feature amount space for each abnormality type.

[0031] For example, as shown in FIG. 3, in the basic feature space (here, a planar space formed by basic feature A and basic feature B), there are a normal judgment region, a monitoring judgment region, and a use limit judgment region for each abnormality type. The use limit judgment region is a region where a judgment is made as the end of life or a malfunction. The normal judgment region is a region where a judgment is made as normal, and the monitoring judgment region is a region where a judgment is made as the pre-end of life or a malfunction. In the normal judgment region, the values ​​of the basic feature are monitored (the values ​​of the auxiliary feature are not monitored), and in the monitoring judgment region, the values ​​of the auxiliary feature are monitored along with the values ​​of the basic feature at least until the abnormality type is identified.

[0032] FIG. 4 is a diagram illustrating the selection of auxiliary features to be additionally monitored according to the values ​​of the basic features. When multiple anomaly types to be determined are specified, there are boundaries (monitoring judgment boundaries) between the normal judgment regions and the monitoring judgment regions for the multiple anomaly types. When the values ​​of the basic features cross the monitoring judgment boundaries and enter the monitoring judgment regions, monitoring of the values ​​of the auxiliary features is initiated. For example, as shown in FIG. 4, when the values ​​of the basic features A and B are measurement result #1, the values ​​of the basic features A and B are within the monitoring judgment regions for anomaly type #1 and also within the monitoring judgment regions for anomaly type #2. Therefore, auxiliary features C corresponding to anomaly type #1 and auxiliary features D corresponding to anomaly type #2 are selected as auxiliary features for which monitoring should be initiated. Also, as shown in FIG. 4, when the values ​​of the basic features A and B are measurement result #2, the values ​​of the basic features A and B are within the monitoring judgment region for anomaly type #3. Therefore, auxiliary features E corresponding to anomaly type #3 are selected as auxiliary features for which monitoring should be initiated.

[0033] Monitoring of the auxiliary feature is started and ended according to the values ​​of the basic feature A and B. In this embodiment, the feature monitoring unit 13 derives the value of the abnormality level r from the value of the feature being monitored (e.g., the basic feature A and B), and when the value of the abnormality level r exceeds a predetermined threshold TH1 for a certain abnormality type, it determines that the value of the basic feature has exceeded the monitoring judgment boundary for that abnormality type and entered a monitoring judgment region (i.e., it determines that the monitoring judgment condition is satisfied), and starts monitoring the value of the auxiliary feature corresponding to that abnormality type. Furthermore, when the value of the abnormality level r falls below a predetermined threshold TH2 for that abnormality type, the feature monitoring unit 13 ends monitoring the value of the auxiliary feature corresponding to that abnormality type.

[0034] The abnormality level r is derived using a function or a table, which may be specified in advance by experiment or the like, and may be approximately expressed as a linear expression (r=W1×A+W2×B+W3, where W1, W2, and W3 are constants). Furthermore, the threshold value TH2 may be the same as or different from the threshold value TH1.

[0035] Furthermore, it is determined individually for each auxiliary feature whether to end monitoring. When multiple auxiliary features are being monitored, it is determined individually for each auxiliary feature whether to end monitoring. FIG. 5 is a diagram illustrating the start and end of monitoring of auxiliary features. For example, as shown in FIG. 5, when the value of an auxiliary feature being monitored falls outside the allowable error range σ from a specific predicted value V, the feature monitoring unit 13 ends monitoring the value of the auxiliary feature. This predicted value V is derived from the value of the basic feature at the start of monitoring using a predetermined formula, table, or the like. The predicted value V and the allowable error range σ are set individually for each auxiliary feature.

[0036] Furthermore, the feature monitoring unit 13 (a) identifies multiple auxiliary feature sets as feature values ​​corresponding to a specific anomaly type, (b) selects one of the multiple auxiliary feature sets, and identifies one or more feature values ​​included in the selected auxiliary feature set as auxiliary features, and (c) when monitoring of all of the one or more feature values ​​included in the selected auxiliary feature set has been completed, selects another auxiliary feature set from the multiple auxiliary feature sets, and identifies one or more feature values ​​included in the selected auxiliary feature set as auxiliary features. Note that the multiple auxiliary feature sets are selected in a predetermined order of priority.

[0037] 4, when measurement result #1 is obtained, the above-mentioned auxiliary feature set may be a set of auxiliary features C and D, a set of only auxiliary feature C, a set of only auxiliary feature D, etc. In this case, the set of auxiliary features C, D, E, a set of auxiliary feature E, etc. may also be set as the above-mentioned auxiliary feature set, including an auxiliary feature associated with an anomaly type having an adjacent monitoring determination boundary within a predetermined distance range from the value (coordinates) of the basic feature (here, auxiliary feature E associated with anomaly type #3).

[0038] The feature monitoring unit 13 may (a) select one of the anomaly types other than the auxiliary feature to be monitored based on the distance from the current value of the basic feature to the value of the basic feature that satisfies the monitoring judgment condition of an anomaly type other than the auxiliary feature to be monitored among the above-mentioned predetermined plurality of anomaly types (for example, for measurement result #1 in FIG. 4, the distance from the position of measurement result #1 to the monitoring judgment boundary of anomaly type #3), and (b) include the auxiliary feature corresponding to the selected anomaly type in the auxiliary feature set. That is, an anomaly type whose distance is equal to or less than a predetermined value is selected, and an anomaly type whose distance is not equal to or less than a predetermined value is not selected.

[0039] Furthermore, with regard to the priority of these auxiliary feature sets, the auxiliary feature set that includes both auxiliary feature values ​​C and D of the two anomaly types for which the values ​​of basic feature values ​​A and B fall within the monitoring judgment region has the highest priority, followed by the auxiliary feature set that includes one of these auxiliary feature values ​​C and D, and the auxiliary feature set that includes auxiliary feature value E corresponding to an adjacent monitoring judgment boundary has a lower priority than the set that does not include auxiliary feature value E. For example, for measurement result #1, the priority decreases in the order of the set of auxiliary feature values ​​C and D, the set of auxiliary feature value D only, the set of auxiliary feature value C only, the set of auxiliary feature values ​​C, D, and E, and the set of auxiliary feature value E.

[0040] 4, when measurement result #2 is obtained, a set of only auxiliary feature E and a set of auxiliary feature D and auxiliary feature E corresponding to the adjacent monitoring judgment boundary are set. In this case, for measurement result #2, based on the above-mentioned distance, anomaly type #2 (auxiliary feature D) is selected, but anomaly type #1 (auxiliary feature C) is not selected. For example, for this measurement result #2, the priority order is, in descending order, the set of auxiliary feature E only, followed by the set of auxiliary features D and E.

[0041] In addition, when the values ​​of multiple auxiliary features (e.g., auxiliary features C and D) are being monitored, if some of the multiple auxiliary features fall outside the range corresponding to the values ​​of the basic features but the remaining multiple auxiliary features do not fall outside the range corresponding to the values ​​of the basic features, the feature monitoring unit 13 will stop monitoring the auxiliary features for some of them and continue monitoring the remaining auxiliary features.

[0042] Furthermore, if the degree of abnormality r and the fluctuation range of the value of the auxiliary feature (the above-mentioned allowable error range δ, the same applies below) are less than or equal to a predetermined value during a predetermined period (a period of a predetermined length from the start of monitoring of the auxiliary feature, the same applies below), the feature monitoring unit 13 terminates monitoring of the value of the auxiliary feature.

[0043] 1, the anomaly type identification unit 14 identifies an anomaly type corresponding to an abnormal object based on the basic feature amount (or the basic feature amount and auxiliary feature amount) monitored by the feature amount monitoring unit 13. The identified anomaly type is notified to an administrator or service person, or is used to repair the anomaly.

[0044] Specifically, if the fluctuation range of the anomaly degree r and the auxiliary feature value for a certain anomaly type is equal to or less than a predetermined value during a predetermined period, the anomaly type identification unit 14 determines that the auxiliary feature value has converged and that there is a correlation between the auxiliary feature value and the anomaly degree r, and determines that the anomaly type is the anomaly type that is causing the detected abnormal object.

[0045] Furthermore, when the abnormality degree r for that abnormality type exceeds the judgment threshold δ, the abnormality type identification unit 14 determines that the part corresponding to that abnormality type has reached its usage limit (lifespan or failure state). Also, in this embodiment, when the feature amount monitoring unit 13 monitors the values ​​of auxiliary feature amounts corresponding to each of a predetermined number of abnormality types but is unable to identify the abnormality type corresponding to the abnormal object, the abnormality type identification unit 14 determines that the abnormal object is an abnormal object of an unknown anomaly type. These judgment results are notified to an administrator, service person, etc.

[0046] If the fluctuation range of the anomaly level r and the auxiliary feature value over a predetermined period is equal to or less than a predetermined value, the feature monitoring unit 13 sets a judgment threshold δ. The judgment threshold δ may be a predetermined value, or may be set based on the value of the auxiliary feature. Furthermore, the feature monitoring unit 13 (a) selects a feature correlated with image quality as an image quality monitoring feature when the fluctuation range of the anomaly level and the auxiliary feature value over a predetermined period is equal to or less than a predetermined value, and adds the selected feature as an auxiliary feature. Furthermore, (b) determines that image quality degradation has occurred when the value of the image quality monitoring feature being monitored exceeds a predetermined threshold. The image quality monitoring feature may be specified in advance, or may be selected from the monitored auxiliary features (according to a predetermined index for image quality).

[0047] Next, a description will be given of the operation of the image processing device shown in Fig. 1. Figs. 6 and 7 are flowcharts illustrating the operation of the image processing device shown in Fig. 1.

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

[0049] If no abnormal object is detected, the system is determined to be in a normal state and no repair process is performed.

[0050] If an abnormal object is detected, the feature amount monitoring unit 13 identifies the value of the basic feature amount of the detected abnormal object (coordinate value in a basic feature amount space consisting of values ​​of a plurality of basic feature amounts) (step S3).

[0051] The feature amount monitoring unit 13 determines whether the abnormal object has already been classified into an abnormality type (step S4). If the abnormal object has already been classified into an abnormality type, the feature amount monitoring unit 13 executes a lifespan / failure determination process (step S5).

[0052] FIG. 8 is a diagram illustrating the lifespan / failure determination process in FIG. 6. In the lifespan / failure determination process, for the identified anomaly type, it is determined whether the value of the abnormality level r based on the basic feature (excluding auxiliary feature) exceeds the determination threshold δ (step S21). If the value of the abnormality level r exceeds the determination threshold δ, a warning about lifespan / failure is output (step S22). It is also determined whether the value of the auxiliary feature for monitoring image quality currently being monitored exists (step S23). If the value of the auxiliary feature for monitoring image quality currently being monitored exists, the value is identified (step S24), and it is determined whether the value exceeds the image quality threshold ε (step S25). If the value exceeds the image quality threshold ε, a warning about degradation in image quality is output (step S26).

[0053] In this way, depending on the situation, the fact that a specific part in the image processing device has reached its usage limit due to its lifespan or malfunction, or that image quality has deteriorated, is displayed on the display device 4, for example, to notify the user or service personnel.

[0054] Returning to FIG. 6, if the abnormality type for this abnormal object has not been classified, the feature monitoring unit 13 determines, for example, based on the above-mentioned abnormal value r, whether there is an abnormality type for which the value of the basic feature identified this time belongs to the monitoring target area (step S6).

[0055] If there is no abnormality type for which the value of the currently identified basic feature belongs to the monitoring target area, the feature monitoring unit 13 determines whether or not there is an auxiliary feature being monitored (step S7), and if there is an auxiliary feature being monitored, ends monitoring of that auxiliary feature (step S8).

[0056] On the other hand, if there is an abnormality type for which the value of the currently identified basic feature belongs to the monitoring target area, the feature monitoring unit 13 identifies one or more auxiliary feature sets for that abnormality type as described above, and selects one auxiliary feature set from the one or more auxiliary feature sets in accordance with a predetermined priority order (step S9). At this time, monitoring of auxiliary features other than the selected auxiliary feature set is terminated.

[0057] Then, the feature monitoring unit 13 determines whether the selected auxiliary feature set (the auxiliary features belonging to it) is already being monitored (step S10), and if the selected auxiliary feature set (the auxiliary features belonging to it) is not being monitored, starts monitoring it (step S11).

[0058] The feature monitoring unit 13 executes an auxiliary feature evaluation process for the auxiliary features being monitored (auxiliary features belonging to the selected auxiliary feature set) (step S12). In the auxiliary feature evaluation process, it is determined whether or not to continue monitoring each auxiliary feature being monitored.

[0059] FIG. 9 is a diagram illustrating the auxiliary feature evaluation process in FIG. 7. As shown in FIG. 9, in the auxiliary feature evaluation process, one auxiliary feature is selected from the auxiliary features belonging to the selected auxiliary feature set (step S31), and the value of the selected auxiliary feature for the abnormal object is identified (step S32). A predicted value V for the auxiliary feature is derived as described above (step S33), and it is determined whether the value of the auxiliary feature is within the allowable error range (step S34). If the value of the auxiliary feature is within the allowable error range, monitoring of the value of the auxiliary feature continues (step S35). If not, monitoring of the value of the auxiliary feature is terminated (step S36). It is then determined whether there are any unselected auxiliary features among the auxiliary features belonging to the selected auxiliary feature set (step S37). The process returns to step S32, where one of the unselected auxiliary features is selected, and the same process is performed until there are no unselected auxiliary features.

[0060] The value of the auxiliary feature for an anomaly type different from the actual anomaly type is likely to deviate from the predicted value V over time, and therefore such an auxiliary feature is excluded from monitoring.

[0061] 7, after the auxiliary feature evaluation process, the feature monitoring unit 13 determines whether there are any auxiliary features for which monitoring should continue (step S13). If there are no auxiliary features for which monitoring should continue, the feature monitoring unit 13 determines whether there are any unselected auxiliary feature sets among the one or more identified auxiliary feature sets (step S14), and if there are any unselected auxiliary feature sets, selects one of the unselected auxiliary feature sets (step S15), and similarly performs the processes from step S10 onwards for the selected auxiliary feature set.

[0062] On the other hand, if there is no unselected auxiliary feature set, the feature monitoring unit 13 determines that the abnormality is unknown, and notifies the user or service person by displaying a message to that effect on the display device 4, for example (step S16).

[0063] On the other hand, if there is an auxiliary feature for which monitoring should be continued in step S13, the abnormality type identifying unit 14 executes an abnormality classification process (step S17).

[0064] Fig. 10 is a diagram illustrating the anomaly classification process in Fig. 7. As shown in Fig. 10, in the anomaly classification process, the elapsed time t from the start of monitoring is identified for the auxiliary feature being monitored (step S41). The elapsed time t is measured by a timer (not shown) or the like.

[0065] Then, it is determined whether the elapsed time t exceeds a predetermined time threshold THt (step S42), and if the elapsed time t exceeds the predetermined time threshold THt, monitoring has continued for the time THt, and the abnormality type is classified based on the value of the auxiliary feature (step S43).

[0066] For example, if there is one auxiliary feature being monitored, the abnormal object is classified into the abnormality type corresponding to that auxiliary feature, and if there are multiple auxiliary features being monitored, the abnormal object is classified into the abnormality type corresponding to those auxiliary features that satisfies a predetermined condition (for example, the abnormality type corresponding to the auxiliary feature with the largest value).

[0067] Then, a determination threshold δ corresponding to the classified (identified) anomaly type is set (step S44), and the monitoring of all auxiliary features is terminated (step S45). At this time, the monitoring of the basic features continues. By terminating the monitoring of the auxiliary features, the computation load on the processor 1 is reduced.

[0068] Here, it is determined whether there are auxiliary features correlated with image quality (step S46), and if there are auxiliary features correlated with image quality, one of the auxiliary features correlated with image quality is set as the auxiliary feature for image quality monitoring described above (step S47), the image quality threshold ε described above is set, and monitoring of the auxiliary feature for image quality monitoring begins (step S48).

[0069] Note that this abnormality classification process is executed when the abnormality level r is low, and then the abnormality level r increases and the above-mentioned lifespan / failure judgment process is executed. Therefore, the above-mentioned lifespan / failure judgment process is executed based on the thresholds δ and ε set here.

[0070] Here, a specific example will be described.

[0071] The above-mentioned multiple predetermined abnormality types were set as exposure lines, electrostatic lines, and restriction lines, and target images were acquired once a day over a 15-day period. When the abnormality types of the line-shaped abnormal objects were classified, the classification results were more accurate than those obtained using the above-mentioned technology based on test patterns of multiple toner colors and white.

[0072] As described above, according to the above embodiment, the anomaly detection unit 12 detects an abnormal object in a target image. The feature amount monitoring unit 13 (a) monitors the values ​​of at least two basic feature amounts for an abnormal object, (b) determines whether the value of the basic feature amount satisfies a predetermined monitoring judgment condition for one of a predetermined plurality of anomaly types, (c) if it determines that the value of the basic feature amount satisfies the monitoring judgment condition, identifies the feature amount corresponding to the anomaly type whose value of the basic feature amount satisfies the monitoring judgment condition as an auxiliary feature amount for the abnormal object, and (d) starts monitoring the value of the auxiliary feature amount. The anomaly type identification unit 14 identifies the anomaly type corresponding to the detected abnormal object based on the basic feature amount and auxiliary feature amount monitored by the feature amount monitoring unit 13.

[0073] This allows the cause of the abnormality to be identified accurately without increasing the time required to detect the abnormal image. Also, since the defect and its cause can be identified early before the service limit is reached, the service limit is less likely to occur and the abnormality is reduced until the service limit is reached.

[0074] 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, it is intended that such changes and modifications be included within the scope of the claims. [Industrial Applicability]

[0075] The present invention is applicable to, for example, detecting abnormalities in an image forming apparatus or the like. [Explanation of symbols]

[0076] 12 Abnormality detection unit 13 Feature monitoring unit 14. Abnormality type identification unit

Claims

1. An anomaly detection unit that detects an abnormal object in a target image obtained by scanning a printout obtained by printing a predetermined reference image; (a) monitoring values ​​of at least two basic feature amounts for the abnormal object; (b) determining whether the value of the basic feature amount satisfies a predetermined monitoring judgment condition for any of a predetermined plurality of abnormality types; (c) when it is determined that the value of the basic feature amount satisfies the monitoring judgment condition, identifying a feature amount corresponding to the abnormality type for which the value of the basic feature amount satisfies the monitoring judgment condition as an auxiliary feature amount for the abnormal object; and (d) starting monitoring the value of the auxiliary feature amount. an abnormality type identification unit that identifies the abnormality type corresponding to the abnormal object based on the basic feature amount and the auxiliary feature amount monitored by the feature amount monitoring unit; Equipped with the basic feature amount and the auxiliary feature amount are selected in advance from a predetermined feature amount group for each of the abnormality types; An image processing device comprising:

2. The image processing device according to claim 1, characterized in that the feature monitoring unit (a) derives an abnormality level from the value of the basic feature, and (b) when the value of the abnormality level exceeds a predetermined first threshold, determines that the monitoring judgment condition is satisfied and starts monitoring the value of the auxiliary feature corresponding to the abnormality type of the monitoring judgment condition.

3. 3. The image processing device according to claim 2, wherein the feature monitoring unit terminates monitoring the value of the auxiliary feature corresponding to the abnormality type of the monitoring judgment condition when the value of the abnormality degree becomes less than a predetermined second threshold value.

4. 4. The image processing device according to claim 3, wherein the feature monitoring unit (a) identifies a plurality of auxiliary feature sets as features corresponding to a specific anomaly type, (b) selects one of the plurality of auxiliary feature sets, and identifies one or more feature sets included in the selected auxiliary feature set as the auxiliary feature, and (c) when monitoring of all of the one or more feature sets included in the selected auxiliary feature set has been completed, selects another auxiliary feature set from the plurality of auxiliary feature sets, and identifies one or more feature sets included in the selected auxiliary feature set as the auxiliary feature.

5. 5. The image processing device according to claim 4, wherein the feature monitoring unit (a) selects one of the anomaly types other than the anomaly type of the auxiliary feature to be monitored based on a distance from the value of the basic feature to the value of the basic feature that satisfies a monitoring determination condition for the anomaly type other than the auxiliary feature to be monitored, and (b) includes an auxiliary feature corresponding to the selected anomaly type in the auxiliary feature set.

6. 2. The image processing apparatus according to claim 1, wherein, when the values ​​of a plurality of auxiliary features are being monitored, if some of the plurality of auxiliary features fall outside a range corresponding to the values ​​of the basic feature features but the remaining of the plurality of auxiliary features do not fall outside a range corresponding to the values ​​of the basic feature features, the feature monitoring unit ends monitoring of the some of the auxiliary features and continues monitoring of the remaining auxiliary features.

7. 3. The image processing apparatus according to claim 2, wherein the feature amount monitoring unit terminates monitoring of the value of the auxiliary feature amount when the degree of abnormality and the fluctuation range of the value of the auxiliary feature amount are equal to or less than a predetermined value for a predetermined period of time.

8. the abnormality type identification unit (a) derives an abnormality degree from the value of the basic feature amount; and (b) when the abnormality degree for the abnormality type exceeds a specific determination threshold, determines that the part corresponding to the abnormality type has reached its usage limit; when a fluctuation range of the degree of abnormality and the value of the auxiliary feature is equal to or less than a predetermined value during a predetermined period, the feature monitoring unit sets the determination threshold based on the value of the auxiliary feature; 2. The image processing device according to claim 1, wherein:

9. The anomaly type identification unit derives an anomaly degree from the value of the basic feature amount, 2. The image processing device according to claim 1, wherein the feature monitoring unit (a) selects a feature for image quality monitoring when a fluctuation range of the value of the abnormality degree and the value of the auxiliary feature is equal to or less than a predetermined value over a predetermined period of time, and adds the selected feature as the auxiliary feature, and (b) determines that a deterioration in image quality has occurred when a value of the feature for image quality monitoring being monitored exceeds a predetermined threshold.

10. 2. The image processing device according to claim 1, wherein the anomaly type identification unit determines that the abnormal object is an abnormal object of an unknown anomaly type when the anomaly type corresponding to the abnormal object cannot be identified even when the feature monitoring unit monitors the values ​​of the auxiliary features corresponding to each of a predetermined number of anomaly types.

11. an image processing device according to any one of claims 1 to 10; an internal device for generating the target image; An image forming apparatus comprising:

12. A step of detecting an abnormal object in a target image obtained by scanning a printout obtained by printing a predetermined reference image; (a) monitoring values ​​of at least two basic feature quantities for the abnormal object; (b) determining whether the value of the basic feature quantities satisfies a predetermined monitoring judgment condition for any one of a predetermined plurality of abnormality types; (c) when it is determined that the value of the basic feature quantities satisfies the monitoring judgment condition, identifying a feature quantity corresponding to the abnormality type for which the value of the basic feature quantity satisfies the monitoring judgment condition as an auxiliary feature quantity for the abnormal object; and (d) starting monitoring of the value of the auxiliary feature quantities. identifying the anomaly type corresponding to the abnormal object based on the monitored basic feature amount and the monitored auxiliary feature amount; Equipped with the basic feature amount and the auxiliary feature amount are selected in advance from a predetermined feature amount group for each of the abnormality types; An image processing method comprising:

Images