Image Processing Device

Abstract

To suppress computation cost and processing time when one original anomaly is detected as plural anomalies.SOLUTION: An anomaly detection unit 12 detects anomalies included in a target image. An anomaly unification processing unit 13 unifies specific anomalies among the detected anomalies. Further, if a type of an anomaly among the detected anomalies is the same as a type of another anomaly among the detected anomalies, the anomaly unification processing unit 13 (a) determines whether the anomaly and the other anomaly should be unified or not on the basis of a relationship between a position of the anomaly and a position of the other anomaly, and (b) unifies the anomaly and the other anomaly if it is determined that the anomaly and the other anomaly should be unified.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] One image processing device detects abnormalities such as unintended streaks, dots, and unevenness that appear on print products output by image forming devices such as multifunction devices and printers based on images obtained by scanning the print products, and estimates the cause of each abnormality (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-223892 A Summary of the Invention [Problem to be solved by the invention]

[0004] When detecting the above-mentioned abnormalities, if the image of the abnormality that appears in the target image has discontinuous parts, it may be detected as multiple abnormalities, even though it is actually one abnormality. For example, in the case of an intermittent muscle abnormality, it may be detected as multiple muscle abnormalities, even though it is actually one abnormality.

[0005] In this way, when a single anomaly is detected as multiple anomalies, subsequent processing such as estimating the cause of each detected anomaly is performed, resulting in extra calculation costs and longer processing time.In addition, although it is possible to manually discover and integrate such anomalies that are actually a single anomaly but are detected as multiple anomalies, this is not realistic as it takes time and effort.

[0006] The present invention has been made in consideration of the above problems, and provides an image processing device that reduces the calculation cost and processing time when one abnormality is detected as multiple abnormalities. Place The purpose is to obtain. [Means for solving the problem]

[0007] The image processing device according to the present invention includes an anomaly detection unit that detects anomalies included in a target image, and an anomaly integration processing unit that integrates a specific anomaly from among the detected anomalies. The anomaly integration processing unit (a) determines whether or not to integrate the one anomaly and the other anomaly based on a correspondence relationship between the position of the one anomaly and the position of the other anomaly when a type of the one anomaly and a type of the other anomaly are the same among the detected anomalies, and (b) integrates the one anomaly and the other anomaly when it is determined to integrate the one anomaly and the other anomaly. The anomaly integration processing unit further includes either of the following configurations (A) and (B): (A) when the certain anomaly and the other anomaly are integrated, the anomaly integration processing unit sets color information of the anomaly obtained by integrating the certain anomaly and the other anomaly based on the color information of the certain anomaly and the color information of the other anomaly; (B) when the anomaly detection unit detects the anomaly with a filter and generates characteristic information of the anomaly, the characteristic information including a type of the anomaly and an anomaly degree corresponding to an output value of the filter at the time of detection of the anomaly, and when the certain anomaly and the other anomaly are integrated, the anomaly integration processing unit sets an anomaly degree of the anomaly obtained by integrating the certain anomaly and the other anomaly based on the anomaly degree of the certain anomaly and the anomaly degree of the other anomaly. Effect of the Invention

[0010] According to the present invention, an image processing device that reduces the calculation cost and processing time when a single abnormality is detected as multiple abnormalities is provided. Place Obtained.

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

[0012] [Figure 1] FIG. 1 is a block diagram showing a configuration of an image processing device according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a flowchart illustrating the operation of the image processing device shown in FIG. [Diagram 3] FIG. 3 is a flowchart illustrating the anomaly integration process (step S3) in FIG. [Figure 4] FIG. 4 is a diagram illustrating an example of the anomaly integration process (step S3) in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

[0019] Here, the arithmetic processing device 1 operates as the target image acquisition unit 11, the anomaly detection unit 12, the anomaly integration processing unit 13, and the anomaly response processing 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 a RAM or the like.

[0021] The anomaly detection unit 12 detects anomalies contained in the acquired target image by using an existing method. In this embodiment, the anomaly detection unit 12 detects anomalies using, for example, a filter (second-order differential filter, Gabor filter, etc.) and generates feature information of the anomaly. In other words, anomalies are detected based on the feature amount (filter output) obtained by applying the filter to the input image.

[0022] The feature information includes the position and size of the abnormality (position and size of the detection area described below), the type of abnormality (streaks, bands, dots, etc.), the degree of abnormality corresponding to the output value of the filter when the abnormality is detected, and color information. For example, when there is a large difference in density between the surroundings of the abnormality and the abnormality, the degree of abnormality becomes large. Note that types of abnormalities include streaks (vertical and horizontal streaks), bands (vertical and horizontal bands), dots, patterns, etc.

[0023] The anomaly integration processing unit 13 integrates and replaces a plurality of specific anomalies, among the detected anomalies, that satisfy a predetermined integration condition described below, into one anomaly.

[0024] Specifically, the anomaly integration processing unit 13 (a) determines whether or not to integrate one anomaly and another anomaly among the detected anomalies based on the correspondence between the position of the one anomaly and the position of the other anomaly, when the type of the one anomaly is the same as the type of another anomaly, and (b) integrates the one anomaly and the other anomaly into one anomaly when it determines to integrate the one anomaly and the other anomaly. Note that the type of the anomaly obtained by integration is set to be the same as the types of the one anomaly and the other anomaly.

[0025] In this embodiment, the anomaly integration processing unit 13 determines whether or not to integrate the one anomaly and the other anomaly based on the distance between the detection area of ​​the one anomaly and the detection area of ​​the other anomaly. Specifically, if the distance is equal to or less than a predetermined threshold, the two anomalies are integrated, but if not, the two anomalies are not integrated.

[0026] The detection area is a rectangular area that includes an abnormality, and is specified by the abnormality detection unit 12.

[0027] Furthermore, in this embodiment, when the types of the certain anomaly and the other anomaly are a predetermined type (a type of anomaly whose shape changes depending on the orientation, such as a streak), the anomaly integration processing unit 13 determines whether or not to integrate the certain anomaly and the other anomaly based on (a) the distance between the detection area of ​​the certain anomaly and the detection area of ​​the other anomaly, and (b) the orientation of the certain anomaly and the orientation of the other anomaly. Specifically, when the distance is equal to or less than a predetermined threshold and the difference in orientation between the two (angular difference) is equal to or less than a predetermined threshold, the two are integrated, but otherwise, the two are not integrated. Furthermore, anomalies of different types are not integrated even if the distance between the two and the orientations of the two satisfy the above-mentioned conditions.

[0028] Furthermore, in this embodiment, when the anomaly integration processing unit 13 integrates the certain anomaly and the other anomaly, it sets the color information of the anomaly (color value of the anomaly location) obtained by integrating the certain anomaly and the other anomaly based on the color information of the certain anomaly and the color information of the other anomaly.

[0029] For example, the color information (color value) of the anomaly obtained by integration is a weighted average value based on weighting coefficients corresponding to the detection area of ​​the certain anomaly and the detection area of ​​the other anomaly.

[0030] Furthermore, in this embodiment, when the anomaly integration processing unit 13 integrates the certain anomaly and the other anomaly, it sets the anomaly degree of the anomaly obtained by integrating the certain anomaly and the other anomaly based on the anomaly degree of the certain anomaly and the anomaly degree of the other anomaly.

[0031] For example, the anomaly degree of the anomaly obtained by integration is set to the maximum value of the anomaly degree of the one anomaly and the anomaly degree of the other anomaly.

[0032] In addition, if there are other anomalies that satisfy the integration conditions for the anomalies obtained after integration, the two are further integrated. Therefore, if there are three or more anomalies that each satisfy the integration conditions, the three or more anomalies are integrated into one anomaly.

[0033] The anomaly response processing unit 14 executes a predetermined anomaly response process for the detected anomaly. In other words, the anomaly response process is not executed for the original multiple anomalies that were integrated into one anomaly among the detected anomalies, but is executed for the one anomaly obtained by integration. The anomaly response process includes reporting each detected anomaly (reporting by sending a message via the communication device or displaying a message on the display device 4 to an operator who identifies the defective part corresponding to the anomaly or performs maintenance, etc.), identifying the defective part corresponding to each detected anomaly, performing maintenance operations, etc.

[0034] Next, a description will be given of the operation of the image processing device shown in Fig. 1. Fig. 2 is a flow chart illustrating the operation of the image processing device shown in Fig. 1.

[0035] First, the target image acquisition unit 11 acquires a target image (image data) (step S1). Next, the abnormality detection unit 12 detects an abnormality contained in the acquired target image, generates characteristic information of the detected abnormality (position and size information, type, abnormality level, color information, etc.), and stores it in a RAM or the like (step S2).

[0036] Next, the anomaly integration processing unit 13 executes an anomaly integration process for integrating specific anomalies among the detected anomalies (step S3).

[0037] The anomaly handling processor 14 executes a predetermined anomaly handling process for the detected anomaly (including the anomaly after the anomaly integration process) (step S4).

[0038] Here, the anomaly integration process in step S3 will be described. Fig. 3 is a flowchart illustrating the anomaly integration process (step S3) in Fig. 2. Fig. 4 is a diagram illustrating an example of the anomaly integration process (step S3) in Fig. 2.

[0039] The anomaly integration processing unit 13 first identifies two anomalies of the same type among the detected anomalies as one pair (step S11).

[0040] Here, the anomaly integration processing unit 13 determines whether or not at least one pair has been identified (step S12), and if at least one pair has been identified, selects one pair from the pairs of identified anomalies (step S13), and determines whether or not the two anomalies in the selected pair satisfy the above-mentioned integration condition (step S14).

[0041] If the two anomalies in the selected set satisfy the above-mentioned integration condition, the anomaly integration processing unit 13 integrates the two anomalies in the selected set into one anomaly (step S15). Note that if the two anomalies in the selected set do not satisfy the above-mentioned integration condition, the anomaly integration processing unit 13 does not integrate the two anomalies in the selected set into one anomaly.

[0042] At this time, the anomaly integration processing unit 13 sets the circumscribing rectangle of the detection areas of the two anomalies in the selected set as the detection area of ​​the anomaly obtained by integration, sets the anomaly degree of the anomaly obtained by integration as described above based on the anomaly degrees of the two anomalies in the selected set, and sets color information of the anomaly obtained by integration as described above based on color information of the two anomalies in the selected set. The anomaly integration processing unit 13 also additionally identifies a pair of the anomaly obtained by integration and another anomaly of the same type among the detected anomalies.

[0043] Then, the anomaly integration processing unit 13 determines whether or not there is an unselected pair (step S16), and if there is an unselected pair, the process returns to step S13, selects the next pair, and similarly executes the processes from step S14 onward. If there is no unselected pair, the anomaly integration processing unit 13 ends the anomaly integration process.

[0044] In this manner, among the detected anomalies, specific anomalies that satisfy the integration condition are integrated. If none of the above-mentioned pairs are identified in step S12, the anomaly integration processing unit 13 immediately ends the anomaly integration process.

[0045] For example, as shown in FIG. 4, even if a single intermittent muscle abnormality is actually detected as multiple muscle abnormalities, the multiple muscle abnormalities are integrated into a single muscle abnormality by the abnormality integration process.

[0046] As described above, according to the above embodiment, anomaly detection unit 12 detects anomalies contained in a target image, and anomaly integration processing unit 13 integrates a specific anomaly from among the detected anomalies. Then, (a) when a type of one anomaly and a type of another anomaly are the same among the detected anomalies, anomaly integration processing unit 13 determines whether or not to integrate the one anomaly and the other anomaly based on a correspondence relationship between the position of the one anomaly and the position of the other anomaly, and (b) when it is determined that the one anomaly and the other anomaly should be integrated, integrates the one anomaly and the other anomaly.

[0047] As a result, even if a single anomaly is detected as multiple anomalies, the multiple anomalies are consolidated into a single anomaly, reducing the amount of anomaly response processing performed for each anomaly, thereby reducing computational costs and processing time.

[0048] It should be noted that various changes and modifications to the above-described embodiments will be apparent to those skilled in the art. Such changes and modifications may be made without departing from the spirit and scope of the subject matter and without diminishing its intended advantages. In other words, such changes and modifications are intended to be included within the scope of the claims.

[0049] For example, in the above embodiment, the above-mentioned distance thresholds may be set separately depending on the type of abnormality. [Industrial Applicability]

[0050] The present invention is applicable, for example, to anomaly detection. [Explanation of symbols]

[0051] 1. Processing unit (an example of a computer) 12 Anomaly detection section 13. Anomaly integration processing unit

Claims

1. an anomaly detection unit that detects anomalies contained in a target image; an anomaly integration processing unit that integrates specific anomalies among the detected anomalies, the anomaly integration processing unit (a) determines whether or not to integrate the one anomaly and the other anomaly based on a correspondence relationship between a position of the one anomaly and a position of the other anomaly when a type of the one anomaly and a type of the other anomaly are the same among the detected anomalies, and (b) integrates the one anomaly and the other anomaly when it is determined that the one anomaly and the other anomaly are to be integrated; the anomaly integration processing unit, when integrating the one anomaly and the other anomaly, sets color information of the anomaly obtained by integrating the one anomaly and the other anomaly based on the color information of the one anomaly and the color information of the other anomaly; An image processing device comprising:

2. 2. The image processing device according to claim 1, wherein the anomaly integration processing unit determines whether or not to integrate the certain anomaly and the other anomaly based on a distance between a detection area of ​​the certain anomaly and a detection area of ​​the other anomaly.

3. The image processing device according to claim 1, characterized in that, when the types of the certain anomaly and the other anomaly are predetermined types, the anomaly integration processing unit determines whether to integrate the certain anomaly and the other anomaly based on (a) the distance between the detection area of ​​the certain anomaly and the detection area of ​​the other anomaly, and (b) the orientation of the certain anomaly and the orientation of the other anomaly.

4. An anomaly detection unit that detects anomalies contained in a target image; an anomaly integration processing unit that integrates specific anomalies among the detected anomalies, the anomaly integration processing unit (a) determines whether or not to integrate the one anomaly and the other anomaly based on a correspondence relationship between a position of the one anomaly and a position of the other anomaly when a type of the one anomaly and a type of the other anomaly are the same among the detected anomalies, and (b) integrates the one anomaly and the other anomaly when it is determined that the one anomaly and the other anomaly are to be integrated; the anomaly detection unit detects the anomaly using a filter and generates characteristic information of the anomaly; the characteristic information includes a type of the abnormality and an abnormality degree corresponding to an output value of the filter at the time when the abnormality is detected; when the anomaly integration processing unit integrates the one anomaly and the other anomaly, it sets an anomaly degree of the anomaly obtained by integrating the one anomaly and the other anomaly based on the anomaly degree of the one anomaly and the anomaly degree of the other anomaly; An image processing device comprising:

Images