Information processor, control method of information processor, and program

Abstract

To reduce burden on a user related to confirmation of a detection result of deformation from an image in a more suitable mode.SOLUTION: An input section 201 receives a detection request related to detection of deformation in an image from a user and designation of the image to be the detection object. A display section 206 displays a representative result selected from detection results of deformation on the basis of each of a plurality of parameters in which set values in at least a part of prescribed plurality of kinds of detection conditions having the designated image as an object are different from each other in a prescribed display region. The representative result is selected on the basis of the feature of deformation included in a noticed region set in the image on the basis of importance of deformation detected from the designated image.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, a control method for an information processing device, and a program. [Background technology]

[0002] In recent years, a technology for detecting anomalies from an image using a trained model constructed based on machine learning (for example, a technology also called image recognition) is used in various situations. In order to obtain a desired detection result using such image recognition, it is desirable to apply parameters (for example, detection conditions and set values) in a more suitable manner for the image recognition. For example, when detecting anomalies such as cracks in an infrastructure structure from an image, a situation may be assumed in which parameters related to detection conditions are set for the detection amount, noise removal rate, etc. Conventionally, a method has been applied in which the desired detection result is obtained by repeatedly changing such parameters and confirming the detection result of the anomaly from the image based on the parameters. Patent Document 1 discloses a method for obtaining a desired detection result by applying and tuning parameters multiple times when detecting cracks in an image. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-51597 Summary of the Invention [Problem to be solved by the invention]

[0004] On the other hand, in a situation where anomalies manifested in infrastructure structures are detected, the size of the target images tends to be huge and the number of images tends to be huge, so that it may be practically difficult for the user to distinguish the area in the image to be confirmed. In addition, in such a situation, when parameters related to the detection of anomalies are also taken into consideration, the number of combinations of parameters to be confirmed becomes huge, so that it may be practically difficult for the user to identify the combination for confirming the target anomaly.

[0005] In view of the above problems, the present invention aims to reduce the burden on a user involved in checking the detection results of abnormalities in an image in a more suitable manner. [Means for solving the problem]

[0006] The information processing device of the present invention has a receiving means for receiving a detection request from a user for detecting an abnormality in an image and a specification of the image to be detected, and a display control means for displaying in a specified display area a representative result selected from the abnormality detection results based on a plurality of parameters having different setting values ​​for at least some of a predetermined number of types of detection conditions for the specified image, and the representative result is selected based on the characteristics of the abnormality contained in a region of interest set in the specified image based on the importance of the abnormality detected in the image. Effect of the Invention

[0007] According to the present invention, it is possible to reduce the burden on a user in checking the detection results of an abnormality from an image in a more preferable manner. [Brief description of the drawings]

[0008] [Figure 1] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device. [Diagram 2] FIG. 2 is a diagram illustrating an example of a functional configuration of an information processing device. [Diagram 3] 11 is a flowchart showing an example of processing by an information processing device. [Figure 4] FIG. 13 is a diagram showing an example of a detection execution screen. [Diagram 5] 11 is a diagram showing an example of information managed based on a result of detection of a deformation. FIG. [Figure 6] 11 is a diagram showing an example of a relationship between a result of abnormality detection and a region of interest. FIG. [Figure 7] 11 is a flowchart showing an example of processing by an information processing device. [Figure 8] FIG. 13 is a diagram showing an example of a detection result display screen. [Figure 9] FIG. 13 is a diagram showing an example of a detection result display screen. [Figure 10] FIG. 2 is a diagram illustrating an example of a functional configuration of an information processing device. [Figure 11] FIG. 11 is a diagram showing an example of information managed as a defect detection history. [Figure 12] 11 is a flowchart showing an example of processing by an information processing device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are denoted by the same reference numerals, and redundant description will be omitted.

[0010] <First embodiment> An example of a hardware configuration of an information processing device according to a first embodiment of the present disclosure will be described with reference to FIG. The information processing device 100 includes a central processing unit (CPU) 101, a random access memory (RAM) 102, a read only memory (ROM) 103, and an external storage device 105. The information processing device 100 also includes a network interface 104, a display device 106, and an input device 107.

[0011] The CPU 101 controls the operation of each unit constituting the information processing device 100, and is the main body that executes various processes performed by the information processing device 100, which will be described later. The RAM 102 is a memory that temporarily stores data and control information, and is used as a work area when the CPU 101 executes various processes. The ROM 103 stores fixed operating parameters, operating programs, and the like of the information processing device 100.

[0012] The network interface 104 provides a function for connecting to a network and communicating. The information processing device 100 can transmit and receive data to and from an external device by connecting to a predetermined network such as the Internet via the network interface 104.

[0013] The external storage device 105 is a device that stores data, and has an interface that accepts I / O commands for reading and writing data. The external storage device 105 can be realized by, for example, a hard disk drive (HDD), a solid state drive (SSD), an optical disk drive, a semiconductor storage device, or the like. Of course, these are merely examples, and the external storage device 105 may be realized by other storage devices. The external storage device 105 stores computer programs and data for causing the CPU 101 to execute each process, which will be described later as being performed by the information processing device 100.

[0014] The display device 106 is a device that plays the role of an output interface that displays target information as an image to present it to the user, and can be realized by, for example, an LCD (Liquid Crystal Display) or the like. The input device 107 is a device that serves as an input interface for accepting input from a user, and can be realized by various input devices such as a keyboard, a mouse, and a touch panel.

[0015] Next, an example of the functional configuration of the information processing device according to this embodiment will be described with reference to Fig. 2. The information processing device 100 has an input unit 201, a detection unit 202, a detection result management unit 203, a region of interest setting unit 204, a representative result selection unit 205, and a display unit 206.

[0016] The input unit 201 accepts input from a user specifying an image to be processed and a request for detecting abnormalities that have become apparent in objects in the image (hereinafter also referred to as an abnormality detection request). The detection unit 202 performs image recognition according to the conditions specified in the abnormality detection request on the image specified by the input unit 201 from the user, thereby detecting abnormalities in the image (e.g., changes in the state manifested in an object in the image, etc.). The detection result management unit 203 manages the results of the detection by the detection unit 202 of the abnormality in the target image. The attention area setting unit 204 sets an attention area for an image designated by the input unit 201 from a user. For example, the attention area setting unit 204 may set an attention area for the image based on a detection result of an abnormality in the target image by the detection unit 202. An example of a method for setting an attention area will be described in detail later together with the processing of the information processing device. Based on the result of setting the area of ​​interest by the area of ​​interest setting unit 204, the representative result selection unit 205 selects a portion of the detection results of abnormalities detected by the detection unit 202 based on each of a plurality of different conditions from the target image as a representative result. The display unit 206 displays information in a predetermined display area (for example, the screen of the display device 106, etc.) to present the information to a user. For example, the display unit 206 may display information such as the result of detection of anomalies in a target image by the detection unit 202, the result of setting an attention area in the image by the attention area setting unit 204, and a representative result selected by the representative result selection unit 205.

[0017] The configuration shown in FIG. 2 is merely an example, and does not necessarily limit the functional configuration of the information processing device according to the present embodiment as long as the functions of the above-mentioned components are realized. For example, the above-mentioned series of components may be realized by cooperation of multiple devices. As a specific example, some of the series of components shown in FIG. 2 may be realized by other external devices different from the information processing device. As a more specific example, components corresponding to the front end such as the input unit 201 and the display unit 206 and components corresponding to the back end such as the detection unit 202, the attention area setting unit 204, and the representative result selection unit 205 may be realized by different devices. In addition, at least some of the series of components shown in FIG. 2 may be realized by a so-called network service represented by a cloud service.

[0018] Next, an example of processing of the information processing device according to this embodiment will be described with reference to FIG. In S301, the input unit 201 receives from the user a designation of an image to be analyzed and a request for detecting abnormalities targeting the image. In this embodiment, for convenience, it is assumed that detection of abnormalities such as cracks that have occurred in infrastructure structures captured in an image is performed. The abnormality detection request includes information indicating the type of abnormality to be detected (e.g., cracks, exposed rebar, etc.), conditions (setting items) related to abnormality detection such as the amount of abnormality detected and noise removal rate, and parameters that specify the setting values ​​set for the conditions. Generally, when a larger amount of detection is specified, fewer abnormalities are missed, but there is a tendency for more false positives, in which things other than abnormalities (such as noise) are detected as abnormalities. Also, when a higher noise removal rate (stronger noise removal strength) is specified, the amount of noise that appears in the image is reduced, but there is a tendency for more abnormalities to be missed in the image. In this embodiment, the above parameters are managed separately as a reference parameter and a comparison parameter. The reference parameter is a parameter set in advance and is used as a criterion for setting an attention area or selecting a representative result. The comparison parameter is a parameter used for comparison in order for a user to obtain a desired detection result. The reference parameter and the comparison parameter are commonly specified for a plurality of types of detection conditions (for example, the amount of abnormality detection and the noise removal rate, etc.), and it is desirable that at least some of the set values ​​of the plurality of types of detection conditions are specified so as to be different from each other. The comparison parameter may be set in advance or may be specified by the user. Note that the parameter specified in the abnormality detection request corresponds to the comparison parameter. In this embodiment, the reference parameter corresponds to an example of a "first parameter", and the comparison parameter corresponds to an example of a "second parameter".

[0019] Now, referring to Figure 4, we will explain an example of a screen (hereinafter also referred to as a detection execution screen) that the input unit 201 displays in a specified display area to accept from the user the designation of an image and the input of a request to detect abnormalities in the image.

[0020] Specifically, the detection execution screen 401 shown in FIG. 4(a) shows an example of the detection execution screen when the user does not specify comparison parameters. The input form 402 is an input interface for receiving, from the user, the specification of an image file to be input. The input form 403 is an input interface for receiving, from the user, the specification of the type of abnormality to be the target of abnormality detection. The button 404 is an input interface for receiving, from the user, an instruction to confirm the information specified via the input forms 402 and 403 as the input. When the button 404 is pressed, abnormality detection is executed from the target image based on the information specified via the input forms 402 and 403.

[0021] Moreover, the detection execution screen 411 shown in FIG. 4(b) shows an example of the detection execution screen when the comparison parameters are specified by the user. The input form 412 is an input interface for receiving the specification of the image file to be input from the user. The input form 413 is an input interface for receiving the specification of the type of anomaly to be detected from the user. The input form 414 is an input interface for receiving the specification of parameters (for example, the setting values ​​of conditions such as the detection amount and the noise removal amount) related to the detection of anomalies from the image from the user. The parameters specified via the input form 414 are used as comparison parameters. In this embodiment, the user can specify multiple combinations of parameters to be compared via the input form 414. When the button 415 is pressed, anomaly detection from the target image is executed based on the information specified via the input forms 412, 413, and 414.

[0022] Here, reference is made again to Fig. 3. In S302, the detection unit 202 executes anomaly detection for the image specified in S301 based on the reference parameters. In the anomaly detection, for example, a so-called trained model (hereinafter also simply referred to as a model) constructed by reinforcement learning is used to detect cracks, water leakage areas, spalling areas, rust areas, and the like from the concrete wall surface image. The results of the anomaly detection are managed by the detection result management unit 203.

[0023] An example of information managed by the detection result management unit 203 will now be described with reference to FIG. FIG. 5(a) shows an example of information for managing information related to anomaly detection performed on an image indicated by an image file specified as input in association with the result of the anomaly detection. In the example shown in FIG. 5(a), an anomaly type 503, a parameter type 504, and a parameter 505 are stored in association with a file name 501 and a detection result ID 502. The input image file name 501 is the image file name of the image on which anomaly detection was performed. The detection result ID 502 is an identifier for uniquely identifying the result of anomaly detection. The anomaly type 503 is information indicating the type of anomaly specified as the target of anomaly detection. The parameter type 504 is information indicating whether the parameter applied when anomaly detection is performed is a reference parameter or a comparison parameter. The parameter 505 is information indicating the parameter applied when anomaly detection is performed (the set value specified for each detection condition).

[0024] FIG. 5(b) shows an example of information (e.g., information on a deformation) stored as a result of the deformation detection. In the example shown in FIG. 5(b), a point coordinate 508, a length 509, a crack width 510, and an importance 511 are stored in association with a detection result ID 506 and a deformation ID 507. The detection result ID 506 is an identifier for uniquely identifying the result of the deformation detection, and corresponds to the detection result ID 502 in the example shown in FIG. 5(a). The deformation ID 507 is an identifier for uniquely identifying each deformation included in the result of the deformation detection. The point coordinate 508 is information indicating the position of the target deformation in the image, and is indicated by the coordinates (two-dimensional or three-dimensional) of each bending point of the polyline. The length 509 is information indicating the length of the deformation. The crack width 510 is information indicating the width of a crack, which is a target deformation when the deformation type is a crack. The importance 511 is information indicating the importance of the target deformation. Here, an example of a method for determining the importance 511 will be described. For example, the importance may be determined so that the more dangerous the deformation is, the higher the importance is. As another example, the importance may be determined based on the degree to which the deformation affects the performance of the structure (hereinafter, also referred to as deformation rank). As another example, when the deformation type is a crack, the importance may be determined so that the longer the length and the wider the width is, the higher the importance is determined. As another example, the aging change may be calculated based on a comparison with past images of the same infrastructure structure as a subject, and the greater the aging change is, the higher the importance is determined.

[0025] Here, reference is made again to FIG. 3. In S303, the attention area setting unit 204 sets an attention area for the specified image. Specifically, the attention area setting unit 204 sets an area in the image including an abnormality with a higher importance 511 (for example, an abnormality with an importance 511 equal to or higher than a threshold value or an abnormality with a higher importance 511) among the abnormalities detected based on the reference parameters in S302 as an attention area. As a more specific example, the attention area setting unit 204 may set an attention area in the image by determining whether or not to set each partial area in the image as an attention area based on whether or not the partial area includes an abnormality with a higher importance 511. Note that the number of attention areas to be set may be a fixed number defined in advance, or may vary according to the setting conditions, such as targeting an area including each of a series of abnormalities with an importance equal to or higher than a threshold value.

[0026] With reference to Fig. 6, an example of the relationship between the result of anomaly detection based on the reference parameters and the attention area to be set in the process related to setting of the attention area by the attention area setting unit 204 will be described. In the example shown in Fig. 6, the target image 601 is divided into partial areas each including a predetermined number of pixels in a grid pattern, and a rectangular area including a more important deformation is set as the attention area. At this time, a maximum size of the rectangular area may be set. Under such circumstances, for example, if the target deformation does not fit into a rectangular area of ​​the maximum size, a rectangular area including a part of the deformation that is particularly important (for example, a part with a wide crack width) is set as the attention area. The example shown in Figure 6(a) illustrates a schematic example of a case in which an attention area 603 is set to a maximum size of two squares vertically and two squares horizontally when an abnormality 602 of higher importance (e.g., an abnormality whose importance is equal to or greater than a threshold) is present in an image 601. Moreover, the example shown in FIG. 6(b) illustrates a schematic example of a case in which an attention area 604 is set to a maximum size of four squares vertically and four squares horizontally when an abnormality 602 of higher importance is present in an image 601.

[0027] Here, reference is made again to Fig. 3. In S304, the detection unit 202 judges whether or not a comparison parameter exists. The comparison parameter is judged to exist when, for example, it is set in advance or specified in the abnormality detection request received by the input unit 201. If the detection unit 202 determines in S304 that the comparison parameter exists, it executes the process of S305. On the other hand, if the detection unit 202 determines in S304 that the comparison parameter does not exist, the detection unit 202 executes the process of S306, in which case the process of S305 is skipped.

[0028] In S305, the detection unit 202 performs anomaly detection from the target image based on each of the existing series of comparison parameters. In S306, the representative result selection unit 205 selects a portion of the results of the series of abnormality detections that have been executed as representative results.

[0029] Now, with reference to FIG. 7, an example of the process relating to the selection of a representative result by the representative result selection section 205, shown as the process of S306 in FIG. 6, will be described. In S701, the representative result selection unit 205 calculates a score based on the result of the abnormality detection based on the reference parameters for the region of interest. The score can be calculated, for example, based on the characteristics of the abnormality included in the result of the abnormality detection. As a specific example, when the type of abnormality is a crack, the score is calculated by multiplying the length and width of the target crack by a coefficient. In S702, the representative result selection unit 205 calculates a score based on the result of abnormality detection based on each comparison parameter for the region of interest. In S703, the similarity between the reference parameter and each comparison parameter is calculated. For example, the representative result selection unit 205 may calculate the similarity such that the value of the similarity is higher for a comparison parameter corresponding to a score closer to the score calculated based on the result of abnormality detection based on the reference parameter. In S704, the representative result selection unit 205 selects the reference parameter and a comparison parameter having a lower similarity to the reference parameter as representative parameters. That is, the representative result selection unit 205 selects a comparison parameter that shows a tendency for the result of abnormality detection to be more different from the reference parameter as a comparison target. The number of parameters selected as representative parameters may be a predefined fixed number, or may vary according to the extraction conditions, such as selecting all of a series of comparison parameters whose similarity is equal to or less than a threshold value. In S705, the representative result selection unit 205 selects, as representative results, the results of abnormality detection based on each of the series of parameters selected as the representative parameters. In this manner, a representative result is selected, and the series of processes shown in FIG. 7 is completed.

[0030] Here, reference is made again to Fig. 3. In S307, the display unit 206 performs control so that the representative result selected in S306 is displayed in a predetermined display area (for example, the screen of the display device 106). In S308, the display unit 206 receives an output request for the abnormality detection result from the user who confirmed the representative result displayed in S307. The output request specifies which parameter out of the series of parameters (representative parameters) applied to the detection of the representative result is to be used as the output target for the abnormality detection result. In S309, the display unit 206 outputs the result of the abnormality detection based on the parameters designated by the user in S308 to a predetermined output destination. With this, the series of processes shown in FIG. 3 is completed.

[0031] 8, a description will be given of an example of a screen (hereinafter also referred to as a detection result display screen) on which the results of the abnormality detection are presented and displayed by the display unit 206. The detection result display screen 801 is a screen that serves to display the results of the abnormality detection and to accept requests to output the results of the abnormality detection. The input image display area 802 is an area in which the entire input image 804 and attention areas 805 set in the input image are displayed. The series of attention areas 805 set in the input image are displayed in parallel, with each area corresponding to the position in the entire input image 804 in which it is set. The detection result display area 803 displays a plurality of representative results 806 selected for each of a series of attention areas set in the input image in parallel. The detection result display area 803 also displays an entire display button 807 and a result output button 808 associated with each of the series of representative results 806. The entire display button 807 is a button for displaying the entire associated representative result 806 (i.e., the abnormality detection result for the entire input image). The result output button 808 is a button for outputting the abnormality detection result based on the parameters applied to the detection of the associated representative result 806.

[0032] As described above, the information processing device according to this embodiment performs anomaly detection on an input image, and based on the result, sets an attention area including anomalies of higher importance, and selects anomaly detection results using parameters with different tendencies in the attention area. By applying such control, it becomes possible to more efficiently obtain anomaly detection results to which more suitable parameters are applied, even in a situation where it is difficult to distinguish the image area or parameter combination to be confirmed using conventional methods.

[0033] <Second embodiment> A second embodiment of the present disclosure will be described below. In the above-described first embodiment, an example of a case where a partial region of one input image is set as a region of interest is described. In contrast, in this embodiment, an example of a case where a region of interest is set on an image file basis when a large number of image files of relatively small size are input will be described. The functional configuration of the information processing device according to this embodiment is substantially the same as that of the first embodiment described above. The processing of the information processing device according to this embodiment is substantially the same as that of the first embodiment described above, except for the processing of S303 shown in Fig. 3. When setting an attention area in the processing of S303 shown in Fig. 3, the attention area setting unit 204 according to this embodiment sets an attention area for an image file including an abnormality having a higher importance level 511.

[0034] An example of a detection result display screen displayed by the display unit 206 according to this embodiment will be described with reference to Fig. 9. A detection result display screen 901 is a screen that displays a representative result and accepts a request to output the detection result. The input image display area 902 is an area in which a list 904 of a plurality of input image files and an image file set as an image of interest 905 are displayed. The detection result display area 903 displays, in parallel, a plurality of representative results 906 selected for the reference parameters and each of a plurality of comparison parameters in each of a plurality of target image files. Furthermore, the detection result display area 903 displays an all display button 907 and a result output button 908 in association with each of the series of representative results 906. The all display button 907 is a button for displaying the entirety of the associated representative result 906 (i.e., the abnormality detection results for the entire input image). The result output button 908 is a button for outputting the results of abnormality detection for the series of image files based on the parameters applied to the detection of the associated representative result 906.

[0035] As described above, according to the information processing device of this embodiment, when multiple image files are input, a more important attention area is set for each image file. With this configuration, even when a large number of image files are input, it is possible to more efficiently obtain anomaly detection results to which more suitable parameters are applied.

[0036] <Third embodiment> A third embodiment of the present disclosure will be described below. In the above-described first embodiment, an example of a case where a region of interest is set based on preset reference parameters has been described. In contrast, in this embodiment, an example of a case where a reference parameter is changed based on a user's past detection history will be described.

[0037] Fig. 10 shows an example of the functional configuration of the information processing device according to this embodiment. The information processing device 100 according to this embodiment differs from the information processing device 100 according to the first embodiment described with reference to Fig. 2 in that it has a detection history management unit 1001. Note that other components are substantially similar to the example shown in Fig. 2, and therefore detailed description thereof will be omitted. The detection history management unit 1001 manages the past detection history of the user.

[0038] An example of information managed as a detection history by the detection history management unit 1001 will be described with reference to FIG. 11. In the example shown in FIG. 11, a series of information in which a detection result ID 1102, an anomaly type 1103, and parameters 1104 are associated with a user ID 1101 is managed as a detection history. The user ID 1101 is an identifier for uniquely identifying a user. The detection result ID 1102 is an identifier for uniquely identifying the result of anomaly detection. The anomaly type 1103 is information indicating the type of anomaly specified as a target of anomaly detection. The parameters 1104 are information indicating parameters (setting values ​​specified for each detection condition) related to the execution of anomaly detection finally determined by the user as an applicable target. The parameters related to the execution of anomaly detection finally determined by the user as an applicable target are recorded, for example, when the result of anomaly detection is output.

[0039] The processing of the information processing device according to this embodiment is substantially similar to that of the first embodiment described above, except for the difference in the processing of S302 shown in Fig. 3. In the processing of S302 shown in Fig. 3, when performing anomaly detection, the detection unit 202 according to this embodiment uses, as a reference parameter, a parameter that is more frequently applied by the target user when detecting the type of anomaly to be detected.

[0040] As described above, according to the information processing device of the present embodiment, the reference parameters are changed using the user's past detection history. By applying such a configuration, it becomes possible to set the attention area in accordance with the user's usage tendency.

[0041] <Fourth embodiment> A fourth embodiment of the present disclosure will be described below. In the above-mentioned first embodiment, an example of a case where an anomaly detection is performed using a reference parameter and a comparison parameter when an anomaly detection request is received from a user is described. In contrast, in the present embodiment, an example of a case where anomaly detection is limited to a region of interest using comparison parameters rather than the entire image when an anomaly detection request is received, and anomaly detection is performed on the entire image when a request for result output is received from a user is described. Note that the functional configuration of the information processing device according to this embodiment is substantially similar to that of the information processing device 100 according to the first embodiment described with reference to FIG. 2, and therefore a detailed description thereof will be omitted.

[0042] An example of processing by the information processing device according to this embodiment will be described with reference to FIG. In S301, the input unit 201 receives from the user a designation of an image to be analyzed and a request for detecting abnormalities in the image. For convenience, in this embodiment, it is assumed that detection of abnormalities such as cracks in infrastructure structures captured in an image is performed in the same manner as in the first embodiment described above. In S302, the detection unit 202 executes anomaly detection for the image specified in S301 based on the reference parameters. In S303, the attention area setting unit 204 sets an attention area in the specified image. The above processing is substantially similar to the processing of the information processing device 100 according to the first embodiment described with reference to FIG.

[0043] In S304, the detection unit 202 determines whether or not a comparison parameter exists. If the detection unit 202 determines in S304 that the comparison parameters exist, it executes the process of S1201. Specifically, in S1201, the detection unit 202 executes anomaly detection from the target image based on each of the series of comparison parameters that exist. Note that, at this time, the detection unit 202 executes anomaly detection based on the comparison parameters for the region of interest, not the entire image. Furthermore, if the detection unit 202 determines in S304 that the comparison parameter does not exist, it executes the process of S306, in which case the process of S305 is skipped.

[0044] In S306, the representative result selection unit 205 selects some results as representative results from the results of a series of executed abnormality detections. Note that the method of selecting the representative result is substantially the same as the example described with reference to FIG. 7 in the first embodiment. In S307, the display unit 206 performs control so that the representative result selected in S306 is displayed in a predetermined display area (for example, the screen of the display device 106). In S308, the display unit 206 receives an output request for the abnormality detection result from the user who confirmed the representative result displayed in S307. The output request specifies which parameter out of the series of parameters (representative parameters) applied to the detection of the representative result is to be used as the output target for the abnormality detection result. In S1202, the detection unit 202 executes anomaly detection for the entire image based on the parameters specified in S308. In S309, the display unit 206 outputs the result of the abnormality detection executed in S1202 to a predetermined output destination. With this, the series of processes shown in FIG. 12 ends.

[0045] As described above, the information processing device according to the present embodiment limits the target of anomaly detection to the region of interest rather than the entire image at the stage of selecting a representative result. By applying such control, it is expected that the processing load of anomaly detection when selecting a representative result can be reduced.

[0046] <Other embodiments> Although the embodiment has been described above in detail, the present invention can be embodied as, for example, a system, an apparatus, a method, a program, a recording medium (storage medium), etc. Specifically, the present invention may be applied to a system composed of multiple devices (for example, a host computer, an interface device, an imaging device, a Web application, etc.), or may be applied to an apparatus composed of a single device. Needless to say, the object of the present invention can be achieved by the following: That is, a recording medium (or storage medium) on which is recorded a program code (computer program) of software that realizes the functions of the above-mentioned embodiments is supplied to a system or device. The storage medium is, of course, a computer-readable storage medium. Then, a computer (or a CPU or MPU) of the system or device reads and executes the program code stored in the recording medium. In this case, the program code itself read from the recording medium realizes the functions of the above-mentioned embodiments, and the recording medium on which the program code is recorded constitutes the present invention.

[0047] The disclosure of the present embodiment also includes the following configurations, methods, and programs. (Configuration 1) An information processing device comprising: a receiving means for receiving from a user a detection request for detecting an anomaly in an image and a specification of an image to be detected; and a display control means for displaying in a specified display area a representative result selected from the anomaly detection results based on a plurality of parameters having different setting values ​​for at least some of a plurality of predetermined types of detection conditions for the specified image; wherein the representative result is selected based on the characteristics of the anomaly contained in a region of interest set in the specified image based on the importance of the anomaly detected in the specified image. (Configuration 2) The information processing device according to configuration 1, wherein the display control means displays the image and the region of interest in association with the representative result targeted at the region of interest. (Configuration 3) The information processing device according to configuration 1 or 2, wherein the display control means displays the representative results so that the representative results are presented in parallel. (Configuration 4) An information processing device as described in any one of configurations 1 to 3, comprising: a detection means for detecting anomalies from the image based on each of the multiple parameters in response to the detection request received by the receiving means; a setting means for setting the attention area in the image based on the importance of the anomaly detected from the image by the detection means; and a selection means for selecting a portion of the detection results of anomalies from the image based on each of the multiple parameters as the representative result based on characteristics of the anomaly included in the attention area set by the setting means, wherein the display control means displays the representative result selected by the selection means in a predetermined display area. (Configuration 5) The information processing device described in Configuration 4, characterized in that the setting means sets the attention area in the image based on the importance of an abnormality detected from the image based on a first parameter having a predetermined setting value specified for the multiple types of detection conditions. (Configuration 6) The information processing device described in Configuration 5, characterized in that the selection means selects as the representative result a detection result of an anomaly in the image based on the first parameter and a detection result having a lower similarity to the detection result of an anomaly in the image based on the first parameter among the detection results of an anomaly in the image based on each of the second parameters other than the first parameter among the multiple parameters. (Configuration 7) An information processing device as described in configuration 5 or 6, further comprising a management means for managing a history of parameters applied to detection of anomalies from images performed in the past, and the setting means sets the area of ​​interest in the image based on the importance of anomalies detected from the image based on the first parameters determined on the basis of the history managed by the management means. (Configuration 8) The information processing device described in any one of configurations 5 to 7, characterized in that the receiving means receives from a user an output request for outputting the detection result of abnormality from the image, and the detection means, in response to the detection request received by the receiving means, detects abnormality in the target area based on each second parameter different from the first parameter, and detects abnormality in the target image based on the second parameter specified in response to the output request received by the receiving means. (Configuration 9) The information processing device of any one of configurations 4 to 8, characterized in that the receiving means receives the designation of multiple image files as targets for detecting abnormalities in the images, the detection means detects abnormalities in the images for each of the multiple image files, and the setting means sets the attention area for an image file in which an abnormality of higher importance has been detected. (Configuration 10) The information processing device described in any one of configurations 4 to 9, characterized in that the detection means detects a deformation of a structure imaged as a subject in the image, and the setting means sets the attention area in the image based on at least one of the degree to which the deformation affects the performance of the structure and the magnitude of change in the deformation over time. (Method 1) A control method for an information processing device, comprising: a reception step for receiving from a user a detection request for detecting an anomaly in an image and a designation of the image to be detected; and a display control step for displaying in a designated display area a representative result selected from the anomaly detection results based on a plurality of parameters having different setting values ​​for at least some of a plurality of predetermined types of detection conditions for the designated image, wherein the representative result is selected based on the characteristics of the anomaly contained in a region of interest set in the designated image based on the importance of the anomaly detected in the designated image. (Program 1) A program for causing a computer to function as an information processing device having a receiving means for receiving a detection request from a user for detecting an abnormality in an image and a designation of the image to be detected, and a display control means for displaying in a designated display area a representative result selected from the abnormality detection results based on a plurality of parameters having different setting values ​​for at least some of a predetermined plurality of types of detection conditions for the designated image, wherein the representative result is selected based on the characteristics of the abnormality included in a region of interest set in the designated image based on the importance of the abnormality detected in the designated image. [Explanation of symbols]

[0048] 100 Information processing device 201 Input section 204 Area of ​​interest setting section 205 Representative results selection department 206 Display section

Claims

1. A receiving means for receiving a detection request from a user for detecting an abnormality in an image and a designation of an image to be detected; A display control means for displaying in a predetermined display area a representative result selected from the detection results of the abnormality based on a plurality of parameters each having different set values ​​among a plurality of predetermined types of detection conditions for the specified image; having The representative result is selected based on the characteristics of the abnormality included in the attention area set in the specified image based on the importance of the abnormality detected from the specified image. An information processing device comprising:

2. The information processing apparatus according to claim 1 , wherein the display control means displays the image and the region of interest in association with the representative result targeted at the region of interest.

3. The information processing apparatus according to claim 1 , wherein the display control means displays the representative results so that the representative results are presented in parallel.

4. A detection means for detecting an abnormality from the image based on each of the plurality of parameters in response to the detection request received by the reception means; A setting means for setting the attention area in the image based on the importance of the abnormality detected from the image by the detection means; A selection means for selecting a part of the detection results of the anomaly from the image based on each of the plurality of parameters as the representative result based on the characteristics of the anomaly included in the attention area set by the setting means; having The display control means displays the representative result selected by the selection means in a predetermined display area.

2. The information processing device according to claim 1.

5. The information processing device described in claim 4, characterized in that the setting means sets the attention area in the image based on the importance of the abnormality detected from the image based on a first parameter having a predetermined setting value specified for the multiple types of detection conditions.

6. The selection means is A detection result of an abnormality from the image based on the first parameter; A detection result having a lower similarity to the detection result of the anomaly from the image based on the first parameter among the detection results of the anomaly from the image based on each of the second parameters other than the first parameter among the plurality of parameters; is selected as the representative result.

6. The information processing device according to claim 5.

7. A management means for managing a history of parameters applied to detection of anomalies from images in the past, The setting means sets the attention area in the image based on the importance of the abnormality detected from the image based on the first parameter determined based on the history managed by the management means.

6. The information processing device according to claim 5.

8. The receiving means receives an output request from a user for outputting a result of detection of an abnormality from the image, The detection means includes: In response to the detection request received by the receiving means, detection of anomalies is performed on the attention area based on second parameters different from the first parameters; Based on the second parameter specified in response to the output request accepted by the accepting means, an abnormality is detected for the image.

6. The information processing device according to claim 5.

9. The receiving means receives designation of a plurality of image files as targets for detecting abnormalities in the images, The detection means detects anomalies in the images of each of the plurality of image files, The setting means sets the attention area for an image file in which a defect of higher importance is detected.

5. The information processing device according to claim 4.

10. The detection means detects a deformation of a structure captured as a subject in the image, The setting means sets the attention area in the image based on at least one of the degree to which the deformation affects the performance of the structure and the magnitude of aging of the deformation.

5. The information processing device according to claim 4.

11. A method for controlling an information processing device, comprising: A receiving step of receiving a detection request for detecting an abnormality in an image from a user and a designation of an image to be detected; A display control step of displaying in a predetermined display area a representative result selected from the detection results of the abnormality based on a plurality of parameters each having different set values ​​among a plurality of predetermined types of detection conditions for the specified image; Including, The representative result is selected based on the characteristics of the abnormality included in the attention area set in the specified image based on the importance of the abnormality detected from the specified image.

23. A method for controlling an information processing apparatus comprising:

12. Computer, A receiving means for receiving a detection request from a user for detecting an abnormality in an image and a designation of an image to be detected; A display control means for displaying in a predetermined display area a representative result selected from the detection results of the abnormality based on a plurality of parameters each having different set values ​​among a plurality of predetermined types of detection conditions for the specified image; having The representative result is selected based on the characteristics of the abnormality included in the attention area set in the specified image based on the importance of the abnormality detected from the specified image. A program for causing the information processing device to function as the information processing device.

Images