Information processing device, information processing method, and program

Abstract

This makes it easier to configure the recognition process so that recognition can be performed in a recognition environment that can reproduce recognition results similar to those of past recognition processes. [Solution] An information processing device that displays the results of a recognition process on a display device. The device obtains the results of a first recognition process performed on a first recognition target information using a first model. The device displays the results of the first recognition process, the results of a second recognition process performed on the first recognition target information using a second model different from the first model, information indicating that the results of the first recognition process were performed using the first model, and information indicating that the results of the second recognition process were performed using the second model on a display device.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program, and for example, to a deformation detection process for an image of a structure. [Background technology]

[0002] Recognition devices and services are provided that recognize objects or other targets from information such as images. Such recognition devices train models such as CNNs (Convolutional Neural Networks) using a large amount of training data, and then use the trained model to recognize targets from input information.

[0003] For example, Patent Document 1 discloses a technology for detecting cracks from images captured by an unmanned aerial vehicle using a learning model. In Patent Document 1, cracks are detected using two types of models: a specialized learning model capable of identifying a specific type of crack, and a non-specialized learning model capable of identifying multiple types of cracks other than the specific type. [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Patent No. 6807093 [Overview of the Initiative] [Problems that the invention aims to solve]

[0005] Users of recognition devices may want to compare the results of recognition processing on past information (e.g., past images of a structure) with the results of recognition processing on current information (e.g., current images of a structure). For example, when inspecting a structure, comparing images may allow for the analysis of the progression of deformation. Specifically, the degree of deformation can be evaluated by analyzing the extension or amplification of cracks in the structure. In this case, since the recognition results will differ if the model or processing parameters used for recognition processing are different, it is desirable to perform the recognition processing in a recognition environment where similar recognition results can be obtained.

[0006] On the other hand, providers of recognition devices may update their models and deprecate older models. In this case, the previously used model can no longer be used for recognition processing, which can make it difficult to compare the results of recognition processing for information at different points in time.

[0007] The present invention aims to facilitate the configuration of recognition processing so that recognition processing can be performed in a recognition environment that can reproduce recognition results similar to those of past recognition processing. [Means for solving the problem]

[0008] The information processing device according to one embodiment of the present invention has the following configuration. That is, An information processing device that displays the results of a recognition process on a display device, An acquisition means for acquiring the result of a first recognition process performed on a first recognition target information using a first model, Display means for displaying on the display device the result of the first recognition process, the result of a second recognition process performed on the first recognition target information using a second model different from the first model, information indicating that the result of the first recognition process is due to the first model, and information indicating that the result of the second recognition process is due to the second model. It is equipped with. [Effects of the Invention]

[0009] It is possible to facilitate setting of recognition processing so that recognition processing can be performed in a recognition environment that can reproduce recognition results similar to past recognition processing.

Brief Description of Drawings

[0010] [Figure 1] A block diagram showing a functional configuration example of a recognition device according to an embodiment. [Figure 2] A block diagram showing a hardware configuration example of a recognition device according to an embodiment. [Figure 3] A flowchart of a recognition processing method according to an embodiment. [Figure 4] A diagram showing an example of a display screen showing the history of recognition processing. [Figure 5] A diagram showing an example of a user interface for setting recognition processing. [Figure 6] A diagram showing an example of a screen for proposing search processing. [Figure 7] A diagram showing an example of a screen for displaying search results. [Figure 8] A diagram showing an example of history information managed by the history management unit 122. [Figure 9] A flowchart of search processing. [Figure 10] A diagram showing an example of classification information of models managed by the model management unit 106.

Modes for Carrying Out the Invention

[0011] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.Note that the following embodiments do not limit the invention according to the claims.Although a plurality of features are described in the embodiments, not all of these plurality of features are essential for the invention, and the plurality of features may be arbitrarily combined.Furthermore, in the accompanying drawings, the same or similar configurations are denoted by the same reference numerals, and redundant descriptions are omitted.

[0012] FIG. 1 shows the functional configuration of a recognition device according to an embodiment of the present invention. Information to be recognized (recognition target information) 102 is input to the recognition device 101, and a recognition result 103 obtained by recognition processing on the recognition target information 102 is output. The type of the recognition target is not particularly limited, and may be, for example, an image, text information, voice information, or signal information. Also, the type of the recognition processing is not particularly limited, and examples thereof include processing for recognizing a recognition target from an image, processing for recognizing an abstract sentence from text information, or processing for recognizing an abnormality from the hitting sound of a structure or a sensor signal of a device. In the following embodiments, a case where the recognition device 101 recognizes a deformation occurring in a structure in an image, such as a crack, from an image will be described. The structure may be an infrastructure structure such as a tunnel or a bridge.

[0013] The recognition device 101 according to the present embodiment can be realized by a computer including a processor and a memory. FIG. 2 shows an example of the hardware configuration of the recognition device 101 according to an embodiment. A CPU (Central Processing Unit) 201 executes a control program of the recognition device 101. A ROM 202 stores this control program and the like. A RAM 203 provides a work area for the CPU 201. A network IF 204 is used for communicating with an application outside the recognition device 101. A storage device 205 is, for example, a hard disk and stores data or programs. As described above, by a processor such as the CPU 201 executing a program stored in a memory such as the ROM 202, the RAM 203, or the storage device 205, the functions of each part shown in FIG. 1 and the like can be realized.

[0014] Next, the functional configuration of the recognition device 101 according to the present embodiment will be described with reference to the block diagram of FIG. 1. The recognition device 101 according to the present embodiment can facilitate searching for a setting of recognition processing that can obtain a similar result when a model used in the past for recognition processing is abolished.

[0015] As shown in Figure 1, the recognition device 101 comprises a recognition unit 105, a model management unit 106, an output unit 108, and a search unit 120. The model management unit 106 manages the models used for recognition processing.

[0016] The search unit 120 obtains the result of the first recognition process performed on the first recognition target information using the first model.

[0017] The recognition unit 105 performs recognition processing on the information to be recognized. The recognition unit 105 can perform recognition processing using a model managed by the model management unit 106. Furthermore, the recognition unit 105 can perform this recognition processing according to the set processing parameters. In this embodiment, the recognition unit 105 uses a model different from the first model managed by the model management unit 106 to perform recognition processing on the first information to be recognized according to each of the multiple settings, and generates the recognition processing result corresponding to each of the multiple settings. The recognition unit 105 can also perform recognition processing on the second information to be recognized. At this time, the recognition unit 105 can perform recognition processing according to the set recognition processing settings by referring to the settings output by the output unit 108.

[0018] The output unit 108 outputs the settings corresponding to the recognition processing result selected based on a comparison of the results of the recognition processing corresponding to each of the multiple settings with the result of the first recognition processing. For example, the output unit 108 can output the model and processing parameters set by the search unit 120 that correspond to the recognition processing result selected by the determination unit 121 or according to user input. The output unit 108 can also output the results of the recognition processing managed by the history management unit 122.

[0019] The recognition device 101 may further include an information input unit 104, a setting unit 107, a search unit 120, a determination unit 121, and a history management unit 122. The information input unit 104 can acquire a second recognition target information.

[0020] The setting unit 107 can configure the recognition process. For example, the setting unit 107 can configure the recognition process according to user input.

[0021] The search unit 120 can further create multiple settings used for the recognition processing performed by the recognition unit 105 on the first recognition target information. The search unit 120 can create multiple settings by combining the model and processing parameters used based on the search method.

[0022] The determination unit 121 can determine the similarity of the results of the recognition process. Specifically, the determination unit 121 can determine the similarity of the results of the recognition process corresponding to each of the multiple settings with the result of the first recognition process. Furthermore, the determination unit 121 can select a recognition process result from the results of the recognition process corresponding to each of the multiple settings according to the similarity. In this embodiment, the determination unit 121 calculates the similarity based on the difference between the two recognition results, as will be described later.

[0023] The history management unit 122 manages the recognition target information and the results of the recognition processing applied to the recognition target information. The history management unit 122 may also manage the recognition processing settings in association with the results of the recognition processing. The recognition processing settings may include information that identifies the model, such as a model ID, which is the model's identification information. The recognition processing settings may also include processing parameters used in the recognition processing using the model. Furthermore, the recognition processing settings may include information that indicates the recognition target. In this way, the recognition processing settings can indicate the content of the recognition processing and can be called model information. The history management unit 122 may also manage the recognition target information that has been subjected to the recognition processing.

[0024] In the following example, the first and second recognition target information are the same type of information or information about the same type of object, for example, the first and second images of a structure. The first and second images may be images obtained by imaging the same structure at different times. For example, the time the second image was captured may be several years later than the time the first image was captured.

[0025] In the following example, a recognition process setting using a model managed by the model management unit 106 can be obtained that can reproduce a recognition result similar to the first recognition process performed on the first image in the past using the first model. Such a setting can indicate the model and processing parameters used in the recognition process, and these will be referred to as the similar model and similar parameters below. Then, the recognition process on the second image is performed according to the recognition process setting that was set by referring to the recognition process setting obtained in this way. Through this process, the recognition process on the second image can be performed in a recognition environment that can reproduce a recognition result similar to the first recognition process performed in the past. Such similar models and similar parameters can be used for recognition processing on images for the purpose of year-on-year comparison.

[0026] Next, the recognition process performed by the recognition device according to this embodiment will be explained with reference to the flowchart in Figure 3. In S301, the information input unit 104 acquires the information to be recognized. In this example, the information input unit 104 acquires a second image.

[0027] In S302, the setting unit 107 checks whether the first model previously used for recognition processing on the first image is available. In one embodiment, the output unit 108 can present the user with a history of recognition processing managed by the history management unit 122. For example, the output unit 108 can present the user with a list of the execution history of recognition processing, as shown in Figure 4. The output unit 108 may also present the user with the settings for each recognition processing. In Figure 4, list 401 shows the date and time of execution of the recognition processing, the input image which is the information to be recognized, the identification information of the model used for the recognition processing, and the processing parameters used for the recognition processing. The processing parameters may include, for example, detection quantity parameters that control the amount of recognition target detected in the recognition processing (for example, making the recognition target easier or harder to detect). The processing parameters may also include noise reduction parameters that indicate the intensity of noise reduction processing as preprocessing on the recognition target information. However, the types of processing parameters are not limited to these.

[0028] This list 401 further includes a notification 402 indicating that a model previously used for recognition processing has been deprecated and is no longer available. In this way, the model management unit 106 can notify the availability of a model on the execution history list via the output unit 108. The model management unit 106 may also notify the availability of a model by another method, for example, on another screen such as the top screen or model management screen of the recognition processing system.

[0029] The user can identify the history of recognition processes that recognize the same object for an image of the same structure as the second image, from the execution history. This identified recognition process is the first recognition process. The user can also check whether the model used in the first recognition process for the first image is available, based on the model identification information and model deprecation status displayed in the execution history list.

[0030] In this embodiment, the user checks whether the model used in the first recognition process is available. If the first model is available, the setting unit 107 receives a user instruction indicating that recognition processing will be performed using the first model, and the process then proceeds to S303. On the other hand, if the first model is unavailable, the setting unit 107 receives a user instruction indicating that model search processing will be performed, and the process then proceeds to S304.

[0031] On the other hand, the setting unit 107 may obtain a user instruction to select a first recognition process from the history of presented recognition processes. In this case, the setting unit 107 can refer to the model management unit 106 to check whether the first model used for the first recognition process specified by the user is available. If the first model is available, the process proceeds to S303; if the first model is unavailable, the process proceeds to S304.

[0032] In S303, the setting unit 107 obtains the recognition processing settings for the second recognition target information, which have been set by referring to the settings for the first recognition processing. In one embodiment, the user can set the recognition processing settings by referring to the settings for the first recognition processing. Figure 5 shows an example of a user interface (UI) for setting the model and processing parameters. This UI has a list 501 for selecting the recognition target, a list 502 for selecting the model to be used for the recognition processing, and a slider 503 for setting the processing parameters. There is one or more models for each recognition target.

[0033] However, the setting unit 107 may configure the recognition process for the second recognition target information so that it performs the same processing as the first recognition process. Also, the initial values ​​in the UI shown in Figure 5 may be set according to the settings in the first recognition process. Furthermore, the setting unit 107 may automatically configure the recognition process considering the attributes of the recognition target information (e.g., acquisition time period, image brightness, or GPS information) and the type of recognition target.

[0034] From S304 onward, a search for similar models and parameters is performed. Figure 6 shows an example of a UI for suggesting a search for similar models and parameters to the user and accepting user instructions before proceeding to S304. Such a UI can be displayed in response to the user selecting a history of recognition processing using an unavailable model in S302. Alternatively, such a UI may be displayed in response to the user selecting an unavailable model in S303.

[0035] In S304, the output unit 108 presents the user with the history of recognition processes managed by the history management unit 122. In S305, the setting unit 107 obtains a user instruction to select a first recognition process from the presented history of recognition processes. The processes in S304 and S305 can be carried out as described in relation to S302. If a first recognition process has already been selected in S302 or elsewhere, S304 and S305 can be omitted.

[0036] In S306, the search unit 120 obtains from the history management unit 122 the result of the first recognition process performed on the first recognition target information using the first model. That is, the search unit 120 can obtain the recognition result managed by the history management unit 122 in association with the history selected in S305. Furthermore, the search unit 120 can obtain the first recognition target information from the history management unit 122. For example, the search unit 120 can obtain the first image managed by the history management unit 122 in association with the history selected in S305. In another embodiment, the search unit 120 may also obtain the exported first recognition target information and the result of the first recognition process.

[0037] In S307, the search unit 120 and the determination unit 121 search for similar models and similar parameters based on the results of the first recognition process and the first recognition target information obtained in S306. Specifically, a recognition process result is selected from the results of the recognition process corresponding to each of the multiple settings, based on a comparison with the result of the first recognition process. As will be described later, the determination unit 121 can select a recognition process result based on its similarity to the result of the first recognition process. The model and processing parameters used to obtain the selected recognition process result are then determined to be similar models and similar parameters. The detailed process will be described later.

[0038] In S308, the output unit 108 outputs the search result from S307. In this example, the output unit 108 presents the user with the result of the recognition process selected by the determination unit 121 from among the results of the recognition processes corresponding to each of the multiple settings.

[0039] Figure 7 shows an example of a UI used to present the search results to the user. Area 701 shows the result of the first recognition process obtained in S306, and area 702 shows the result of the recognition process selected by the determination unit 121. The output unit 108 can also output settings corresponding to the recognition process result selected in S307. Here, the settings output by the output unit 108 may include information that identifies the model used for the recognition process. The settings output by the output unit 108 may also include processing parameters used for the recognition process. For example, area 702 also shows the similar model and similar parameters selected by the determination unit 121. Furthermore, the output unit 108 may also output the similarity between the result of this recognition process and the result of the first recognition process, as determined in S307, along with the result of the recognition process.

[0040] In S309, the recognition process is configured by referring to the settings output by the output unit 108. For example, the setting unit 107 accepts user input indicating the settings for the recognition process to be performed on the second recognition target information. Here, the user can configure the recognition process by referring to the similar model and similar parameters output in S308. The recognition process can be configured in the same way as in S303. For example, the user can configure the recognition process using the UI shown in Figure 5. The user may configure the similar model and similar parameters output in S308. Alternatively, the user may further adjust the processing parameters. The output unit 108 may also present the user with a UI that includes an area where the output unit 108 presents the settings and an area where user input indicating the settings for the recognition process to be performed on the second recognition target information is accepted. In this case, the user can configure the recognition process on such a UI.

[0041] As another example, the setting unit 107 may automatically configure the recognition process to be performed on the second recognition target information according to the settings output by the output unit 108 in S307. For example, the setting unit 107 may configure the second recognition process to use the similar model and similar parameters output in S308.

[0042] In S310, the recognition unit 105 performs recognition processing on the second recognition target information according to the recognition processing settings set in S303 or S309. For example, the recognition unit 105 performs recognition processing on the image acquired in S301 using the set model and processing parameters.

[0043] In S311, the history management unit 122 stores the history of the recognition process for the second recognition target information in S310. Here, the history management unit 122 can store the model and processing parameters used in the recognition process, the second recognition target information, and the recognition result. Figure 8 shows an example of the history information stored in the history management unit 122. As shown in Figure 8, the recognition date and time, the identification information of the image which is the recognition target information, the identification information of the model, and the processing parameters are stored in association with the execution ID that identifies the history. Note that the history information stored in the history management unit 122 may also include information indicating the recognition target or the identification information of the user who performed the recognition process.

[0044] In S312, the output unit 108 outputs the result of the recognition processing obtained in S310. In this embodiment, the output unit 108 can superimpose the location of the recognized cracks or other deformations onto the image, which is the information to be recognized, and output a superimposed image. The output unit 108 may also output vector data indicating the cracks. However, as described above, the recognition processing performed by the recognition device according to the present invention is not particularly limited, and the output of the output unit 108 can take various forms. The result of such recognition processing can be displayed on a display device such as a display, and the user can confirm it.

[0045] Next, the search process performed by the search unit 120 and the determination unit 121 in S307 will be explained with reference to the flowchart in Figure 9. As described above, in S305 the execution history of the first recognition process is selected, and in S306 the search unit 120 acquires the first recognition result and the first image stored in the history management unit 122. Based on these first recognition result and first image, the search unit 120 searches for similar models and similar parameters.

[0046] In S901, the search unit 120 generates settings for recognition processing. In S902, the recognition unit 105 performs recognition processing on the first recognition target information according to the settings generated in S901. In S903, the determination unit 121 determines the similarity between the recognition result obtained in S902 and the first recognition result. In S904, the search unit 120 determines whether to continue the search. If the search is to be continued, the process returns to S901 and new settings for recognition processing are generated. If the search is to be terminated, the process proceeds to S905.

[0047] By repeating the processes S901 to S904, the search unit 120 can generate multiple settings for recognition processing. Each of these settings can have a different combination of model and processing parameters. For example, the search unit 120 can generate multiple settings using each of the multiple models managed by the model management unit 106. The search unit 120 can also generate multiple settings using each of the different processing parameters.

[0048] The search unit 120 can configure settings including models and processing parameters based on the search method. For example, in S901, the search unit 120 may generate settings that use various processing parameters while fixedly using one model. Alternatively, the search unit 120 may generate settings that use various models while fixedly using one processing parameter (e.g., initial parameter). The search method used by the search unit 120 is not particularly limited, and for example, exhaustive search, grid search, random search, Bayesian optimization, or other search methods can be used.

[0049] In one embodiment, the search unit 120 generates a setting to use a model associated with the first model from among the models managed by the model management unit 106. In this case, the model management unit 106 can manage the associations between models. By narrowing the search range of the setting to use only models associated with the first model in this way, the time required for the search can be reduced. For example, the model management unit 106 can manage information that specifies one or more models as successor models to the first model. In this case, the search unit 120 can generate a setting to use the successor models.

[0050] Figure 10 shows an example of model classification information managed by the model management unit 106. The model management unit 106 can register model identification information such as the model name, the model's recognition target, and information indicating the model's lineage. The lineage is a value assigned by the model's registrant for classifying the model. The model management unit 106 may also manage other information about the model, such as information identifying users who can use the model or the model's registration date and time. Based on this model classification information, the search unit 120 can generate settings to use only models associated with the first model. For example, the search unit 120 can search for settings so that the first model and the recognition target or lineage, or both, use the same model.

[0051] In S905, the search unit 120 determines the recognition result with the highest similarity calculated in S903 from among the recognition results obtained according to each of the multiple settings generated by the repetition of S902. The model and parameters used to obtain this recognition result become the similar model and similar parameters. The similar model and similar parameters determined in S905 are output by the output unit 108 in S308.

[0052] A method for determining similarity in S903 will be described. In S903, the determination unit 121 can estimate the difference between the first recognition result and the recognition result obtained in S902, and obtain this estimated value as the similarity. When detecting deformation from an image as in this embodiment, it is conceivable that an image indicating the position of the deformation is output as the recognition result. In such a case, the difference between the two images indicating the respective recognition results can be taken, and the similarity can be calculated based on the difference amount.

[0053] As a specific example, the similarity can be calculated as follows. One image contains a predetermined number of pixels. Therefore, the difference amount of the image can be estimated by obtaining the absolute value of the density difference of the corresponding pixels in the two images to be compared and taking the sum of these absolute values. In this case, it can be considered that the smaller the difference amount, the higher the similarity, and the larger the difference amount, the lower the similarity. For example, the density of each pixel is represented by 0 to 1, and the density of each pixel of the recognition result A is A(a , , , , ,

[0054] , a 0,1 , …, a 0,n , a 1,0 , …, a n,n ), and the density of each pixel of the recognition result B is B(b 0,0 , b 0,1 , …, b 0,n , b 1,0 , …, b n,n ). In this case, the similarity between the recognition result A and the recognition result B can be obtained according to Equation (1).

Equation

[0054] On the other hand, since a deformation such as a crack is a partial feature in image data, even when the crack is represented by the same vector data, there is a possibility that a slight positional deviation may be determined as a difference. Therefore, a method for calculating the difference considering the positional deviation, such as expanding the crack, may be adopted. Note that the similarity may be calculated by converting the vector data representing the result of the recognition process into feature data suitable for comparison and calculating the distance between the feature data.

[0055] In the above embodiment, the recognition result with the highest similarity is determined in S905, and the model and parameters used to obtain this recognition result are output as a similar model and similar parameters in S308. On the other hand, the most desirable setting for the user that gives a recognition result similar to the first recognition processing result may not be the setting that gives the highest similarity. For example, this possibility is likely to occur when the recognition result is represented as visual information or multiple item values, and when there are multiple settings that give a high similarity. Therefore, in S905, the search unit 120 may select two or more recognition results. For example, the search unit 120 can select a predetermined number of recognition results that have a higher similarity than other settings.

[0056] In this case, instead of outputting the recognition result with the highest similarity in S308, the search unit 120 may output each of the two or more recognition results selected in S905. In this case, the search unit 120 can output the combination of models and parameters used to obtain each of the two or more recognition results. With this configuration, the user can select a recognition result that suits their intention from among multiple recognition results with high similarity, and furthermore, in S309, they can set similar models and similar parameters that will yield a recognition result that suits their intention. Alternatively, in S309, the user may provide user input indicating a recognition result that suits their intention from among the recognition results output in S308. In this case, the setting unit 107 can set the combination of models and parameters used to obtain the recognition result indicated by the user input as a setting for the recognition processing to be performed on the second recognition target information.

[0057] In the above embodiment, in S902, recognition processing was performed on recognition target information used in past recognition processing managed by the history management unit 122. In S903, a comparison was made between the results of past recognition processing managed by the history management unit 122 and the recognition result obtained in S902. On the other hand, recognition processing may also be performed on other recognition target information in S902. For example, the first recognition target information used in S902 may be a sample image. This sample image is prepared in advance as a general image to be input into the recognition process. In this case, in S902, the recognition unit 105 can perform recognition processing on the sample image according to the settings generated in S901.

[0058] In this embodiment, the history management unit 122 can manage the results of recognition processing performed on common recognition target information, such as a sample image, using each of multiple models. For example, the history management unit 122 can manage the results of a first recognition processing performed on a sample image using a first model. Then, in S903, the determination unit 121 can compare the results of the first recognition processing performed on the sample image using the first model, which is managed by the history management unit 122, with the recognition results obtained in S902.

[0059] On the other hand, this configuration using sample images allows for the pre-search for similar models and parameters corresponding to the first model, without waiting for user instructions to search for similar models and parameters. For example, by performing such a search when decommissioning a model, it becomes possible to quickly present similar models and parameters that generally correspond to the decommissioned model.

[0060] This configuration can be achieved by performing the process shown in Figure 9 when the first model is discontinued, or when it is decided that the first model will be discontinued. The model management unit 106 can manage whether the model is usable or not, and discontinuing a model means that the model management unit 106 sets the model to unusable.

[0061] In this case, before performing the processing in S901, the recognition unit 105 first performs a first recognition process on the sample image using the first model. The processing parameters used at this time may be parameters that follow the initial settings, or they may be set by the user. After that, the processing in S901 to S905 is performed using the sample image as the first recognition target information. In this way, in S905, a recognition result with a high similarity to the result of the first recognition process using the first model is selected. After that, the output unit 108 can output the settings used to obtain the recognition result selected in S905, and the model management unit 106 can manage these settings in association with the identification information of the first model. For example, the model management unit 106 can store similar models and similar parameters used to obtain the recognition result selected in S905 in association with the first model that is to be decommissioned.

[0062] As described above, the model management unit 106 can store the settings output by the output unit 108 in association with the identification information of the first model when the first model is made unavailable.

[0063] Thus, when the model management unit 106 manages similar models and similar parameters associated with the first model, the recognition process according to Figure 3 can be performed as follows. That is, instead of performing the processes in S306 to S308, the output unit 108 can refer to the model management unit 106 and output the similar models and similar parameters associated with the first model used in the first recognition process selected in S305.

[0064] Furthermore, as shown in Figure 10, if the model management unit 106 manages model classification information such as the model's recognition target or lineage, sample images may be prepared for each model classification defined by the recognition target or lineage. In this case, in S902, the recognition unit 105 can refer to the model management unit 106 and obtain a sample image corresponding to the first model classification.

[0065] The recognition device described above may be composed of multiple devices. For example, the recognition device according to one embodiment may be composed of multiple information processing devices connected via a network. In particular, if the recognition device 101 is a server that receives requests from a user terminal, the functions of the recognition unit 105 may be executed by another server. With such a configuration, even if the processing of the recognition unit 105 takes time, the processing of the recognition unit 105 can be performed asynchronously with respect to the request. Furthermore, although the functions of the information processing device shown in Figure 1 can be realized by a computer, some or all of the functions of the information processing device may be realized by dedicated hardware.

[0066] Furthermore, the recognition unit 105 can take various forms, such as a library within the recognition device 101, or a server or cloud service separate from the recognition device 101.

[0067] (Other examples) The present invention can also be realized by supplying a program that implements one or more of the functions of the above-described embodiments to a system or device via a network or storage medium, and by having one or more processors in the computer of that system or device read and execute the program. It can also be realized by a circuit (e.g., an ASIC) that implements one or more functions.

[0068] The invention is not limited to the embodiments described above, and various modifications and variations are possible without departing from the spirit and scope of the invention. Accordingly, claims are attached to disclose the scope of the invention. [Explanation of symbols]

[0069] 101: Recognition device, 104: Information input unit, 105: Recognition unit, 106: Model management unit, 107: Setting unit, 108: Output unit, 120: Search unit, 121: Judgment unit, 122: History management unit

Claims

1. An information processing device that displays the results of a recognition process on a display device, An acquisition means for acquiring the result of a first recognition process performed on a first recognition target information using a first model, Display means for displaying on the display device the result of the first recognition process, the result of a second recognition process performed on the first recognition target information using a second model different from the first model, information indicating that the result of the first recognition process is due to the first model, and information indicating that the result of the second recognition process is due to the second model. An information processing device characterized by comprising:

2. The information processing apparatus according to claim 1, characterized in that it displays on the display device the result of recognizing the deformation that occurred in the structure in the image as a result of the recognition process.

3. The aforementioned display means is Information indicating the first setting when the first model performs the first recognition process, Information indicating the second setting when the second model performs the second recognition process, The information processing apparatus according to claim 1 or 2, characterized in that it displays the information on the display device.

4. The information processing apparatus according to any one of claims 1 to 3, characterized in that the display means causes the display device to display information indicating that the result of the second recognition process is similar to the result of the first recognition process.

5. The information processing apparatus according to any one of claims 1 to 4, characterized in that the display means causes the display device to display information indicating that the first model has been discontinued.

6. The information processing apparatus according to claim 5, characterized in that the display means causes the display device to display information indicating whether or not to search for a model and setting similar to the result of the first recognition process.

7. An information processing method performed by an information processing device that displays the results of a recognition process on a display device, A step of obtaining the result of a first recognition process performed on a first recognition target information using a first model, A step of displaying on the display device the result of the first recognition process, the result of a second recognition process performed on the first recognition target information using a second model different from the first model, information indicating that the result of the first recognition process is due to the first model, and information indicating that the result of the second recognition process is due to the second model. An information processing method characterized by having the following features.

8. A program for causing a computer to function as an information processing device according to any one of claims 1 to 6.

Images