Information processing device, information processing method, and information processing program

Abstract

The invention discloses an information processing apparatus, an information processing method, and an information processing program. The information processing device acquires a transformation parameter including the irradiation direction in the configuration information, and uses the transformation parameter to transform the position of the defect of the object to be inspected in the inspection image to the position in the configuration information. The conversion parameter is used for converting a position in an inspection image captured by irradiating a subject to be inspected with radiation along an irradiation direction into a position of structure information representing a three-dimensional structure of the subject to be inspected.

Description

Technical Field

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

[0002] Japanese Patent Publication No. 2007-192818 discloses the following technology: in non-destructive inspection of parts, a point cloud is extracted from a three-dimensional image generated by using a plurality of tomographic images of the part obtained by taking a CT (Computed Tomography) device, and the extracted point cloud is registered in a CAD (Computer Aided Design) coordinate system. Summary of the invention

[0003] Technical issues to be solved by the invention

[0004] In non-destructive inspection, it is preferable to associate information about defects in a two-dimensional inspection image captured by irradiating the inspection object with the position of the defect in the three-dimensional structure of the inspection object. This is because by comparing the shape and texture information of the defect in the two-dimensional inspection image with the position of the defect in the three-dimensional structure of the inspection object, the inspection efficiency can be improved.

[0005] In the technology of specifying the three-dimensional position of a defect from a three-dimensional image generated using multiple tomographic images, the cost of imaging equipment such as CT equipment is high, and the imaging of multiple tomographic images takes a relatively long time. Therefore, there is room for improvement from the perspective of inspection efficiency of non-destructive inspection.

[0006] The present invention has been made in view of the above circumstances, and an object of the present invention is to provide an information processing device, an information processing method, and an information processing program that can improve the inspection efficiency of non-destructive inspection.

[0007] Means for solving technical problems

[0008] The first method is an information processing device comprising at least one processor, wherein the processor obtains transformation parameters and uses the transformation parameters to transform the position of a defect of an inspection object in an inspection image into a position in structural information, wherein the transformation parameters are used to transform the position in an inspection image captured by irradiating the inspection object with radiation along an irradiation direction into the position of structural information representing the three-dimensional structure of the inspection object, and the transformation parameters include the irradiation direction in the structural information.

[0009] The information processing device of the second mode is based on the information processing device of the first mode, wherein the processor derives the depth of the defect along the irradiation direction based on the inspection image, and derives a position that is an amount of distance from the surface of the inspection object in the structural information away from the depth derived along the irradiation direction as the position of the defect in the structural information.

[0010] The information processing apparatus of a third aspect is the information processing apparatus of the second aspect, wherein the processor derives the depth of the defect based on the degree of blurring of the defective region in the inspection image.

[0011] The information processing device of the fourth mode is based on the information processing device of the first mode, wherein a plurality of inspection images are taken from a plurality of different irradiation directions, and the processor uses transformation parameters to transform the position of the defect of each of the plurality of inspection images into the position of the structural information in the plane when the irradiation direction is used as the viewpoint direction, and derives the intersection of a plurality of straight lines along the irradiation direction that pass through the position of the transformed defect for each of the plurality of inspection images as the position of the defect in the structural information.

[0012] The information processing device of a fifth aspect is the information processing device of any one of the first aspect to the fourth aspect, wherein the processor integrates the structural information and the position of the defect in the structural information as data.

[0013] The sixth method is an information processing method, wherein a processor of an information processing device performs the following processing: obtaining transformation parameters, and using the transformation parameters to transform the position of a defect of an inspection object in an inspection image into a position in structural information, wherein the transformation parameters are used to transform the position in an inspection image captured by irradiating the inspection object along an irradiation direction with radiation into the position of structural information representing the three-dimensional structure of the inspection object.

[0014] The seventh method is an information processing program, which is used to cause a processor of an information processing device to perform the following processing: obtaining transformation parameters, and using the transformation parameters to transform the position of a defect of an inspection object in an inspection image into a position in structural information, wherein the transformation parameters are used to transform the position in an inspection image captured by irradiating the inspection object with radiation along an irradiation direction into the position of structural information representing the three-dimensional structure of the inspection object, and the transformation parameters include the irradiation direction in the structural information.

[0015] Effects of the Invention

[0016] According to the present invention, the inspection efficiency of non-destructive inspection can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1This is a block diagram showing a schematic configuration of a radiation imaging device.

[0018] Figure 2 This is a block diagram showing an example of the hardware configuration of the information processing device.

[0019] Figure 3 A diagram for explaining structural information.

[0020] Figure 4 This is a diagram for explaining the learned model.

[0021] Figure 5 This is a block diagram showing an example of the functional structure of the information processing device.

[0022] Figure 6 This is a diagram for explaining the derivation process of the irradiation direction.

[0023] Figure 7 This is a diagram for explaining the process of deriving the position of a defect in the structural information.

[0024] Figure 8 This is a diagram for explaining the relationship between the depth of a defect and the degree of blurring of the defect region in an inspection image.

[0025] Fig. 9 This is a diagram for explaining a process of deriving a defect position based on a plurality of inspection images.

[0026] Fig.10 This is a flowchart showing an example of defect position transformation processing.

[0027] Fig.11 This is a diagram showing an example of the irradiation direction of a modification. DETAILED DESCRIPTION

[0028] Hereinafter, examples of modes for implementing the technology of the present invention will be described in detail with reference to the drawings.

[0029] First, refer to Figure 1 The structure of the radiation imaging device 1 of this embodiment is described. The radiation imaging device 1 is used for non-destructive inspection of an inspection object. Figure 1 As shown, the radiation imaging device 1 includes an information processing device 10, a radiation source 12, and a radiation detector 14. The information processing device 10, the radiation source 12, and the radiation detector 14 are connected to each other so as to be able to communicate with each other. The information processing device 10 is, for example, a computer such as a personal computer or a server computer.

[0030] The radiation source 12 irradiates radiation R such as X-rays to the inspection object O. The radiation source 12 of the present embodiment irradiates the radiation R in a cone beam. The direction from the radiation source 12 to a point on the radiation detector 14 where the radiation R that has passed through the inspection object O arrives is referred to as "irradiation direction D". In the present embodiment, a case where the direction from the radiation source 12 to a point on the radiation detector 14 where the radiation R that has passed through the center of the inspection object O arrives is set as the irradiation direction D is described as an example.

[0031] The radiation detector 14 includes a flash as an example of a light-emitting layer that emits light by irradiating radiation R, and a TFT (Thin Film Transistor) substrate. The flash and the TFT substrate are stacked. The TFT substrate has a plurality of pixels arranged in a two-dimensional shape, and each pixel has a sensor unit and a thin film field effect transistor as an example of a conversion element whose generated charge increases as the amount of irradiated radiation increases. The sensor unit absorbs the light emitted by the flash to generate charge and accumulates the generated charge. The thin film field effect transistor converts the charge accumulated in the sensor unit into an electrical signal and outputs it. Through the above structure, the radiation detector 14 generates a two-dimensional radiation image corresponding to the radiation R irradiated from the radiation source 12 to the inspection object O, and outputs the generated radiation image to the information processing device 10.

[0032] Thus, in the radiation imaging device 1, a radiation image captured by irradiating the inspection object O with radiation R from the radiation source 12 along the irradiation direction D is stored in the information processing device 10. Hereinafter, a radiation image captured by irradiating the inspection object O with radiation R along the irradiation direction D is referred to as an "inspection image."

[0033] Next, refer to Figure 2 , the hardware structure of the information processing device 10 of this embodiment is described. Figure 2 As shown, the information processing device 10 includes a CPU (Central Processing Unit) 20, a memory 21 as a temporary storage area, and a non-volatile storage unit 22. In addition, the information processing device 10 includes a display 23 such as a liquid crystal display, an input device 24 such as a keyboard and a mouse, and a network I / F (InterFace) 25 connected to a network. In addition, the information processing device 10 includes an external I / F 26 connected to the radiation source 12 and the radiation detector 14. The CPU 20, the memory 21, the storage unit 22, the display 23, the input device 24, the network I / F 25, and the external I / F 26 are connected to the bus 27. The CPU 20 is an example of a processor related to the technology of the invention.

[0034] The storage unit 22 is implemented by a HDD (Hard Disk Drive), an SSD (Solid State Drive), or a flash memory. The storage unit 22 as a storage medium stores an information processing program 30. The CPU 20 reads the information processing program 30 from the storage unit 22, expands it into the memory 21, and executes the expanded information processing program 30.

[0035] In addition, the storage unit 22 stores an inspection image, structure information 32, and a learned model 34. The structure information 32 includes information indicating the three-dimensional structure of the inspection object O. Figure 3 As shown in FIG. 1 , the structure information 32 of the present embodiment is information used when displaying a virtual inspection object O on the display 23, and is information expressing the three-dimensional structure of the inspection object O using coordinates of a rectangular coordinate system consisting of three axes: the X-axis, the Y-axis, and the Z-axis. In addition, the structure information 32 also includes the material of each component constituting the inspection object O. The transmittance of the radiation R of the component is specified based on the material of the component. As an example of the structure information 32, design information such as CAD data can be cited.

[0036] like Figure 4 As shown, the learned model 34 is a learned model that takes the inspection image as input and takes the information related to the defects of the inspection object O in the input inspection image as output, and is a learned model that uses multiple sets of inspection images and the information related to the defects of the inspection object O in the inspection images as learning data (sometimes also referred to as supervision data) for learning. Examples of information related to defects include the position of the defect in the inspection image, the size of the defect, and the shape of the defect. In this embodiment, the position of the defect in the inspection image is represented by the coordinates of a rectangular coordinate system composed of two axes, the X-axis and the Y-axis, with a specific point (for example, the point in the upper left corner) of the two-dimensional inspection image as the origin. In addition, the "defect" in this specification is defined as a term for non-destructive inspection, and refers to discontinuous parts such as bubbles, foreign matter, and cracks.

[0037] Next, refer to Figure 5 , the functional structure of the information processing device 10 of this embodiment is described. Figure 5 As shown, the information processing device 10 includes a detection unit 40, a first derivation unit 42, a second derivation unit 44, a generation unit 46, and a display control unit 48. The CPU 20 executes the information processing program 30 to function as the detection unit 40, the first derivation unit 42, the second derivation unit 44, the generation unit 46, and the display control unit 48.

[0038] The detection unit 40 detects defects of the inspection object O in the inspection image based on the inspection image stored in the storage unit 22 and the learned model 34. Specifically, the detection unit 40 inputs the inspection image to the learned model 34. The learned model 34 outputs information related to the defects of the inspection object O corresponding to the input inspection image. Thus, the detection unit 40 detects defects of the inspection object O in the inspection image.

[0039] The detection unit 40 may detect defects of the inspection object O in the inspection image using a known detection algorithm. The defects of the inspection object O in the inspection image may also be specified by the user via the input device 24. In this case, the detection unit 40 detects the defects specified by the user.

[0040] The first deriving unit 42 derives a transformation parameter for transforming a position in a two-dimensional inspection image into a position of the three-dimensional structure information 32, and the transformation parameter includes an irradiation direction D in the structure information 32. Figure 6 , a specific example of the derivation process of the irradiation direction D in the structural information 32 performed by the first derivation unit 42 is described.

[0041] like Figure 6 As shown on the right side of FIG. 1 , a two-dimensional inspection image is obtained by irradiating the inspection object O with radiation R from the radiation source 12 along the irradiation direction D. Figure 6 As shown on the left side of , the first derivation unit 42 generates a two-dimensional simulated image by projecting the inspection object O along the viewpoint direction when the virtual inspection object O is displayed on the display 23 based on the structure information 32. The viewpoint direction is the direction in which the surface of the inspection object O becomes the front of the display screen when the virtual inspection object O is observed along this direction. Figure 6 The example on the left shows the generation of Figure 6 , that is, an example of a simulated image when observing a virtual inspection object O based on the structure information 32 in the direction of arrow A. For example, the viewpoint direction is represented by the coordinates of a point, and the direction from the coordinates through the origin is the viewpoint direction.

[0042] The first deriving unit 42 generates simulation images for different multiple viewpoint directions. In addition, the first deriving unit 42 derives the similarity between each generated simulation image and the inspection image. Specifically, for example, the first deriving unit 42 derives the similarity between the contour of the inspection object O in the simulation image and the contour of the inspection object O in the inspection image. In addition, the first deriving unit 42 may also extract the contour line of the inspection object O in the simulation image and the contour line of the inspection object O in the inspection image, respectively, and derive the similarity of the outer shape of the inspection object O formed by the extracted contour lines.

[0043] Then, the first derivation unit 42 sets the viewpoint direction of the simulated image having the highest similarity to the inspection image as the irradiation direction D in the structure information 32 .

[0044] The second derivation unit 44 uses the irradiation direction D derived by the first derivation unit 42 to transform the position of the defect of the inspection object O in the inspection image detected by the detection unit 40 into the position of the defect in the structural information 32, thereby deriving the three-dimensional coordinates of the defect in the structural information 32. In addition, the second derivation unit 44 may acquire the irradiation direction D derived by the external device via the network I / F 25 instead of the first derivation unit 42.

[0045] Specifically, first, the second derivation unit 44 transforms the position of the defect of the inspection object O in the inspection image into the position of the structural information 32 in the plane when the irradiation direction D is set as the viewpoint direction. For example, the second derivation unit 44 can perform the above-mentioned transformation by matching the scale of the outer shape of the inspection object O in the inspection image and the outer shape of the virtual inspection object O observed from the irradiation direction D in the structural information 32.

[0046] In this way, the position of the defect of the inspection object O in the plane when the virtual inspection object O is observed from the irradiation direction D in the structure information 32 can be obtained. Figure 7 As shown, as long as the depth L of the defect along the irradiation direction D can be obtained, the three-dimensional coordinates of the defect in the structural information 32 can be obtained.

[0047] The second derivation unit 44 of this embodiment derives the depth of the defect along the irradiation direction D based on one inspection image. Figure 8 As shown, the smaller the depth of the defect along the irradiation direction D, that is, the farther the defect is from the radiation detector 14, the greater the blurriness of the defect region in the inspection image. This is because the farther the defect is from the radiation detector 14, the more easily it is affected by scattered rays. Therefore, the second derivation unit 44 derives the depth of the defect along the irradiation direction D based on the blurriness of the defect region in the inspection image. Specifically, the greater the blurriness of the defect region in the inspection image, the greater the value that the second derivation unit 44 derives the depth of the defect along the irradiation direction D. Furthermore, the second derivation unit 44 derives a position that is away from the position corresponding to the surface of the inspection object O in the structural information 32 by the amount of the depth derived along the irradiation direction D as the position of the defect in the structural information.

[0048] Through the above-described processing, the second derivation unit 44 can convert the position of the defect of the inspection object O in the two-dimensional inspection image into the three-dimensional coordinates in the structural information 32 .

[0049] Furthermore, the second derivation unit 44 may also transform the position of the defect of the inspection object O in the inspection image into the position of the defect in the structural information 32 based on the plurality of inspection images captured from the different plurality of irradiation directions D. In this case, the second derivation unit 44 uses the irradiation direction D derived by the first derivation unit 42 to transform the position of the defect in each of the plurality of inspection images into the position of the structural information 32 in the plane when the irradiation direction D is set as the viewpoint direction. Fig. 9 As shown, the second deriving unit 44 derives the intersection point P of a plurality of straight lines passing through the position of the defect after the transformation for each of the plurality of inspection images and respectively along the irradiation direction D as the position of the defect in the structural information 32. Fig. 9 , an example is shown when there are two inspection images.

[0050] The generator 46 generates data integrating the structural information 32 and the position of the defect in the structural information 32 derived by the second deriving unit 44. For example, the generator 46 generates data including the position of the defect in the structural information 32 derived by the second deriving unit 44 in the attributes of the data file representing the structural information 32.

[0051] The display control unit 48 controls the display 23 to display a virtual inspection object O and an object indicating a defect based on the data generated by the generating unit 46. The object indicating a defect may be a mark such as a circular mark or an image of a defective area in the inspection image.

[0052] Next, refer to Fig.10 The function of the information processing device 10 of this embodiment is described. The CPU 20 executes the information processing program 30, Fig.10 Defect position transformation processing shown. Fig.10 The defect position conversion process shown is executed when, for example, a user inputs an instruction to start the execution.

[0053] exist Fig.10 In step S10, as described above, the detection unit 40 detects defects of the inspection object O in the inspection image based on the inspection image stored in the storage unit 22 and the learned model 34. In step S12, as described above, the first deriving unit 42 derives transformation parameters for transforming the position in the two-dimensional inspection image into the position of the three-dimensional structure information 32, and the transformation parameters include the irradiation direction D in the structure information 32.

[0054] In step S14 , as described above, the second derivation unit 44 converts the position of the defect of the inspection object O in the inspection image detected in step S10 into the position of the defect in the structural information 32 using the irradiation direction D derived in step S12 .

[0055] In step S16, the generator 46 generates data that integrates the structural information 32 and the position of the defect in the structural information 32 derived in step S14. In step S18, the display controller 48 controls the display 23 to display the virtual inspection object O and the object representing the defect based on the data generated in step S16. When the process of step S18 is completed, the defect position conversion process is completed.

[0056] As described above, according to the present embodiment, the position of the defect of the inspection object O can be obtained as a three-dimensional position based solely on the X-ray image rather than the tomographic image such as the CT image. Thus, the user can grasp the position of the defect of the inspection object O as a three-dimensional position. Therefore, according to the present embodiment, the inspection efficiency of the non-destructive inspection can be improved.

[0057] In addition, in the above embodiment, if Fig.11 As shown, when the second deriving unit 44 derives the three-dimensional coordinates of the defect, the irradiation direction D may be set to a direction inclined with respect to the direction from the radiation source 12 toward the center of the inspection object O.

[0058] Furthermore, in the above-described embodiment, the conversion parameters may include, in addition to the irradiation direction D, correction data for correcting the distortion of the inspection image.

[0059] In addition, in the above-mentioned embodiment, for example, various processors as shown below can be used as the hardware structure of the processing unit that performs various processes such as the functional units of the information processing device 10. The various processors mentioned above include, in addition to the general-purpose processor that executes software (programs) and functions as various processing units as described above, CPUs, processors that can change the circuit structure after manufacturing such as FPGA (Field Programmable Gate Array), programmable logic devices (PLD), and ASIC (Application Specific Integrated Circuit), which are processors that have a circuit structure specially designed to perform specific processes, i.e., dedicated circuits.

[0060] One processing unit may be composed of one of these various processors, or a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, a combination of a CPU and an FPGA). In addition, multiple processing units may be composed of one processor.

[0061] As an example of a processor constituting multiple processing units, there is a method, such as a computer such as a client and a server, in which a processor is constituted by a combination of one or more CPUs and software, and the processor functions as multiple processing units. Second, there is a method such as a system on chip (SoC) that uses a processor that implements the functions of the entire system including multiple processing units by using one IC (Integrated Circuit) chip. In this way, various processing units are constituted using one or more of the above-mentioned various processors as a hardware structure.

[0062] Furthermore, as the hardware configuration of these various processors, more specifically, a circuit (circuitry) in which circuit elements such as semiconductor elements are combined can be used.

[0063] In addition, in the above-mentioned embodiment, the information processing program 30 is pre-stored (installed) in the storage unit 22, but the present invention is not limited thereto. The information processing program 30 may also be provided in a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. In addition, the information processing program 30 may also be downloaded from an external device via a network.

[0064] The invention of Japanese Patent Application No. 2022-099870 filed on June 21, 2022 is incorporated herein by reference in its entirety. In addition, all documents, patent applications, and technical specifications described in this specification are incorporated herein by reference to the same extent as if each document, patent application, and technical specification was specifically and individually described.

Claims

1. An information processing device comprising at least one processor, wherein: The processor performs the following processing: acquiring a transformation parameter for transforming a position in an inspection image captured by irradiating an inspection object with radiation along an irradiation direction into a position of structural information representing a three-dimensional structure of the inspection object, wherein the transformation parameter includes the irradiation direction in the structural information, The position of the defect of the inspection object in the inspection image is transformed into a position in the structural information using the transformation parameter.

2. The information processing device according to claim 1, wherein: The processor performs the following processing: deriving a depth of the defect along the irradiation direction based on the inspection image, A position that is separated from a position corresponding to the surface of the inspection object in the structural information by the depth derived along the irradiation direction is derived as a position of a defect in the structural information.

3. The information processing device according to claim 2, wherein: The processor derives a depth of the defect based on a degree of blurriness of a region of the defect in the inspection image.

4. The information processing device according to claim 1, wherein: Taking a plurality of inspection images from a plurality of different irradiation directions, The processor performs the following processing: using the transformation parameters, transforming the position of the defect in each of the plurality of inspection images into the position of the structural information in a plane when the irradiation direction is set as a viewpoint direction; Intersection points of a plurality of straight lines respectively along the irradiation direction that pass through the position of the defect after the transformation for each of the plurality of inspection images are derived as the position of the defect in the structural information.

5. The information processing device according to any one of claims 1 to 4, wherein: The processor integrates the structural information and the position of the defect in the structural information as data.

6. An information processing method, wherein: The processor included in the information processing device executes the following processing: acquiring a transformation parameter for transforming a position in an inspection image captured by irradiating an inspection object with radiation along an irradiation direction into a position of structural information representing a three-dimensional structure of the inspection object, wherein the transformation parameter includes the irradiation direction in the structural information, The position of the defect of the inspection object in the inspection image is transformed into a position in the structural information using the transformation parameter.

7. An information processing program, wherein: It is used to enable the processor of the information processing device to perform the following processing: acquiring a transformation parameter for transforming a position in an inspection image captured by irradiating an inspection object with radiation along an irradiation direction into a position of structural information representing a three-dimensional structure of the inspection object, wherein the transformation parameter includes the irradiation direction in the structural information, The position of the defect of the inspection object in the inspection image is transformed into a position in the structural information using the transformation parameter.

Images