Image generation device, image generation method, and program

Abstract

An image generating device, an image generating method, and a program that can shorten the overall time required for inspection. [Solution] The image generating device of the present disclosure comprises an acquisition unit that acquires inspection data of an object to be inspected using an ultrasonic flaw detection inspection device; an image generating unit that generates an image that represents the intensity of an echo wave by changes in the color of two-dimensional pixels based on the inspection data; an interpolation unit that performs frame interpolation on images before and after an image without defects to generate an intermediate image that shows an image halfway between the images before and after; a filter unit that uses a low-pass filter on the intermediate image generated by the interpolation unit to smooth out sudden changes in brightness in the intermediate image; and a merging unit that integrates multiple images generated by the interpolation unit to generate a single merged image.

Description

[Technical Field]

[0001] The present disclosure relates to an image generation device, an image generation method, and a program. [Background technology]

[0002] In ultrasonic flaw detection, when there are many inspection points, inspection engineers inspect all of the inspection points to detect defects. However, this requires a lot of work time and there is a possibility of misjudgment, so there is a need to automate the acquisition of inspection data and the subsequent defect sorting.

[0003] For example, Patent Document 1 listed below discloses a three-dimensional defect inspection device for a water turbine structure, which includes a flaw detection means that transmits ultrasonic pulses to the stage and receives echoes in response to the operation of an ultrasonic probe, a three-dimensional defect calculation means that calculates the three-dimensional position and defect size of a defect in the stage based on each contact position of the ultrasonic probe in the stage, echo reception information, and the three-dimensional shape measured by a three-dimensional shape measurement means, and a display means that displays the calculated three-dimensional defect in a three-dimensional graphic. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-145298 Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional automatic defect detection methods such as those described in Patent Document 1 determine the presence or absence of defects using a single image. Therefore, to avoid overlooking defects, the defect detection threshold is lowered to determine the presence or absence of defects. On the other hand, lowering the detection threshold reduces the number of overlooked defects, but increases the number of false detections of defects. This increases the number of reinspections, which poses a problem in that the effect of reducing the overall time required for inspection through automation cannot be achieved.

[0006] In view of the above-mentioned problems, the present disclosure aims to provide an image generating device, an image generating method, and a program that can shorten the overall time required for inspection. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the objectives, the image generating device of the present disclosure comprises an acquisition unit that acquires inspection data of an object to be inspected using an ultrasonic flaw detection inspection device; an image generating unit that generates an image that represents the intensity of an echo wave by changes in the color of two-dimensional pixels based on the inspection data; an interpolation unit that uses frame interpolation on a predetermined number of images before and after an image that includes a defect to generate an intermediate image that shows an intermediate image between the previous and next images; a filter unit that uses a low-pass filter on the intermediate images generated by the interpolation unit to smooth out sudden changes in brightness in the intermediate images; and a merging unit that integrates multiple intermediate images after processing by the filter unit to generate a single merged image.

[0008] In order to solve the above-mentioned problems and achieve the objectives, the image generation method of the present disclosure includes the steps of acquiring inspection data of an object to be inspected using an ultrasonic flaw detection inspection device, generating an image based on the inspection data that represents the intensity of echo waves by changes in the color of two-dimensional pixels, using frame interpolation on a predetermined number of images before and after an image containing a defect to generate an intermediate image that represents an intermediate image between the images before and after the defect, using a low-pass filter to smooth out sudden changes in brightness in the generated intermediate image, and integrating the multiple intermediate images after processing using the low-pass filter to generate a single merged image.

[0009] In order to solve the above-mentioned problems and achieve the objectives, the program disclosed herein causes a computer to perform the following steps: acquiring inspection data of an object to be inspected using an ultrasonic flaw detection device; generating an image based on the inspection data that represents the intensity of echo waves through changes in the color of two-dimensional pixels; using frame interpolation on a predetermined number of images before and after an image containing a defect to generate an intermediate image that represents an intermediate image between the images before and after the defect; using a low-pass filter on the generated intermediate image to smooth out sudden changes in brightness in the intermediate image; and integrating the multiple intermediate images after processing using the low-pass filter to generate a single merged image. [Effects of the Invention]

[0010] According to the present disclosure, it is possible to provide an image generating device, an image generating method, and a program that can shorten the overall time required for inspection. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram for explaining an overview of ultrasonic flaw detection. [Figure 2] FIG. 2 is a diagram illustrating an example configuration of an image generation system according to the present disclosure. [Figure 3]FIG. 3 is a diagram illustrating an example of the configuration of an image generating device according to the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in the inspection data storage unit of the image generating device according to the present disclosure. [Figure 5] FIG. 5 is a diagram illustrating an example of information stored in a model storage unit of the image generating device according to the present disclosure. [Figure 6] FIG. 6 is a diagram illustrating an example of an image generated by the image generating device according to the present disclosure. [Figure 7] FIG. 7 is a diagram showing an example of a plurality of images generated by an image generating device according to the present disclosure at different inspection locations. [Figure 8] FIG. 8 is a diagram illustrating the processing of the interpolation unit in the image generating device according to the present disclosure. [Figure 9] FIG. 9 is a diagram illustrating the image generation process performed by the image generation device according to the present disclosure. [Figure 10] FIG. 10 is a diagram showing an example of the configuration of an ultrasonic flaw detection inspection device according to the present disclosure. [Figure 11] FIG. 11 is a flowchart showing the flow of an inspection process using an image generating device according to the present disclosure. [Figure 12] FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the image generating device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. However, the present disclosure is not limited to the embodiments described below.

[0013] (Overview of ultrasonic flaw detection) First, an overview of ultrasonic flaw detection will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining the overview of ultrasonic flaw detection. As shown in Fig. 1, in ultrasonic flaw detection, for example, ultrasonic waves are emitted from an ultrasonic flaw detection device 200 to an inspection object TP having a weld W, echo waves are received from the inspection object TP, and the echo waves are analyzed to detect defects (voids, cracks, etc.). Note that the inspection object TP is not limited to one having a weld W, and may be a pipe in a thermal power plant, a composite material component of an aircraft, or the like.

[0014] The ultrasonic flaw detection inspection device 200 transmits ultrasonic waves using a probe capable of scanning the object of inspection in a plane, and acquires ultrasonic echo waves at each scanning position. The image generation device 100 acquires inspection data, which is the echo waves, from the ultrasonic flaw detection inspection device 200, and generates a two-dimensional image in which the height (intensity, amplitude) of the echo waves is the brightness value of each pixel. As a result, if a defect exists in the object of inspection, it will be possible to detect the defect because there will be areas where the intensity of the echo waves is high other than on the surface and the opposite side.

[0015] (Image generation system configuration) Next, the configuration of an image generation system 1 according to the present disclosure will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example configuration of an image generation system according to the present disclosure. As shown in Fig. 2, the image generation system 1 according to the present disclosure includes an image generation device 100, an ultrasonic flaw detection inspection device 200, and a network N. Below, these components will be briefly described in order.

[0016] The image generating device 100 is an information processing device that generates an image showing an inspection result based on inspection data obtained by the ultrasonic flaw detection inspection device 200. The image generating device 100 may be realized by various information processing devices, and is realized by a computer such as a PC (Personal Computer) or a WS (Work Station), for example.

[0017] The ultrasonic flaw detection inspection device 200 is a device that performs ultrasonic flaw detection on an inspection object. The ultrasonic flaw detection inspection device 200 transmits ultrasonic waves to the inspection object using a probe that can scan in a plane, and acquires ultrasonic echo waves from the inspection object. The inspection data acquired by the ultrasonic flaw detection inspection device 200 is acquired by the image generation device 100 via the network N.

[0018] The network N is responsible for exchanging information between the image generating device 100 and the ultrasonic flaw detection device 200. The network N may be realized wirelessly or wired. If it is wired, it may be realized by a wired LAN (Local Area Network) or a USB (Universal Serial Bus) cable. If it is wireless, it may be realized by a wireless LAN defined in IEEE802.11. If security is important, it may be realized by a VPN (Virtual Private Network).

[0019] As described above, the image generation system 1 functions as a single system by the image generation device 100 and the ultrasonic flaw detection inspection device 200 exchanging information via the network N and each performing information processing.

[0020] (Configuration of image generating device) Next, the configuration of an image generating device according to the present disclosure will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example configuration of an image generating device according to the present disclosure. As shown in Fig. 3, an image generating device 100 according to the present disclosure includes a communication unit 110, a storage unit 120, a control unit 130, an input unit 140, and a display unit 150. These components will be described in order below.

[0021] The communication unit 110 is responsible for transmitting and receiving various types of information to and from external devices via wired or wireless connections. In the wired case, it may be realized by a NIC (Network Interface Card) equipped with various interfaces such as a wired LAN terminal or a USB terminal. In the wireless case, it may be realized by an antenna for transmitting and receiving radio waves such as a wireless LAN, Bluetooth (registered trademark), or Wi-Fi (registered trademark).

[0022] The storage unit 120 is a storage device that stores various types of information. The storage unit 120 includes a main storage device and an auxiliary storage device. The main storage device may be realized by a semiconductor memory element such as a random access memory (RAM), a read only memory (ROM), or a flash memory. The auxiliary storage device may be realized by a hard disk or a solid state drive (SSD), for example.

[0023] The inspection data storage unit 121 stores information related to inspection data of ultrasonic flaw detection inspection. An example of the information stored in the inspection data storage unit 121 will now be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the information stored in the inspection data storage unit of the image generating device according to the present disclosure.

[0024] As shown in FIG. 4, the test data storage unit 121 stores information relating to the items "test data ID," "position data," "acoustic intensity data," and "reception time data."

[0025] The "test data ID" is an identifier that identifies the test data and is expressed by a character string, a number, or the like. The "position data" is information that indicates the position where the test data identified by the "test data ID" was acquired, and may be expressed, for example, by two-dimensional X-coordinate and Y-coordinate values. The "acoustic intensity data" is information that indicates the acoustic intensity, or in other words, the amplitude, of the echo signal at the position indicated by the "position data" of the test data identified by the "test data ID." The "reception time data" is information that indicates the time from when an ultrasonic wave is emitted from the probe to when the echo wave is received.

[0026] That is, in Figure 4, the location where the test data identified by the test data ID "DTID#1" was acquired is the location data "LC#1", the acoustic intensity of the test data is "STG#1", and the reception time is the reception time data "TM#1".

[0027] The information stored in the test data storage unit 121 is not limited to information relating to the items "test data ID," "position data," "acoustic intensity data," and "reception time data," and any other information relating to test data may be stored. Furthermore, the structure of the information stored in the test data storage unit 121 is not limited to the structure described above, and the information may be stored in any other structure.

[0028] The model storage unit 122 stores information related to a machine learning model used for frame interpolation. An example of the information stored in the model storage unit 122 will now be described with reference to Fig. 5. Fig. 5 is a diagram illustrating an example of the information stored in the model storage unit of the image generating device according to the present disclosure.

[0029] As shown in FIG. 5, the model storage unit 122 stores information relating to the items "model ID" and "model data".

[0030] A "model ID" is an identifier that identifies a machine learning model and is represented by a string or number. "Model data" is data for the machine learning model identified by the "model ID." The machine learning model may be configured using a deep neural network (DNN), a convolutional neural network (CNN), or the like. "Model data" includes various information, such as connection information about how nodes included in each of the multiple layers that make up the neural network are connected to each other, and connection coefficients that are multiplied by numerical values ​​input and output between connected nodes.

[0031] That is, FIG. 5 shows an example in which model data "MDDT#1" of a model identified by a model ID "MDID#1" is stored.

[0032] Note that the information stored in the model storage unit 122 is not limited to information relating to the items "model ID" and "model data", and may store information relating to any other machine learning model.

[0033] The control unit 130 is a controller that executes various types of arithmetic processing and processing that realizes functions. The control unit 130 is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in the storage unit 120 using RAM as a work area. The control unit 130 may also be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0034] As shown in Fig. 5, the control unit 130 includes an acquisition unit 131, an image generation unit 132, an interpolation unit 133, a filter unit 134, and a merge unit 135 as functions realized by the execution of a program stored in the storage unit 120, a circuit configuration, and the like. The control unit 130 realizes these functions and executes these processes by reading and executing a program (software) from the storage unit 120. Note that the control unit 130 may execute these processes using one CPU, or may be equipped with multiple CPUs and execute these processes in parallel. The processes executed by these units will be described in order below.

[0035] The acquiring unit 131 acquires inspection data of an object to be inspected by the ultrasonic flaw detection inspection device 200. For example, the acquiring unit 131 may acquire the inspection data from the ultrasonic flaw detection inspection device 200 via the communication unit 110 and the network N. The acquiring unit 131 may also acquire the inspection data from an external storage medium connected to the communication unit 110. After acquiring the inspection data, the acquiring unit 131 stores the acquired inspection data in the inspection data storage unit 121.

[0036] The image generation unit 132 generates an image representing the inspection results of the ultrasonic flaw detection inspection based on the inspection data. Specifically, the image generation unit 132 generates an image called a B-scan image. The B-scan image displays the inspection data in two dimensions as a vertical cross-sectional view of the inspection object. The B-scan image represents the amplitude of the echo wave signal at the scanning position of the inspection object with color, and displays it mapped to each XY position.

[0037] Here, a B-scan image will be described with reference to FIG. 6. FIG. 6 is a diagram showing an example of an image generated by an image generation device according to the present disclosure. The B-scan image shown in FIG. 6 is an image generated by scanning a probe and using inspection data obtained for each probe scan. In the B-scan image shown in FIG. 6, the amplitude of the echo wave is expressed by a grayscale, but in an actual B-scan image, the areas with the largest amplitude of the echo wave signal are represented in the order of white, blue, yellow, and red. If a defect is present in the area inspected by the probe, the amplitude of the echo wave will be larger than in the surrounding area, allowing the presence or absence of a defect to be determined.

[0038] However, due to noise, such as echo waves inside healthy parts of the inspection target that are not defects, the signal-to-noise (SN) ratio between the echo waves from the defective part of the inspection target and the echo waves from healthy parts can be quite low, and a single B-scan image may not provide enough information to determine whether a defect exists. For this reason, as shown in Figure 7, the inspection technician scans the inspection target with a probe and makes a judgment while checking the image that changes as the probe scans. Figure 7 is a diagram showing an example of multiple images generated at different inspection locations by an image generation device according to the present disclosure. Figure 7 shows B-scan images generated based on inspection data from multiple different inspection locations along the probe scan, arranged in order from left to right.

[0039] Inspection engineers may be unable to distinguish between defect D in generated image IMG2 shown in FIG. 7 and the false defects PD1, PD2, PD3, and PD4, which are healthy areas in generated image IMG3 shown to the right of it. Furthermore, the inspection area in the generated image shown in FIG. 7 has a different shape for each generated image because the probe contact varies at each scanning position due to the inconsistent surface shape of the weld. This requires the inspection engineer to exercise a high level of judgment to fulfill their responsibility to ensure product safety, which can lead to increased work time. Therefore, an interpolation unit 133, described below, generates an image by interpolating images before and after the image containing the defect, and then subtracts the interpolated image from the image containing the defect to enhance the defect.

[0040] The interpolation unit 133 uses frame interpolation on a predetermined number of images before and after an image containing a defect to generate an intermediate image that shows an intermediate image between the images before and after. Because the generated image containing a defect and the generated images before and after it are similar in parts other than the defect, an inspection engineer can find the defect by comparing the image containing the defect with the images before and after it while scanning with the probe. For this reason, the interpolation unit 133 performs processing to generate an intermediate image from the images before and after the image containing the defect.

[0041] Here, the processing of the interpolation unit 133 will be specifically described with reference to FIG. 8. FIG. 8 is a diagram for explaining the processing of the interpolation unit by the image generating device according to the present disclosure. For example, as shown in FIG. 8, a generated image (F p ) the generated image (F p-1 ) and the generated image immediately after (F p+1 ) and the immediately preceding generated image (F p-1 ) and the generated image immediately after (F p+1 ) corresponding to the intermediate position P of the defect-free generated image (F P ') is generated by interpolation.

[0042] The interpolation unit 133 may generate an interpolated image not only using images before and after an image containing a defect, but also using images spaced a predetermined number of frames before and after the image containing a defect. For example, an intermediate image may be generated using images two frames before and two frames after the image containing a defect, or an intermediate image may be generated using images three frames before and three frames after the image containing a defect. In this way, the predetermined number of frames before and after an image containing a defect may be set arbitrarily. This solves the problem that when images before and after an image containing a defect contain a defect, the intermediate images also contain a defect equivalent, making it impossible to detect the defect.

[0043] The interpolation unit 133 may generate an intermediate image between previous and next images using, for example, FILM (Frame Interpolation for Large Motion), which is a frame interpolation method using machine learning. FILM mainly performs three processes: feature extraction, flow prediction, and fusion. In feature extraction, a convolution filter is used to extract features from the two previous and next images while changing the sizes of the images. In flow prediction, the feature values ​​of an intermediate image between the two previous and next images are predicted based on the difference between the feature values ​​of the two previous and next images for each size. In fusion, a decoder is used to generate an intermediate image between the two previous and next images based on the feature values ​​of the predicted intermediate image. The interpolation unit 133 may also generate intermediate images using various other frame interpolation methods.

[0044] The filter unit 134 uses a low-pass filter on the intermediate image generated by the interpolation unit 133 to smooth out sudden changes in brightness in the intermediate image. A low-pass filter is a filter that blocks signals of high-frequency spatial frequency components in an image and passes signals of low-frequency spatial frequency components. In other words, applying a low-pass filter to the intermediate image in the filter unit 134 can be said to be a process that smooths out sudden changes in brightness in the intermediate image. This makes it possible to reduce noise in the intermediate image.

[0045] The merging unit 135 generates a merged image by integrating multiple images. For example, the merging unit 135 integrates multiple intermediate images generated by the interpolation unit 133 using images spaced a predetermined number of frames apart from each other for an image containing a defect, to generate a single merged image. Such processing by the merging unit 135 will be described with reference to FIG. 9. FIG. 9 is a diagram illustrating the image generation processing performed by the image generating device according to the present disclosure. As shown in FIG. 9, the merging unit 135 uses multiple images with a predetermined number of frames, which indicates the interval between images containing a defect, to generate multiple intermediate images by frame interpolation, and performs processing using a low-pass filter on the multiple intermediate images, thereby averaging the multiple images.

[0046] For example, the merging unit 135 generates a merged image by using an averaging filter to average the multiple intermediate images processed by the filter unit 134. The averaging filter is a filter that smooths an image, and averages pixel values ​​at the same position in the multiple images using a kernel that is a coefficient by which the luminance value of a pixel is multiplied. In other words, the merging unit 135 averages the luminance values ​​of pixels at the same position in the multiple intermediate images using the averaging filter, and outputs the averaged image as a merged image.

[0047] Furthermore, the merging unit 135 may generate a merged image by using an averaging filter in which the same kernel coefficient is assigned to each pixel to average multiple intermediate images processed by the filter unit 134. This makes it possible to remove noise from the intermediate images, thereby making it easier to detect defects.

[0048] The merging unit 135 may generate a merged image by averaging multiple intermediate images processed by the filter unit 134 using a weighted averaging filter in which a different kernel coefficient is assigned to each pixel. For example, in the weighted averaging filter, by setting a large kernel coefficient for pixels in positions where defects are likely to occur, it is possible to make defects easier to detect.

[0049] The enhancement unit 136 performs a process of subtracting the merged image from the image including the defect, thereby enhancing the presence of the defect in the merged image. Here, the process of the enhancement unit 136 will be described again with reference to FIG. 8, which was previously used. As shown in FIG. 8, the interpolation unit 133 subtracts the merged image F p Previous image of F p-1 And the later image F p+1 and are interpolated between frames to obtain intermediate images F p In this case, the enhancement unit 136 enhances the image F p From intermediate image F p By subtracting ', the enhanced image F p -F pAs shown in Figure 8, the enhanced image F p -F p In image ', the presence of defect D is emphasized. This makes it possible to generate an image in which the defect is emphasized, which facilitates the detection of the defect. Note that when performing the process of subtracting the merged image from the image including the defect, the emphasis unit 136 may subtract the merged image multiplied by a predetermined coefficient.

[0050] The input unit 140 receives various types of operation information from an inspection engineer or the like. The input unit 140 may be realized by an input device such as various operation switches, a mouse, a keyboard, or a touch panel. The inspection engineer or the like inputs various types of operation information via the input unit 140 and performs tasks such as analyzing inspection data from ultrasonic flaw detection inspections.

[0051] The display unit 150 displays various types of information. For example, the display unit 150 may display a GUI (Graphical User Interface) for receiving operations related to various processes from an inspection engineer or the like, or an image showing the inspection results of an ultrasonic flaw detection inspection. The display unit 150 may be realized by a liquid crystal display, an organic EL (Electro Luminescence) display, a micro LED (Light Emitting Diode) display, or the like. The display unit 150 may also be realized by a touch panel of various types, such as a capacitive type.

[0052] According to the configuration of image generation device 100 described above, it is possible to generate an image in which defects are highlighted using inspection data. Therefore, the presence or absence of defects can be accurately and easily determined, thereby reducing the number of re-inspections. Therefore, it is possible to provide image generation device 100 that can shorten the overall time required for inspection.

[0053] (Configuration of ultrasonic flaw detection equipment) Next, the configuration of an ultrasonic flaw detection inspection device according to the present disclosure will be described with reference to Fig. 10. Fig. 10 is a diagram showing an example configuration of an ultrasonic flaw detection inspection device according to the present disclosure. As shown in Fig. 10, an ultrasonic flaw detection inspection device 200 according to the present disclosure includes a probe unit 210, a power supply unit 220, a receiving unit 230, a control unit 240, a storage unit 250, and an I / F unit 260. These components will be described in order below.

[0054] The probe unit 210 is a sensor that transmits and receives ultrasonic waves. The probe unit 210 may be realized, for example, by a single-transducer vertical probe in which the transmitting unit and receiving unit are integrated, a two-transducer vertical probe in which the transmitting unit and receiving unit are separated by an acoustic isolation plate, or an angle probe that propagates ultrasonic waves at an angle. The transducer may be realized, for example, by a piezoelectric element. Note that the probe unit 210 may be provided with multiple probes, each of which may transmit and receive ultrasonic waves.

[0055] The power supply unit 220 shares power with each device. The power supply unit 220 may be realized by, for example, a boost circuit and a battery. The boost circuit boosts the battery's power and distributes it to the probe unit 210, the A / D conversion circuit, the memory unit 250, etc. The battery may be realized by, for example, a lithium-ion battery.

[0056] The receiving unit 230 applies a voltage of a pulse waveform to the probe unit 210 to oscillate a pulsed ultrasonic wave, and acquires an echo signal received by the probe unit 210 from the ultrasonic wave transmitted by the probe unit 210. The echo signal received by the receiving unit 230 is converted into a digital signal by an A / D conversion circuit and stored in the storage unit 250.

[0057] The receiving unit 230 sends pulse signals to each probe of the probe unit 210 in a time-division manner. Each probe emits ultrasonic waves toward the object to be inspected and receives the reflected echo waves. The echo signals received by each probe are sequentially received and amplified by the receiving unit 230. The amplified echo signals are converted into digital signals by an A / D conversion circuit and stored in the memory unit 250 together with the position information of the corresponding probe.

[0058] The control unit 240 controls the timing of transmitting pulse signals from the receiving unit 230 and controls the writing of received echo signals to the storage unit 250. The control unit 240 may further control analog-to-digital conversion by an A / D conversion circuit. The control unit 240 may be realized by a CPU, ASIC, FPGA, etc.

[0059] The storage unit 250 is a storage device that stores various types of information. The storage unit 250 may store, for example, echo signals measured by a probe. The storage unit 250 includes a main storage device and an auxiliary storage device. The main storage device may be realized by, for example, a semiconductor memory element such as RAM, ROM, or flash memory. The auxiliary storage device may be realized by, for example, a hard disk or SSD.

[0060] The I / F unit 260 is responsible for exchanging information with external devices. For example, the I / F unit 260 is responsible for sending and receiving test data to and from external devices. The I / F unit 260 is implemented, for example, by a wired or wireless connection. Specifically, if it is wired, it may be realized by a device equipped with a USB terminal or the like. If it is wireless, it may be realized by a wireless LAN or the like.

[0061] According to the configuration of the ultrasonic flaw detection inspection device 200 described above, it is possible to appropriately acquire inspection data from the inspection object and pass the inspection data to the image generation device 100, which analyzes the data. Therefore, it is possible to appropriately fulfill part of the functions of the image generation system 1.

[0062] (Automation of inspection processes) Next, automation of an inspection process using an image generating device 100 according to the present disclosure will be described with reference to FIG. 11. FIG. 11 is a flowchart showing the flow of an inspection process using an image generating device according to the present disclosure. First, an inspection engineer travels from an office to an inspection location where an inspection object is located (step S101). Next, the inspection engineer installs a jig, such as a robot equipped with an ultrasonic flaw detection inspection device 200, on the inspection object (step S102). Next, the inspection engineer acquires inspection data for the Nth location of the inspection object using a robot equipped with an ultrasonic flaw detection inspection device 200 (step S103). Next, the inspection data is acquired from the ultrasonic flaw detection inspection device 200, and the presence or absence of a defect in the Nth location is determined (step S104). If a defect is found in the Nth location (step S104: Yes), the inspection engineer travels from the office to the location where the inspection object is located and performs a detailed reinspection of the inspection object (step S105). Next, the inspection engineer determines whether the inspection of the inspection location is complete by determining whether the presence or absence of a defect can be determined through the reinspection (step S106). If it is determined that the inspection of the inspection area has been completed (step S106: Yes), the inspection ends.

[0063] In addition, if it is determined in step S104 that there is no defect in the Nth location (step S104: No), the process proceeds to step S106, where it is determined whether it can be determined that there is no defect, thereby determining whether inspection of the inspection location has been completed (step S106).

[0064] Furthermore, in step S106, if it is determined that the inspection of the inspection point has not been completed (step S106: No), the inspection engineer returns to step S102 and executes the subsequent steps.

[0065] Furthermore, while an inspection engineer is performing the processes from step S102 to step S103 using a robot or the like and acquiring the inspection data, an automatic analysis is performed on the inspection data of the (N-1)th location in parallel (step S107). The acquired inspection data is acquired by image generation device 100, and the presence or absence of defects is determined in the processes from step S104 onwards.

[0066] In this way, while inspection data is being acquired at the Nth inspection location by, for example, the ultrasonic flaw detection inspection device 200 using a robot, automatic analysis is performed on the inspection data of the N-1th location. If a defect is determined in the automatic inspection, detailed inspection is performed on only that location on the spot, thereby reducing time. This allows for further automation of the inspection process.

[0067] (Hardware configuration) The image generating device 100 according to the above-described embodiment is realized, for example, by a computer 1000 configured as shown in Fig. 12. Fig. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the image generating device according to the present disclosure. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090.

[0068] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device that stores data used by the arithmetic device 1030 for various calculations and various databases, and is realized by a ROM, HDD, flash memory, or the like.

[0069] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, scanner, etc., and is realized by a USB, etc.

[0070] The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

[0071] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0072] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0073] For example, when the computer 1000 functions as the image generating device 100, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 130 of the image generating device 100 by executing a program loaded onto the primary storage device 1040.

[0074] (Composition and Effects) The image generating device 100 according to the first embodiment includes an acquisition unit 131 that acquires inspection data of an object to be inspected by the ultrasonic flaw detection inspection device 200, an image generating unit 132 that generates an image representing the inspection results of the ultrasonic flaw detection inspection based on the inspection data, an interpolation unit 133 that uses frame interpolation on a predetermined number of images before and after an image containing a defect to generate an intermediate image that represents an intermediate image between the previous and next images, a filter unit 134 that uses a low-pass filter on the intermediate image generated by the interpolation unit 133 to smooth out sudden changes in brightness in the intermediate image, and a merging unit 135 that integrates multiple intermediate images after processing by the filter unit 134 to generate a single merged image.

[0075] This configuration allows an intermediate image to be generated using a predetermined number of images before and after an image containing a defect, and noise other than the defect can be removed using a low-pass filter. Therefore, an inspection technician can accurately determine whether or not there is a defect by visually comparing the image containing the defect with the intermediate image. This provides an image generation device 100 that can shorten the overall inspection time.

[0076] The image generating device 100 according to the second embodiment is the image generating device 100 according to the first embodiment, and further includes an enhancement unit 136 that enhances the presence of the defect in the image containing the defect by performing a process of subtracting the merged image from the image containing the defect.

[0077] According to this configuration, by performing a process of subtracting the merged image from the image containing the defect, the presence of the defect in the image containing the defect can be emphasized. Therefore, the presence or absence of the defect can be accurately and easily determined, thereby reducing the number of re-inspections. Therefore, it is possible to provide an image generating device 100 that can shorten the overall time required for inspection.

[0078] The image generating device 100 according to the third embodiment is the image generating device 100 according to the first or second embodiment, and the interpolation section 133 thereof uses FILM (Frame Interpolation for Large Motion) as the inter-frame interpolation method.

[0079] This configuration allows accurate generation of an intermediate image from images before and after an image containing a defect, thereby providing image generation device 100 that can shorten the overall time required for inspection.

[0080] The image generating device 100 according to the fourth aspect is the image generating device 100 according to any one of the first to third aspects, in which the merging unit 135 generates a merged image by using an averaging filter to average multiple intermediate images after processing by the filter unit 134.

[0081] With this configuration, a merged image can be generated by integrating multiple images generated by interpolating images that are spaced apart from each other and that contain defects. Therefore, even if the images before and after a defect contain a defect or pseudo-defect, a defect-free merged image can be generated by integrating multiple images. This allows for accurate and easy determination of the presence or absence of a defect, thereby reducing the number of re-inspections required. Therefore, an image generation device 100 can be provided that can shorten the overall time required for inspection.

[0082] The image generating device 100 according to the fifth aspect is the image generating device 100 according to any one of the first to fourth aspects, in which the merging unit 135 generates a merged image by averaging multiple intermediate images after processing by the filter unit 134 using an averaging filter in which the same kernel coefficient is assigned to each pixel.

[0083] According to this configuration, a merged image can be generated by averaging multiple intermediate images using an averaging filter assigned the same kernel coefficient. Therefore, even if previous and next images contain defects or pseudo-defects, a defect-free merged image can be generated by integrating multiple images using an averaging filter with the same kernel coefficient. This makes it possible to accurately and easily determine whether or not a defect exists, thereby reducing the number of re-inspections required. Therefore, an image generating device 100 can be provided that can shorten the overall time required for inspection.

[0084] The image generating device 100 according to the sixth aspect is the image generating device 100 according to any one of the first to fifth aspects, in which the merging unit 135 generates a merged image by averaging multiple intermediate images after processing by the filter unit 134 using a weighted averaging filter in which a different kernel coefficient is assigned to each pixel.

[0085] This configuration makes it possible to generate a merged image by averaging multiple intermediate images using a weighted averaging filter in which a different kernel coefficient is assigned to each pixel. Therefore, for areas where defects are likely to exist in the previous and next images, an intermediate image can be generated in which the presence of defects is appropriately diluted. This makes it possible to accurately and easily determine the presence or absence of defects, thereby reducing the number of re-inspections. Therefore, it is possible to provide an image generating device 100 that can shorten the overall time required for inspection.

[0086] The image generation method according to the first embodiment includes the steps of acquiring inspection data of the object to be inspected using the ultrasonic flaw detection inspection device 200, generating an image representing the inspection results of the ultrasonic flaw detection inspection based on the inspection data, using frame interpolation on a predetermined number of images before and after an image containing a defect to generate an intermediate image representing an intermediate image between the images before and after the defect, using a low-pass filter to smooth out sudden changes in brightness in the generated intermediate image, and integrating the multiple intermediate images after processing using the low-pass filter to generate a single merged image.

[0087] According to this configuration, an intermediate image is generated using a predetermined number of images before and after an image containing a defect, and after removing noise other than the defect using a low-pass filter, a merged image can be generated by integrating the multiple intermediate images. Therefore, an inspection engineer can accurately determine whether or not there is a defect by visually comparing the image containing the defect with the intermediate image. Therefore, an image generation method that can shorten the overall time required for inspection can be provided.

[0088] The program according to the first aspect causes a computer to execute the following steps: acquiring inspection data of the object to be inspected using the ultrasonic flaw detection inspection device 200; generating an image representing the inspection results of the ultrasonic flaw detection inspection based on the inspection data; using frame interpolation on a predetermined number of images before and after an image containing a defect to generate an intermediate image representing an intermediate image between the images before and after the defect; using a low-pass filter on the generated intermediate image to smooth out sudden changes in brightness in the intermediate image; and integrating the multiple intermediate images after processing using the low-pass filter to generate a single merged image.

[0089] This configuration allows an intermediate image to be generated using a predetermined number of images before and after an image containing a defect, and after removing noise other than the defect using a low-pass filter, a merged image can be generated by integrating the multiple intermediate images. Therefore, an inspection engineer can accurately determine whether or not there is a defect by visually comparing the image containing the defect with the intermediate image. Therefore, a program can be provided that can shorten the overall time required for inspection.

[0090] Although the embodiments of the present invention have been described above, the embodiments are not limited to the contents of these embodiments. Furthermore, the above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the scope of what is called equivalents. Furthermore, the above-described components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments. [Explanation of symbols]

[0091] 1. Image generation system 100 Image generating device 110 Communications Department 120 Storage section 121 Inspection data storage unit 122 Model Memory Unit 130 Control Unit 131 Acquisition Department 132 Image Generation Unit 133 Interpolation part 134 Filter section 135 Merge Section 136 Emphasis part 140 Input section 150 Display section 200 Ultrasonic flaw detection equipment 210 Probe section 220 Power supply section 230 Receiving unit 240 Control Unit 250 Storage section 260 I / F section N Network

Claims

1. an acquisition unit that acquires inspection data of an object to be inspected by an ultrasonic flaw detection inspection device; an image generating unit that generates an image that represents the intensity of the echo wave by changing the color of two-dimensional pixels based on the inspection data; an interpolation unit that generates an intermediate image representing an intermediate image between a predetermined number of images before and after the image including the defect by using frame interpolation; a filter unit that smooths out sudden changes in brightness in the intermediate image generated by the interpolation unit using a low-pass filter; a merging unit that combines the plurality of intermediate images processed by the filtering unit to generate a single merged image. Image generating device.

2. an enhancement unit that enhances the presence of the defect in the image including the defect by performing a process of subtracting the merged image from the image including the defect. The image generating device of claim 1 .

3. The interpolation unit uses FILM (Frame Interpolation for Large Motion) as an inter-frame interpolation method.

3. The image generating device according to claim 1 or 2.

4. the merging unit generates a merged image by averaging a plurality of intermediate images processed by the filtering unit using an averaging filter; 3. The image generating device according to claim 1 or 2.

5. the merging unit generates a merged image by averaging a plurality of intermediate images processed by the filtering unit using an averaging filter in which the same kernel coefficient is assigned to each pixel.

3. The image generating device according to claim 1 or 2.

6. the merging unit generates a merged image by averaging a plurality of intermediate images processed by the filtering unit using a weighted averaging filter in which a different kernel coefficient is assigned to each pixel. The image generating device of claim 1 .

7. A step of acquiring inspection data of an inspection object by an ultrasonic flaw detection inspection device; generating an image based on the inspection data, the image representing the intensity of the echo wave by a change in color of pixels in two dimensions; generating an intermediate image representing an intermediate image between the image including the defect and a predetermined number of images before and after the defect using frame interpolation; smoothing out sudden changes in brightness in the intermediate image by using a low-pass filter on the generated intermediate image; and combining the intermediate images after low-pass filtering to generate a single merged image. Image generation method.

8. A step of acquiring inspection data of an inspection object by an ultrasonic flaw detection inspection device; generating an image based on the inspection data, the image representing the intensity of the echo wave by a change in color of pixels in two dimensions; generating an intermediate image representing an intermediate image between the image including the defect and a predetermined number of images before and after the defect using frame interpolation; smoothing out sudden changes in brightness in the intermediate image by using a low-pass filter on the generated intermediate image; combining the intermediate images after low-pass filtering to generate a single merged image; A program that causes a computer to execute the following.

Images