A method, device and storage medium for identifying sensitivity of a weld radiographic inspection film

Abstract

The present application provides a kind of weld radiographic inspection negative sensitivity identification method, equipment and storage medium, wherein, method includes: obtaining weld radiographic inspection negative image, determines the image quality gauge monofilament image corresponding to the weld radiographic inspection negative image;According to the image quality gauge monofilament image, obtain candidate monofilament image;According to the candidate monofilament image, obtain monofilament image;According to the monofilament image, carry out negative sensitivity identification.The present application can accurately identify the number of effective monofilament in weld radiographic inspection negative, judge weld radiographic inspection negative sensitivity according to the number of effective monofilament, improve the precision of weld radiographic inspection negative sensitivity judgment, reduce the mistake of artificial judgment, reduce cost, improve efficiency.

Description

Technical Field

[0001] This invention relates to the field of computer vision technology, and in particular to a method, device and storage medium for identifying the sensitivity of radiographic testing films of weld seams. Background Technology

[0002] With the rapid development of computer network technology, computer vision has become particularly important. Computer vision is a research field that allows computers or machines to perform visual tasks. Technologies related to computer vision are already ubiquitous in our lives. There are technologies related to images and videos, such as facial recognition and panoramic image creation, object recognition, and image restoration used in smartphone camera functions. Computer vision is the ability to create meaningful information from images, foregrounds, and backgrounds received from cameras or scanners, or from video input media received through input and output media. The generation of such information is performed for a specific purpose and can be considered a field of artificial intelligence.

[0003] Radiographic testing sensitivity refers to the ability to detect the smallest internal defects of a weld on a radiographic film. It is a crucial indicator of the quality of radiographic testing itself, and the technical level of radiographic testing and the performance of the equipment used are largely reflected in this indicator. Weld radiographic testing film sensitivity identification is a type of radiographic testing sensitivity identification. This involves determining how many single wires of the image quality indicator are clearly visible on the film and combining this with the image quality indicator number to determine the film sensitivity. Currently, the determination of how many single wires are clearly visible is done manually, which is not only prone to human error but also increases labor costs. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, equipment, and storage medium for identifying the sensitivity of radiographic testing films for weld seams, in order to address the aforementioned technical problems.

[0005] A method for sensitivity identification of radiographic testing film of weld seams includes the following steps:

[0006] In one embodiment, a radiographic image of the weld is acquired, and a single-wire image of the image quality meter corresponding to the radiographic image of the weld is determined.

[0007] Based on the image quality meter single filament image, candidate single filament images are obtained;

[0008] Based on the candidate monofilament images, a monofilament image is obtained;

[0009] Film sensitivity is identified based on the monofilament image.

[0010] In one embodiment, determining the image quality meter single-wire image corresponding to the radiographic image of the weld includes:

[0011] The radiographic image of the weld seam is subjected to OCR recognition to obtain a character image;

[0012] The character image is analyzed to obtain an image quality indicator image;

[0013] The image quality meter image is derived to obtain the image quality meter monofilament image.

[0014] In one embodiment, obtaining candidate monofilament images based on the image quality meter monofilament image includes:

[0015] The image quality meter monofilament image is binarized to obtain a binarized monofilament image;

[0016] Hough line detection is performed on the binarized monofilament image to obtain candidate monofilament images.

[0017] In one embodiment, obtaining a monofilament image from the candidate monofilament image includes:

[0018] Based on the candidate monofilament image, non-monofilament lines are removed from the candidate monofilament image using the singular line filtering technique to obtain the first monofilament image;

[0019] Based on the first monofilament image, duplicate monofilaments in the first monofilament image are removed using the straight line merging technique to obtain the second monofilament image;

[0020] Based on the second monofilament image, short monofilaments in the second monofilament image are removed using monofilament verification technology to obtain a monofilament image.

[0021] In one embodiment, according to the monofilament verification technique, removing short monofilaments from the second monofilament image to obtain a monofilament image includes:

[0022] The second monofilament image is processed to remove short monofilaments, resulting in a monofilament image.

[0023] In one embodiment, processing multiple monofilaments in the second monofilament image to remove short monofilaments includes:

[0024] Generate a rectangular selection box centered on the monofilament;

[0025] Obtain the grayscale values ​​of the pixels within the rectangular selection box, and generate a pixel grayscale array based on the grayscale values:

[0026] P = [[G] 11 G 12 ,…G 1L ],[G21 G 22 ,…G 2L ],…,[G W1 G W2 ,…G WL ]]

[0027] Where P represents the pixel grayscale array, L represents the pixel column coordinates, W represents the pixel row coordinates, and G represents the pixel grayscale array. WL This represents the grayscale value of the pixel in row W and column L;

[0028] The average gray level of the pixel gray level array is calculated column-wise to obtain the average gray level array:

[0029] p = [G1, G2, ... G i ,…,G L ]

[0030] Where p represents the average grayscale array, G i L represents the grayscale value of the i-th pixel, and L represents the column coordinates of the pixel.

[0031] Determine the relationship between the difference between the gray level of the next pixel element and the gray level of the previous pixel element in the average gray level array and a preset threshold. In response to the difference being greater than the preset threshold, obtain the breakpoint of the single filament.

[0032] The average grayscale array is divided into several grayscale arrays of breakpoint pixels according to the breakpoint. For each grayscale array of breakpoint pixels, the mean of the average grayscale of each array is calculated. Based on the mean of the average grayscale of each array and the length of the grayscale array of breakpoint pixels, it is determined whether the corresponding monofilament is a long monofilament.

[0033] In response to the fact that the responding monofilament is a long monofilament, the long monofilament is retained;

[0034] In response to the response that the monofilament is not a long monofilament, the short monofilament is removed.

[0035] In one embodiment, film sensitivity identification based on the monofilament image includes:

[0036] Obtain the number of monofilaments in the monofilament image, and calculate the film sensitivity based on the number of monofilaments;

[0037] Film sensitivity is identified based on the film sensitivity.

[0038] In one embodiment, calculating the film sensitivity based on the number of monofilaments includes:

[0039] Calculate film sensitivity using the following formula:

[0040] S = M + N - 1

[0041] Where S represents film sensitivity, M represents the first digit of the image quality meter number, and N represents the number of monofilaments.

[0042] An apparatus includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of a weld radiographic testing film sensitivity identification method as described in the above embodiments.

[0043] A storage medium storing a computer program that, when executed by a processor, implements the steps of a weld radiographic testing film sensitivity identification method as described in the above embodiments.

[0044] Compared with the prior art, the advantages and beneficial effects of the present invention are as follows: The present invention can accurately identify the number of effective monofilaments in the weld radiographic testing film, and determine the sensitivity of the weld radiographic testing film based on the number of effective monofilaments, thereby improving the accuracy of the sensitivity judgment of the weld radiographic testing film, reducing human judgment errors, reducing costs, and improving efficiency. Attached Figure Description

[0045] Figure 1 This is a flowchart illustrating a method for identifying the sensitivity of radiographic testing film of weld seams in one embodiment.

[0046] Figure 2 This is a schematic diagram of a radiographic image of a weld in one embodiment;

[0047] Figure 3 This is a schematic diagram illustrating the specific identification of the image quality meter number in one embodiment;

[0048] Figure 4 This is a schematic diagram of a candidate monofilament image in one embodiment;

[0049] Figure 5 This is a schematic diagram of a binarized monofilament image in one embodiment;

[0050] Figure 6 This is a schematic diagram of a candidate monofilament image in one embodiment;

[0051] Figure 7 This is a schematic diagram of the first monofilament image in one embodiment;

[0052] Figure 8 This is a schematic diagram of the second monofilament in one embodiment;

[0053] Figure 9 This is a schematic diagram of a single filament image in one embodiment;

[0054] Figure 10 This is a schematic diagram of the internal structure of the device in one embodiment. Detailed Implementation

[0055] Before describing the specific embodiments of the present invention, the overall concept of the present invention will be explained as follows:

[0056] This invention is mainly about the development of the sensitivity identification process for radiographic testing films of weld seams. Currently, this process is judged manually, which is not only prone to human error but also increases labor costs.

[0057] Therefore, this invention proposes a method for identifying the sensitivity of radiographic testing film of weld seams. The method determines the image quality indicator single-wire image based on the radiographic testing film image of the weld seam, processes the image quality indicator single-wire image to obtain the number of single wires, and then performs film sensitivity identification.

[0058] After introducing the overall concept of the present invention, in order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below through specific embodiments and in conjunction with the accompanying drawings.

[0059] It should be noted that, unless otherwise defined, the technical or scientific terms used in one or more embodiments of this specification should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in one or more embodiments of this specification do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word covers the element or object listed following the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0060] For ease of understanding, the terms used in the embodiments of this application are explained below:

[0061] OCR: Optical Character Recognition (OCR) refers to the process by which electronic devices (such as scanners or digital cameras) examine characters printed on paper and then translate the shapes into computer text using character recognition methods.

[0062] In one embodiment, such as Figure 1 As shown, a method for sensitivity identification of radiographic testing films for weld seams is provided, comprising the following steps:

[0063] Step S101: Obtain the radiographic image of the weld and determine the image quality meter single-wire image corresponding to the radiographic image of the weld.

[0064] Specifically, after obtaining the radiographic image of the weld, it is necessary to locate the image quality meter and crop the single-wire image of the image quality meter based on its location. The radiographic image of the weld is shown below. Figure 2 As shown.

[0065] Based on this, the image quality indicator single-wire image corresponding to the radiographic image of the weld seam includes:

[0066] The radiographic image of the weld seam is subjected to OCR recognition to obtain a character image;

[0067] The character image is analyzed to obtain an image quality indicator image;

[0068] The image quality meter image is derived to obtain the image quality meter monofilament image.

[0069] Specifically, OCR recognition is performed on the radiographic inspection film images of weld seams to identify all characters in the image, including their content and location. Then, each group of characters is analyzed to find the group that best matches the image quality meter's numbering pattern (e.g., characters shorter than 6 characters and containing "FE"). Example: "6FE12". Specific image identification and numbering is shown below. Figure 3 As shown, the position of this group of characters is the position of the image quality meter in the image, that is, the image quality meter number is 6FE12, and the starting position is (6474, 316).

[0070] Step S102: Obtain candidate monofilament images based on the image quality meter monofilament images.

[0071] Specifically, candidate monofilament images are obtained by processing the image based on the position of the image quality monitor in the monofilament image. Since the position of the monofilament on the image quality monitor is fixed, the starting position of the image quality monitor in the image is used. For example, the starting position of the monofilament in the image is derived as (6374, 526). The width of the monofilament region is fixed at 900, and the height is fixed at 1680. Based on the above starting position, width, and height, the image quality monitor monofilament region is extracted, which is the candidate monofilament image, as shown below. Figure 4 As shown.

[0072] Based on this, candidate monofilament images are obtained from the image quality meter monofilament image, including:

[0073] The image quality meter monofilament image is binarized to obtain a binarized monofilament image;

[0074] Hough line detection is performed on the binarized monofilament image to obtain candidate monofilament images.

[0075] Specifically, the monofilament image is binarized to obtain a binary monofilament image, such as... Figure 5As shown, this is preparation for Hough line detection. The Hough line detection technique is used to detect lines in the binarized monofilament image, resulting in candidate monofilament images. These candidate monofilament images contain a series of straight lines, i.e., candidate monofilaments, as shown below. Figure 6 As shown in the figure, the lines represent candidate monofilaments, which include non-monofilaments, repeating monofilaments, short monofilaments, and long monofilaments.

[0076] Step S103: Obtain a monofilament image based on the candidate monofilament image.

[0077] Specifically, the candidate monofilaments in the candidate monofilament images are filtered to obtain monofilament images containing only valid monofilaments.

[0078] Based on this, the monofilament image obtained from the candidate monofilament image includes:

[0079] Based on the candidate monofilament image, non-monofilament lines are removed from the candidate monofilament image using the singular line filtering technique to obtain the first monofilament image;

[0080] Based on the first monofilament image, duplicate monofilaments in the first monofilament image are removed using the straight line merging technique to obtain the second monofilament image;

[0081] Based on the second monofilament image, short monofilaments in the second monofilament image are removed using monofilament verification technology to obtain a monofilament image.

[0082] Specifically, based on the candidate monofilament images, a singular line filtering technique is used to remove non-monofilaments from the candidate monofilaments, resulting in the first monofilament image. The first monofilament image is shown below. Figure 7 As shown, the slopes of some straight lines deviate significantly from the mean and have been removed.

[0083] Based on the first monofilament image, duplicate monofilaments in the candidate monofilaments are removed using a straight-line merging technique to obtain the second monofilament image. The specific second monofilament image is as follows: Figure 8 As shown, duplicate monofilaments have been removed, leaving 8 candidate monofilaments. It should be noted that these 8 straight lines are drawn based on the slope and offset of the merged straight lines, and they run through the entire image. They will be used for subsequent monofilament verification.

[0084] Based on the second monofilament image, short monofilaments in the candidate monofilaments are removed using monofilament verification technology to obtain the monofilament image. The specific monofilament image is shown below. Figure 9 As shown.

[0085] Based on this, using the monofilament verification technique, short monofilaments are removed from the second monofilament image to obtain a monofilament image including:

[0086] The second monofilament image is processed to remove short monofilaments, resulting in a monofilament image.

[0087] Based on this, multiple monofilaments in the second monofilament image are processed to remove short monofilaments, including:

[0088] Generate a rectangular selection box centered on the monofilament;

[0089] Obtain the grayscale values ​​of the pixels within the rectangular selection box, and generate a pixel grayscale array based on the grayscale values:

[0090] P = [[G] 11 G 12 ,…G 1L ],[G 21 G 22 ,…G 2L ],…,[G W1 G W2 ,…G WL ]]

[0091] Where P represents the pixel grayscale array, L represents the pixel column coordinates, W represents the pixel row coordinates, and G represents the pixel grayscale array. WL This represents the grayscale value of the pixel in row W and column L;

[0092] The average gray level of the pixel gray level array is calculated column-wise to obtain the average gray level array:

[0093] p = [G1, G2, ... G i ,…,G L ]

[0094] Where p represents the average grayscale array, G i L represents the grayscale value of the i-th pixel, and L represents the column coordinates of the pixel.

[0095] Determine the relationship between the difference between the gray level of the next pixel element and the gray level of the previous pixel element in the average gray level array and a preset threshold. In response to the difference being greater than the preset threshold, obtain the breakpoint of the single filament.

[0096] The average grayscale array is divided into several grayscale arrays of breakpoint pixels according to the breakpoint. For each grayscale array of breakpoint pixels, the mean of the average grayscale of each array is calculated. Based on the mean of the average grayscale of each array and the length of the grayscale array of breakpoint pixels, it is determined whether the corresponding monofilament is a long monofilament.

[0097] In response to the fact that the responding monofilament is a long monofilament, the long monofilament is retained;

[0098] In response to the response that the monofilament is not a long monofilament, the short monofilament is removed.

[0099] Based on this, determining whether the corresponding monofilament is a long monofilament includes: selecting at least one array with an average gray value greater than the mean value, and selecting the array with the longest length as the key array;

[0100] The length of the key array is compared with a preset length threshold;

[0101] In response to the length of the key array exceeding the preset length threshold, multiple candidate filaments corresponding to the arrays are identified as long filaments, and the long filaments are retained.

[0102] In response to the fact that the length of the key array does not exceed the preset length threshold, candidate monofilaments corresponding to multiple arrays are determined to be short monofilaments, and the short monofilaments are removed.

[0103] Specifically, draw a rectangular selection box centered on the monofilament. The shorter side of the rectangle is perpendicular to the monofilament, with a width of W, and the longer side is parallel to the monofilament, with a length of L. Obtain the grayscale values ​​of the pixels within the rectangular selection box, and generate a two-dimensional pixel grayscale array based on these values: P = [[G 11 G 12 ,…G 1L ],[G 21 G 22 ,…G 2L ],…,[G W1 G W2 ,…G WL Where P represents the pixel grayscale array, L represents the pixel column coordinates, W represents the pixel row coordinates, and G represents the pixel grayscale array. WL This represents the grayscale value of the pixel in row W and column L.

[0104] The average gray level of each pixel is calculated column-wise to obtain a one-dimensional average gray level array: p = [G1, G2, ... G...]. i ,…,G L Where p represents the average grayscale array, G i Let L represent the grayscale value of the i-th pixel, and L represent the column coordinates of the pixel.

[0105] Iterate through the one-dimensional average grayscale array, comparing the grayscale value of each element with the grayscale value of the previous element. If the difference is... If the value is greater than a preset threshold, it is considered that the straight line has a break point at this point, and the break point i of the single filament is obtained. Based on the series of break points obtained, the old one-dimensional average gray-scale array is divided into several new one-dimensional break point pixel gray-scale arrays.

[0106] For each breakpoint pixel's grayscale array, calculate the length and average grayscale of these new breakpoint pixel's grayscale arrays. Then, calculate the mean of the average grayscale of these new breakpoint pixel's grayscale arrays. From these new breakpoint pixel's grayscale arrays, find the breakpoint pixel's grayscale array with the longest length and an average grayscale greater than the mean average grayscale (because the grayscale value of the monofilament is greater than the grayscale value of the background). If the length of this breakpoint pixel's grayscale array is greater than a preset threshold, for example, 100, then the candidate monofilament is considered a long monofilament, meaning the monofilament is clearly visible; otherwise, the candidate monofilament is considered a short monofilament, meaning it is not clearly visible.

[0107] Step S104: Perform film sensitivity identification based on the monofilament image.

[0108] Based on this, film sensitivity identification according to the monofilament image includes:

[0109] Obtain the number of monofilaments in the monofilament image, and calculate the film sensitivity based on the number of monofilaments;

[0110] Film sensitivity is identified based on the film sensitivity.

[0111] Specifically, the number of clearly visible monofilaments in the monofilament image is counted to obtain the total number of monofilaments in the image. The film sensitivity is then calculated based on the number of monofilaments, and film sensitivity identification is performed based on the film sensitivity. The higher the value, the higher the film sensitivity.

[0112] Based on this, the film sensitivity is calculated according to the number of monofilaments, including:

[0113] Calculate film sensitivity using the following formula:

[0114] S = M + N - 1

[0115] Where S represents film sensitivity, M represents the first digit of the image quality meter number, and N represents the number of monofilaments.

[0116] Specifically, the image quality meter number is "6FE12". The first digit of the image quality meter number is 6. A total of 6 monofilaments are clearly visible, so the film sensitivity is 11 (11 = 6 + 6 - 1).

[0117] This invention can accurately identify the number of effective monofilaments in weld radiographic testing films, and determine the sensitivity of the weld radiographic testing film based on the number of effective monofilaments. This improves the accuracy of weld radiographic testing film sensitivity determination, reduces human error, lowers costs, and increases efficiency.

[0118] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0119] It should be noted that the above description describes some embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0120] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this disclosure also provides an apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the weld radiographic testing film sensitivity identification method described in any of the above embodiments.

[0121] Figure 10 This embodiment illustrates a more specific hardware structure of a device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0122] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0123] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0124] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0125] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0126] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0127] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0128] The device described in the above embodiments is used to implement the corresponding weld radiographic testing film sensitivity identification method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0129] Based on the same inventive concept, corresponding to any of the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the weld radiographic testing film sensitivity identification method as described in any of the above embodiments.

[0130] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0131] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the weld radiographic testing film sensitivity identification method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0132] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0133] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuitry) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure may be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0134] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0135] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for identifying the sensitivity of radiographic testing films of weld seams, characterized in that, include: Acquire a radiographic image of the weld seam and determine the image quality meter single-wire image corresponding to the radiographic image of the weld seam. Based on the image quality meter single filament image, candidate single filament images are obtained; Based on the candidate monofilament image, non-monofilament lines are removed from the candidate monofilament image using the singular line filtering technique to obtain the first monofilament image; Based on the first monofilament image, duplicate monofilaments in the first monofilament image are removed using the straight line merging technique to obtain the second monofilament image; Based on the second monofilament image, short monofilaments in the second monofilament image are removed according to the monofilament verification technique to obtain the monofilament image; Film sensitivity identification is performed based on the monofilament image; The step of removing short monofilaments from the second monofilament image using monofilament verification technology to obtain a monofilament image includes: The second monofilament image is processed to remove short monofilaments, thus obtaining a monofilament image. The process of processing multiple monofilaments in the second monofilament image to remove short monofilaments includes: Generate a rectangular selection box centered on the monofilament; Obtain the grayscale values ​​of the pixels within the rectangular selection box, and generate a pixel grayscale array based on the grayscale values: ， in, Represents a grayscale array of pixels. Represents the column coordinates of pixels. Represents the row coordinates of a pixel. express OK The grayscale value of the pixels in the column; The average gray level of the pixel gray level array is calculated column-wise to obtain the average gray level array: ， in Represents the average grayscale array, Indicates the first grayscale of each pixel element Represents the column coordinates of a pixel; Determine the relationship between the difference between the gray level of the next pixel element and the gray level of the previous pixel element in the average gray level array and a preset threshold. In response to the difference being greater than the preset threshold, obtain the breakpoint of the single filament. The average grayscale array is divided into several grayscale arrays of breakpoint pixels according to the breakpoint. For each grayscale array of breakpoint pixels, the mean of the average grayscale of each array is calculated. Based on the mean of the average grayscale of each array and the length of the grayscale array of breakpoint pixels, it is determined whether the corresponding monofilament is a long monofilament. In response to the fact that the corresponding monofilament is a long monofilament, the long monofilament is retained; In response to the corresponding non-long monofilament, the short monofilament is removed.

2. The method for identifying the sensitivity of radiographic testing film of weld seams according to claim 1, characterized in that, The step of determining the image quality meter single-wire image corresponding to the radiographic image of the weld includes: The radiographic image of the weld seam is subjected to OCR recognition to obtain a character image; The character image is analyzed to obtain an image quality indicator image; The image quality meter image is derived to obtain the image quality meter monofilament image.

3. The method for identifying the sensitivity of radiographic testing film of weld seams according to claim 1, characterized in that, The step of obtaining candidate monofilament images based on the image quality meter monofilament image includes: The image quality meter monofilament image is binarized to obtain a binarized monofilament image; Hough line detection is performed on the binarized monofilament image to obtain candidate monofilament images.

4. The method for identifying the sensitivity of radiographic testing film of weld seams according to claim 1, characterized in that, The step of identifying film sensitivity based on the monofilament image includes: Obtain the number of monofilaments in the monofilament image, and calculate the film sensitivity based on the number of monofilaments; Film sensitivity is identified based on the film sensitivity.

5. The method for identifying the sensitivity of radiographic testing film of weld seams according to claim 4, characterized in that, The calculation of film sensitivity based on the number of monofilaments includes: Calculate film sensitivity using the following formula: ， in, Indicates film sensitivity. This indicates the first digit of the quality indicator number. This indicates the number of monofilaments.

6. An apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

7. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images