Hidden crack identification method and device and hidden crack identification equipment
Through position comparison and pixel change analysis of the first and second views of the single crystal silicon rod, the hidden cracks to be identified are identified, which solves the problem of low accuracy of existing hidden crack detection methods and achieves higher accuracy. Detection accuracy.
Patent Information
- Application Number
- CN202411501725.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-25
- Publication Date
- 2025-01-24
AI Technical Summary
The existing hidden crack detection methods have the problem of low detection accuracy.
By comparing the positions of the first crack to be identified in the first view and the second crack to be identified in the second view, it is determined whether the position of the first crack to be identified corresponds to the position of the second crack to be identified. When they do not correspond, Determine the hidden cracks to be identified based on pixel changes, and identify them based on their positional relationships.
It improves the accuracy of hidden crack detection, and can more effectively identify the hybrid of hidden and fissure.
Smart Images
Figure CN119359685A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a method, device and equipment for identifying hidden cracks. Background Art
[0002] With the rapid development of the semiconductor industry, the quality requirements for single crystal square rods are increasing. As an important component of semiconductor materials, the quality of single crystal square rods is directly related to the performance and reliability of the final product, so the quality control is extremely strict during the production process.
[0003] In the prior art, the detection of hidden cracks in monocrystalline silicon rods mainly relies on electroluminescence (EL) imaging detection. This method first applies a certain voltage to the monocrystalline silicon rod or photovoltaic module to generate electroluminescence. Then a high-sensitivity camera is used to capture the luminescent image, and the brightness and uniformity are analyzed through image processing software to identify areas with abnormal brightness, which usually correspond to hidden cracks or other defects. This method can not only detect hidden cracks non-contact and efficiently, but also provide detailed defect location and size information. It is a non-destructive testing method widely used in industrial production.
[0004] However, existing hidden crack detection methods have the problem of low detection accuracy. Summary of the invention
[0005] The embodiments of the present application provide a hidden crack identification method, apparatus and hidden crack identification equipment to solve the problem of low detection accuracy in existing hidden crack detection methods.
[0006] In a first aspect, an embodiment of the present application provides a method for identifying hidden cracks, the method comprising:
[0007] Determining a first crack to be identified in a first view of the object to be identified, and a second crack to be identified in a second view;
[0008] When the position of the first crack to be identified does not correspond to the position of the second crack to be identified, determining a hidden crack to be identified in the first crack to be identified according to a pixel change of the first crack to be identified in the first view;
[0009] According to the positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack, and the positional relationship with other to-be-identified cracks in other views of the to-be-identified object, the to-be-identified hidden crack is identified to obtain a hidden crack identification result.
[0010] In a possible implementation, determining a first crack to be identified in a first view of the object to be identified and a second crack to be identified in a second view includes:
[0011] Identify a first view of the object to be identified, and determine a first crack to be identified in the first view;
[0012] Determine, according to the first view, a second view that satisfies the viewing angle relationship;
[0013] The second view is identified to determine a second crack to be identified in the second view.
[0014] In a possible implementation, determining a first crack to be identified in a first view of the object to be identified and a second crack to be identified in a second view includes:
[0015] Capturing images of the object to be identified to obtain video images of the object to be identified at various viewing angles;
[0016] Generate a view of the object to be identified according to the video images of the object to be identified at various viewing angles;
[0017] The first view and the second view in the view are identified and processed to determine a first crack to be identified in the first view and a second crack to be identified in the second view.
[0018] In a possible implementation, performing image acquisition on the object to be identified to obtain video images of the object to be identified at various viewing angles includes:
[0019] Determine the type of object to be identified;
[0020] Adjusting the shooting parameters of the video image according to the type of the object to be identified;
[0021] After adjusting the shooting parameters, the image of the object to be identified is collected to obtain video images of the object to be identified at various viewing angles.
[0022] In a possible implementation manner, determining a hidden crack to be identified in the first crack to be identified according to a pixel change of the first crack to be identified in the first view includes:
[0023] Determine, according to the pixel value of the pixel point of the first crack to be identified in the first view, a pixel change condition representing a brightness change of the pixel point;
[0024] A first hidden crack to be identified in the first cracks to be identified is determined according to a pixel change condition representing a brightness change of the pixel point.
[0025] In a possible implementation manner, determining a pixel change situation representing a brightness change of a pixel point according to a pixel value of a pixel point of a first crack to be identified in a first view includes:
[0026] According to the pixel value of the pixel of the first crack to be identified in the first view, the gradient strength of the pixel is determined; according to the gradient strength of the pixel, the pixel change condition representing the brightness change of the pixel is determined.
[0027] In a possible implementation, based on the positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack, and the positional relationship between the first to-be-identified hidden crack and other to-be-identified cracks in other views of the to-be-identified object, the to-be-identified hidden crack is identified to obtain a hidden crack identification result, including:
[0028] Determine the positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack according to the positional correspondence between the first to-be-identified hidden crack and the second to-be-identified crack;
[0029] Determine the positional relationship between the first hidden crack to be identified and the other cracks to be identified according to the positional relationship between the first hidden crack to be identified and other cracks to be identified in other views of the object to be identified;
[0030] If the positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack, and the positional relationship between the first to-be-identified hidden crack and other to-be-identified cracks both represent corresponding overlap of positions, then a hidden crack identification result representing that the first to-be-identified hidden crack is a hidden crack is obtained.
[0031] In a possible implementation, the method further includes:
[0032] If the positions representing the positional relationship between the first hidden crack to be identified and the second crack to be identified do not overlap correspondingly, and / or the positions representing the positional relationship between the first hidden crack to be identified and other cracks to be identified do not overlap correspondingly, then view display information of the object to be identified is generated and output.
[0033] In a second aspect, an embodiment of the present application provides a hidden crack identification device, including:
[0034] A first determination module, used to determine a first crack to be identified in a first view of the object to be identified, and a second crack to be identified in a second view;
[0035] a second determination module, configured to determine, when the position of the first crack to be identified does not correspond to the position of the second crack to be identified, a hidden crack to be identified in the first crack to be identified according to a pixel change of the first crack to be identified in the first view;
[0036] The obtaining module is used to identify the hidden crack to be identified according to the positional relationship between the first hidden crack to be identified and the second hidden crack to be identified, and the positional relationship with other hidden cracks to be identified in other views of the object to be identified, and obtain a hidden crack identification result.
[0037] In a third aspect, an embodiment of the present application provides a hidden crack identification device, including: a memory, a processor;
[0038] Memory stores computer-executable instructions;
[0039] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.
[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.
[0041] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.
[0042] The hidden crack identification method, apparatus and equipment provided in the embodiments of the present application determine whether the position of the first crack to be identified corresponds to the position of the second crack to be identified by comparing the position of the first crack to be identified in the first view with the position of the second crack to be identified in the second view. When the position of the first crack to be identified does not correspond to the position of the second crack to be identified, it indicates that the first crack to be identified may be a hidden crack, or a visible crack, or a more complex mixture of hidden cracks and visible cracks. Therefore, based on the pixel change of the first crack to be identified in the first view, the hidden crack to be identified in the first crack to be identified is first determined, and then the hidden crack to be identified is identified based on the positional relationship between the first hidden crack to be identified and the second crack to be identified, as well as the positional relationship with other cracks to be identified in other views of the object to be identified, to obtain a means of hidden crack identification result, thereby achieving the effect of improving the detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0044] Figure 1 A schematic diagram of a scenario of a hidden crack identification method provided in this application;
[0045] Figure 2 Schematic diagram of the process of the hidden crack identification method provided in this application Figure 1 ;
[0046] Figure 3 Schematic diagram of the process of the hidden crack identification method provided in the embodiment of the present application Figure 2 ;
[0047] Figure 4 A schematic diagram of the structure of a hidden crack identification device provided in an embodiment of the present application;
[0048] Figure 5 A schematic diagram of the structure of a hidden crack identification device provided in an embodiment of the present application.
[0049] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0050] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0051] First, the terms involved in this application are explained:
[0052] Hidden cracks can refer to tiny cracks inside or below the surface of a material. These cracks are usually not noticeable to the naked eye, but may expand under certain conditions (such as stress or temperature changes), thus affecting the integrity and performance of the material. In single crystal silicon rods, hidden cracks may be caused by stress concentration during the growth process or improper operation during processing, posing a potential threat to the reliability and yield of semiconductor devices.
[0053] In the prior art, the detection of hidden cracks in monocrystalline silicon rods mainly relies on electroluminescence imaging detection. This method first applies a certain voltage to the monocrystalline silicon rod or photovoltaic module to generate electroluminescence. Then a high-sensitivity camera is used to capture the luminescent image, and the brightness and uniformity are analyzed through image processing software to identify areas with abnormal brightness, which usually correspond to hidden cracks or other defects. This method can not only detect hidden cracks non-contact and efficiently, but also provide detailed defect location and size information. It is a non-destructive testing method widely used in industrial production.
[0054] However, electroluminescence imaging technology is sensitive to the surface conditions of the crystal rod. When cracks appear on the surface of the crystal rod, misjudgment may occur. At the same time, the image analysis process is relatively complicated and requires professional software and algorithms. The operator's technical level and parameter settings will also affect the results. In addition, environmental factors such as changes in light, temperature and humidity may also interfere with detection and reduce accuracy. These factors combined reduce the detection accuracy of electroluminescence imaging technology.
[0055] The hidden crack identification method, device and hidden crack identification equipment provided in the embodiments of the present application judge whether the first crack to be identified is a complex situation by comparing the position of the first crack to be identified in the first view with the position of the second crack to be identified in the second view. When the position of the first crack to be identified does not correspond to the position of the second crack to be identified, it indicates that the first crack to be identified may be a hidden crack, or a visible crack, or a more complex mixture of hidden cracks and visible cracks. Therefore, based on the pixel change of the first crack to be identified in the first view, the first crack to be identified can be initially identified to determine the hidden crack to be identified in the first crack to be identified, and then the hidden crack to be identified can be identified based on the positional relationship between the first hidden crack to be identified and the second crack to be identified, as well as the positional relationship with other cracks to be identified in other views of the object to be identified, to obtain a means of hidden crack identification result, thereby achieving the effect of improving the detection accuracy.
[0056] Figure 1 A schematic diagram of a scenario of a hidden crack identification method provided in this application, such as Figure 1 As shown, the specific application scenarios of the present application may include a hidden crack identification system and a hidden crack photographing device. The hidden crack identification system can be connected to the hidden crack photographing device to obtain the image of the crystal rod photographed by the hidden crack photographing device. The hidden crack photographing device may include multiple cameras. When the crystal rod is sent into the shooting position of the hidden crack photographing device, the multiple cameras can scan and photograph the crystal rod, and send the scanned and photographed images to the hidden crack identification system for processing. The hidden crack identification system can be a server, and the server can be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, or a personal computer (PC) and other devices; the server can be a single server or a server cluster composed of multiple servers.
[0057] The embodiments of the present application do not limit the execution subject, as long as the execution subject can determine the first crack to be identified in the first view of the object to be identified, and the second crack to be identified in the second view; when the position of the first crack to be identified does not correspond to the position of the second crack to be identified, determine the hidden crack to be identified in the first crack to be identified according to the pixel change of the first crack to be identified in the first view; identify the hidden crack to be identified according to the positional relationship between the first hidden crack to be identified and the second crack to be identified, as well as the positional relationship with other cracks to be identified in other views of the object to be identified, and obtain a hidden crack identification result.
[0058] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.
[0059] Figure 2 Schematic diagram of the process of the hidden crack identification method provided in this application Figure 1 ,like Figure 2 As shown, the method includes:
[0060] S201: Determine a first crack to be identified in a first view of an object to be identified, and a second crack to be identified in a second view.
[0061] The object to be identified may refer to a crystal rod that needs to be tested for hidden cracks.
[0062] The first view and the second view may refer to a first view of the object to be identified at a first perspective, and a second view at a second perspective, wherein the first view and the second view may be a set of corresponding views, for example, when the first view is a front view of the object to be identified, the second view may be a rear view of the object to be identified, and when the first view is a left view of the object to be identified, the second view may be a right view of the object to be identified.
[0063] In the embodiment of the present application, the first view and the second view may be views that can display internal defects of the object to be identified, and the first view and the second view may be obtained by transmitted light imaging, such as X-ray imaging, through which structural information inside the crystal rod, including cracks and other defects, may be obtained. Infrared imaging, using a near-infrared light source and an infrared camera, may observe the structure inside the crystal rod to a certain extent.
[0064] In an embodiment of the present application, when cracks exist in each view, the first view and the second view may be a group of views whose image quality meets the quality requirements among all views, that is, the views may be sorted according to their view quality, and a group with the best comprehensive sorting quality may be selected as the first view and the second view.
[0065] The crack to be identified may refer to a place where a crack may appear on the view of the object to be identified. For example, the crack to be identified is usually shown as one or more discontinuous lines or dark areas in the image, and the brightness, color or texture of these areas are different from the surrounding normal areas. Therefore, by identifying these areas on the image, the crack to be identified on the view can be determined, wherein the first crack to be identified may refer to the crack to be identified on the first view, and the second crack to be identified may refer to the crack to be identified on the second view.
[0066] In the embodiment of the present application, determining a first crack to be identified in a first view of the object to be identified and a second crack to be identified in a second view includes:
[0067] Identify a first view of the object to be identified, and determine a first crack to be identified in the first view;
[0068] Determine, according to the first view, a second view that satisfies the viewing angle relationship;
[0069] The second view is identified to determine a second crack to be identified in the second view.
[0070] Among them, identifying the view of the object to be identified may refer to a process of identifying a crack to be identified in the view. In an embodiment of the present application, the process of identifying a crack to be identified in the view may include:
[0071] a. Image preprocessing: including using filters (such as Gaussian filtering, median filtering) to remove noise from the image, improve image quality, enhance the contrast of the image through methods such as histogram equalization or gamma correction to make cracks and other defects more obvious, and convert color images into grayscale images to simplify subsequent processing steps.
[0072] b. Feature extraction: This includes using methods such as Canny edge detection and Sobel operator to detect the edges in the image and extract the outline of the crack. Then, the texture features of the image are analyzed through methods such as gray-level co-occurrence matrix (GLCM) to identify the texture pattern of the crack. Finally, morphological operations such as corrosion, expansion, opening, and closing are used to remove noise and refine the crack features.
[0073] c. Threshold segmentation: This includes using the Otsu method or other global threshold algorithms to separate the crack area in the image from the background. For complex backgrounds, a local threshold algorithm (such as adaptive threshold) can be used to better segment the crack area.
[0074] d. Crack identification: Cracks are identified through a pre-set machine learning model to determine the cracks to be identified in the view that may be crack areas.
[0075] In some embodiments, since the pixels of the crack area are different from those of other areas on the view, the crack area can also be distinguished by pixels.
[0076] In the embodiment of the present application, since the first view and the second view are both transmission images, when making a judgment, if it is impossible to directly determine whether it is a hidden crack or a visible crack, the corresponding second view can be found for judgment based on the viewing angle relationship.
[0077] In the embodiment of the present application, determining a first crack to be identified in a first view of the object to be identified and a second crack to be identified in a second view includes:
[0078] Capturing images of the object to be identified to obtain video images of the object to be identified at various viewing angles;
[0079] Generate a view of the object to be identified according to the video images of the object to be identified at various viewing angles;
[0080] The first view and the second view in the view are identified and processed to determine a first crack to be identified in the first view and a second crack to be identified in the second view.
[0081] Image acquisition refers to the process of obtaining an image of an object to be identified by photographing, scanning, or the like.
[0082] The video image may refer to a video image when scanning the object to be identified. In the embodiment of the present application, the video image can be obtained by setting a camera and moving the camera to shoot video images of the object to be identified at various viewing angles, wherein the video images at various viewing angles can be images with multiple camera positions that can be divided into front, back, top, bottom, and wide-angle full coverage and moving illumination, or can be an annular model, where the camera moves around the crystal rod to shoot images by rotating 360°.
[0083] Generating a view of the object to be identified based on video images of the object to be identified at various perspectives may refer to a process of generating a view of the object to be identified by using a multi-perspective video image fusion technique, wherein the process may include: first capturing video images of the object to be identified from different angles to ensure that all sides of the object are covered; then, using an image stitching algorithm (such as panoramic stitching based on feature point matching) to stitch the images from various perspectives into a complete two-dimensional view; then generating a three-dimensional model of the object by using a three-dimensional reconstruction technique (such as structured light scanning or stereo vision); and finally, extracting two-dimensional projection images of the desired perspectives from the three-dimensional model to generate various views.
[0084] Among them, in the embodiment of the present application, image acquisition is performed on the object to be identified to obtain video images of the object to be identified at various viewing angles, including:
[0085] Determine the type of object to be identified;
[0086] Adjusting the shooting parameters of the video image according to the type of the object to be identified;
[0087] After adjusting the shooting parameters, the image of the object to be identified is collected to obtain video images of the object to be identified at various viewing angles.
[0088] The type of the object to be identified may refer to crystal rods of different specifications, sizes or materials.
[0089] When performing image acquisition, in order to improve the image acquisition effect, different shooting parameters are generally used according to different crystal rods, thereby achieving better image acquisition effects, including:
[0090] Shooting parameters may include exposure time, aperture size, ISO sensitivity, focal length, and white balance. For example, for transparent or translucent single crystal silicon rods, the exposure time can be increased and a high-brightness light source can be used to enhance the contrast of the image; for metal crystal rods with high reflectivity, the aperture and ISO sensitivity need to be adjusted to reduce the interference of reflected light; for the detection of small cracks, a high-resolution camera and an appropriate focal length should be selected to ensure the clarity of details. By finely adjusting these parameters, the image quality can be optimized to better meet the detection requirements of different crystal rod types.
[0091] S202: When the position of the first crack to be identified does not correspond to the position of the second crack to be identified, determine a hidden crack to be identified in the first crack to be identified according to a change in pixels of the first crack to be identified in the first view.
[0092] Among them, the fact that the position of the first crack to be identified does not correspond to the position of the second crack to be identified may mean that the first crack to be identified and the second crack to be identified are partially aligned and the other part is not aligned. Therefore, it can be characterized that both the first crack to be identified and the second crack to be identified are obvious cracks, or that part of the first crack to be identified and the second crack to be identified are obvious cracks and part are hidden cracks.
[0093] Pixel changes can refer to changes in pixel values (such as brightness, color, grayscale, etc.). Due to the different manifestations of hidden cracks and visible cracks in images, hidden cracks usually appear as small, discontinuous pixel changes, with relatively gentle changes in brightness and grayscale gradients and delicate texture features; while visible cracks appear as large, continuous pixel changes, with relatively drastic changes in brightness and grayscale gradients and rough texture features. By analyzing the changes in the pixel values of cracks, such as brightness differences, grayscale gradients, and texture features, it is possible to preliminarily distinguish hidden cracks from visible cracks.
[0094] In the embodiment of the present application, determining the hidden crack to be identified in the first crack to be identified according to the pixel change of the first crack to be identified in the first view includes:
[0095] Determine, according to the pixel value of the pixel point of the first crack to be identified in the first view, a pixel change condition representing a brightness change of the pixel point;
[0096] A first hidden crack to be identified in the first cracks to be identified is determined according to a pixel change condition representing a brightness change of the pixel point.
[0097] The pixel brightness refers to the brightness value of each pixel in the view, which is an indicator of the brightness of the pixel. In a grayscale image, the brightness value is usually an integer between 0 and 255, where 0 represents black (darkest) and 255 represents white (brightest). In a color image, the brightness value can be calculated by weighted averaging the values of the three RGB channels or other methods.
[0098] The pixel change that characterizes the brightness change of the pixel point can refer to the difference between the pixel brightness values in the crack area and its distribution characteristics, including brightness difference, grayscale gradient and texture characteristics. By analyzing these characteristics, it is possible to distinguish between visible cracks and hidden cracks in the cracks. For example, hidden cracks usually appear as small, discontinuous brightness changes and relatively gentle grayscale gradients, with relatively fine texture characteristics; while visible cracks appear as large, continuous brightness changes and relatively drastic grayscale gradients, with relatively rough texture characteristics. Through these pixel change characteristics, visible cracks and hidden cracks in the cracks can be effectively distinguished. For example, in the crack area, the brightness values of some pixels fluctuate between 200 and 210, or have a small change between 180 and 200, the grayscale gradient changes relatively smoothly (1 to 2), the texture features are delicate, and it shows small and discontinuous changes. Then it can be preliminarily determined that the crack in the crack area is a hidden crack. In the crack area, the brightness values of another part of the pixels drop sharply from 150 to 100, or have a large change between 150 and 180, the grayscale gradient changes more violently (above 10), the texture features are rough, and it shows large and continuous changes. Then it can be preliminarily determined that the crack in the crack area is a visible crack.
[0099] In the embodiment of the present application, determining the pixel change representing the brightness change of the pixel point according to the pixel value of the pixel point of the first crack to be identified in the first view includes:
[0100] Determine the gradient strength of the pixel point according to the pixel value of the first crack to be identified in the first view;
[0101] According to the gradient intensity of the pixel point, the pixel change condition representing the brightness change of the pixel point is determined.
[0102] Among them, the gradient intensity can refer to the rate of change of brightness between a certain pixel point and its neighboring pixel points in the image, which can be an indicator to measure the intensity of the brightness change of the pixel point in space. In image processing, the gradient intensity is usually obtained by calculating the gradient of the pixel point. Commonly used gradient operators include Sobel operator, Prewitt operator and Laplacian operator. Areas with higher gradient intensity indicate more drastic brightness changes, usually corresponding to features such as edges or cracks; while areas with lower gradient intensity indicate more gradual brightness changes, usually corresponding to flat or uniform areas. By analyzing the gradient intensity, it is possible to effectively distinguish between hidden cracks and visible cracks in cracks. Hidden cracks usually appear as small, discontinuous changes with lower gradient intensity, while visible cracks appear as larger, continuous changes with higher gradient intensity.
[0103] According to the gradient strength of the pixel point, determining the pixel change that characterizes the brightness change of the pixel point can refer to describing the brightness change characteristics in the crack area by analyzing the gradient strength of the pixel point. Among them, the gradient strength reflects the brightness change rate between the pixel point and its neighboring pixel points. The area with lower gradient strength indicates that the brightness change is relatively gentle, usually corresponding to hidden cracks; the area with higher gradient strength indicates that the brightness change is relatively drastic, usually corresponding to visible cracks.
[0104] S203, identifying the hidden crack to be identified according to the positional relationship between the first hidden crack to be identified and the second hidden crack to be identified, and the positional relationship between the first hidden crack to be identified and other hidden cracks to be identified in other views of the object to be identified, to obtain a hidden crack identification result.
[0105] The positional relationship between the first hidden crack to be identified and the second hidden crack to be identified may refer to whether the first hidden crack to be identified and the second hidden crack to be identified completely overlap.
[0106] Other views may refer to other views of the object to be identified except the first view and the second view. For example, when the first view is the main view and the second view is the rear view, the other views may include at least one of the left view, the right view, the top view, and the bottom view. Among them, the other views may also be views among the left view, the right view, the top view, and the bottom view whose view quality meets the requirements.
[0107] Other cracks to be identified may refer to cracks on other views.
[0108] The positional relationship between the first hidden crack to be identified and other cracks to be identified in other views of the object to be identified may refer to whether the first hidden crack to be identified and other cracks to be identified completely overlap.
[0109] Identifying a hidden crack to be identified may refer to the process of determining whether a hidden crack to be identified is a hidden crack based on the relationship between whether the first hidden crack to be identified completely overlaps with the second crack to be identified and whether the first hidden crack to be identified completely overlaps with other cracks to be identified. When the first hidden crack to be identified completely overlaps with the second crack to be identified and the first hidden crack to be identified completely overlaps with other cracks to be identified, it can be determined that the hidden crack to be identified is a hidden crack; when the first hidden crack to be identified does not completely overlap with the second crack to be identified or the first hidden crack to be identified completely overlaps with other cracks to be identified, it can be determined that the hidden crack to be identified is not a hidden crack. The hidden crack identification method provided in the embodiment of the present application can effectively overcome the limitations of directly comparing cracks in each view and improve the accuracy and reliability of crack detection by first determining the hidden crack based on pixel changes and then making a final confirmation based on the positional relationship. This method combines the advantages of image processing and multi-view analysis and is suitable for complex crack detection tasks.
[0110] Figure 3Schematic diagram of the process of the hidden crack identification method provided in the embodiment of the present application Figure 2 ,like Figure 3 As shown, in this embodiment Figure 2 Based on the embodiment, a method for identifying a hidden crack to be identified and obtaining a hidden crack identification result according to the positional relationship between the first hidden crack to be identified and the second hidden crack to be identified, and the positional relationship with other hidden cracks to be identified in other views of the object to be identified is described in detail. The method includes:
[0111] S301, determining a positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack according to a positional correspondence between the first to-be-identified hidden crack and the second to-be-identified crack;
[0112] S302, determining a positional relationship between the first hidden crack to be identified and other cracks to be identified according to a positional relationship between the first hidden crack to be identified and other cracks to be identified in other views of the object to be identified;
[0113] S303, if the positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack, and the positional relationship between the first to-be-identified hidden crack and other to-be-identified cracks both indicate that the positions correspond and overlap, then a hidden crack identification result indicating that the first to-be-identified hidden crack is a hidden crack is obtained;
[0114] S304: If the positions representing the positional relationship between the first hidden crack to be identified and the second crack to be identified do not overlap correspondingly, and / or the positions representing the positional relationship between the first hidden crack to be identified and other cracks to be identified do not overlap correspondingly, generate and output view display information of the object to be identified.
[0115] Among them, in some embodiments, first, it can be determined whether there is an overlapping or adjacent relationship between the first to-be-identified hidden crack and the second to-be-identified crack according to their relative positions in the same view. If the positions of the two overlap or are very close, this may mean that the first to-be-identified hidden crack is indeed a hidden crack, because hidden cracks are often positionally associated with other more obvious cracks. Then, the positional relationship between the first to-be-identified hidden crack and the cracks detected in other views can be further checked. This step is to verify the possibility that the first to-be-identified hidden crack is a hidden crack, that is, whether it shows a similar positional relationship with other cracks under multiple different viewing angles. Finally, if the positional relationship between the first to-be-identified hidden crack and all other cracks in all relevant views shows that they overlap or are adjacent, then it can be confirmed that the first to-be-identified hidden crack is a hidden crack. Therefore, the result confirming that the first to-be-identified hidden crack is a hidden crack can be output. On the contrary, if it is found in any view that the positional relationship between the first to-be-identified hidden crack and the known crack does not meet expectations (i.e., does not overlap or is far away), it cannot be determined that the first to-be-identified hidden crack is a hidden crack. At this time, the view display information of the object to be identified can be generated and output for manual review or further analysis.
[0116] Figure 4 A schematic diagram of the structure of a hidden crack identification device provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the hidden crack identification device 40 provided in this embodiment includes:
[0117] A first determination module 401 is used to determine a first crack to be identified in a first view of the object to be identified, and a second crack to be identified in a second view;
[0118] A second determination module 402 is used to determine a hidden crack to be identified in the first crack to be identified according to a pixel change of the first crack to be identified in the first view when the position of the first crack to be identified does not correspond to the position of the second crack to be identified;
[0119] The obtaining module 403 is used to identify the hidden crack to be identified according to the positional relationship between the first hidden crack to be identified and the second hidden crack to be identified, and the positional relationship with other hidden cracks to be identified in other views of the object to be identified, to obtain a hidden crack identification result.
[0120] In a possible implementation manner, the first determining module 401 may also be specifically configured to:
[0121] Identify a first view of the object to be identified, and determine a first crack to be identified in the first view;
[0122] Determine, according to the first view, a second view that satisfies the viewing angle relationship;
[0123] The second view is identified to determine a second crack to be identified in the second view.
[0124] In a possible implementation manner, the first determining module 401 may also be specifically configured to:
[0125] Capturing images of the object to be identified to obtain video images of the object to be identified at various viewing angles;
[0126] Generate a view of the object to be identified according to the video images of the object to be identified at various viewing angles;
[0127] The first view and the second view in the view are identified and processed to determine a first crack to be identified in the first view and a second crack to be identified in the second view.
[0128] In a possible implementation manner, the first determining module 401 may also be specifically configured to:
[0129] Determine the type of object to be identified;
[0130] Adjusting the shooting parameters of the video image according to the type of the object to be identified;
[0131] After adjusting the shooting parameters, the image of the object to be identified is collected to obtain video images of the object to be identified at various viewing angles.
[0132] In a possible implementation manner, the second determining module 402 may also be specifically configured to:
[0133] Determine, according to the pixel value of the pixel point of the first crack to be identified in the first view, a pixel change condition representing a brightness change of the pixel point;
[0134] A first hidden crack to be identified in the first cracks to be identified is determined according to a pixel change condition representing a brightness change of the pixel point.
[0135] In a possible implementation manner, the second determining module 402 may also be specifically configured to:
[0136] According to the pixel value of the pixel of the first crack to be identified in the first view, the gradient strength of the pixel is determined; according to the gradient strength of the pixel, the pixel change condition representing the brightness change of the pixel is determined.
[0137] In a possible implementation, the obtaining module 403 may also be specifically used for:
[0138] Determine the positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack according to the positional correspondence between the first to-be-identified hidden crack and the second to-be-identified crack;
[0139] Determine the positional relationship between the first hidden crack to be identified and the other cracks to be identified according to the positional relationship between the first hidden crack to be identified and other cracks to be identified in other views of the object to be identified;
[0140] If the positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack, and the positional relationship between the first to-be-identified hidden crack and other to-be-identified cracks both represent corresponding overlap of positions, then a hidden crack identification result representing that the first to-be-identified hidden crack is a hidden crack is obtained.
[0141] In a possible implementation, the obtaining module 403 may also be specifically used for:
[0142] If the positions representing the positional relationship between the first hidden crack to be identified and the second crack to be identified do not overlap correspondingly, and / or the positions representing the positional relationship between the first hidden crack to be identified and other cracks to be identified do not overlap correspondingly, then view display information of the object to be identified is generated and output.
[0143] The hidden crack identification device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be described in detail here.
[0144] Figure 5 This is a schematic diagram of the structure of the hidden crack identification device provided in the embodiment of the present application. Figure 5 As shown, the hidden crack identification device 50 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the hidden crack identification device 50 also includes a communication component 503. The processor 501, the memory 502 and the communication component 503 are connected via a bus 504.
[0145] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that at least one processor 501 executes the above method.
[0146] The specific implementation process of the processor 501 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.
[0147] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.
[0148] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.
[0149] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.
[0150] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.
[0151] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.
[0152] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.
[0153] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.
[0154] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.
[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0157] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0158] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.
[0159] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.
Claims
1. A method for identifying hidden cracks, characterized in that: The method comprises: Determining a first crack to be identified in a first view of the object to be identified, and a second crack to be identified in a second view; When the position of the first crack to be identified does not correspond to the position of the second crack to be identified, determining a hidden crack to be identified in the first crack to be identified according to a change in pixels of the first crack to be identified in the first view; The hidden crack to be identified is identified according to the positional relationship between the first hidden crack to be identified and the second hidden crack to be identified, as well as the positional relationship between the first hidden crack to be identified and other cracks to be identified in other views of the object to be identified, to obtain a hidden crack identification result.
2. The method according to claim 1, characterized in that The determining a first crack to be identified in a first view of the object to be identified and a second crack to be identified in a second view includes: Identify a first view of the object to be identified, and determine a first crack to be identified in the first view; Determine, according to the first view, a second view that satisfies the viewing angle relationship; The second view is identified to determine a second crack to be identified in the second view.
3. The method according to claim 1, characterized in that The determining a first crack to be identified in a first view of the object to be identified and a second crack to be identified in a second view includes: Capturing images of the object to be identified to obtain video images of the object to be identified at various viewing angles; Generate a view of the object to be identified according to the video images of the object to be identified at each viewing angle; Recognition processing is performed on a first view and a second view in the views to determine a first crack to be identified in the first view and a second crack to be identified in the second view.
4. The method according to claim 3, characterized in that Capturing images of the object to be identified to obtain video images of the object to be identified at various viewing angles includes: Determining the type of the object to be identified; Adjusting shooting parameters of the video image according to the type of the object to be identified; After adjusting the shooting parameters, the image of the object to be identified is collected to obtain video images of the object to be identified at various viewing angles.
5. The method according to claim 1, characterized in that The determining, according to pixel changes of the first crack to be identified in the first view, a hidden crack to be identified in the first crack to be identified, comprises: Determining, according to a pixel value of a pixel point of the first crack to be identified in the first view, a pixel change condition representing a brightness change of the pixel point; A first hidden crack to be identified among the first cracks to be identified is determined according to a pixel change condition that characterizes a brightness change of the pixel point.
6. The method according to claim 5, characterized in that The determining, according to the pixel value of the pixel point of the first crack to be identified in the first view, a pixel change condition representing a brightness change of the pixel point includes: According to the pixel value of the pixel of the first crack to be identified in the first view, the gradient strength of the pixel is determined; according to the gradient strength of the pixel, the pixel change condition representing the brightness change of the pixel is determined.
7. The method according to claim 1, characterized in that The step of identifying the hidden crack to be identified based on the positional relationship between the first hidden crack to be identified and the second hidden crack to be identified, and the positional relationship between the first hidden crack to be identified and other cracks to be identified in other views of the object to be identified, to obtain a hidden crack identification result, includes: Determining a positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack according to a positional correspondence between the first to-be-identified hidden crack and the second to-be-identified crack; Determining the positional relationship between the first to-be-identified hidden crack and the other to-be-identified cracks according to the positional relationship between the first to-be-identified hidden crack and other to-be-identified cracks in other views of the to-be-identified object; If the positional relationship between the first to-be-identified hidden crack and the second to-be-identified crack, and the positional relationship between the first to-be-identified hidden crack and the other to-be-identified cracks both indicate corresponding overlap of positions, then a hidden crack identification result indicating that the first to-be-identified hidden crack is a hidden crack is obtained.
8. The method according to claim 7, characterized in that The method further comprises: If the positional relationship representation positions of the first to-be-identified hidden crack and the second to-be-identified crack do not overlap correspondingly, and / or the positional relationship representation positions of the first to-be-identified hidden crack and the other to-be-identified cracks do not overlap correspondingly, then the view display information of the to-be-identified object is generated and output.
9. A hidden crack identification device, characterized in that: include: A first determination module, used to determine a first crack to be identified in a first view of the object to be identified, and a second crack to be identified in a second view; a second determination module, configured to determine, when the position of the first crack to be identified does not correspond to the position of the second crack to be identified, a hidden crack to be identified in the first crack to be identified according to a pixel change of the first crack to be identified in the first view; The obtaining module is used to identify the hidden crack to be identified according to the positional relationship between the first hidden crack to be identified and the second hidden crack to be identified, and the positional relationship between the first hidden crack to be identified and other cracks to be identified in other views of the object to be identified, so as to obtain a hidden crack identification result.
10. A device for identifying hidden cracks, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 8.