Detection device, surface defect detection method, device, equipment and storage medium

Abstract

The invention discloses a detection device, a surface defect detection method, a surface defect detection device, surface defect detection equipment and a storage medium, relates to the technical field of automobiles, and aims to solve the problem that the subsequent processing effect of a product is poor due to the fact that the defect identification accuracy is low and the grade of the product cannot be accurately determined when defects on the surface of the product are manually detected. The device comprises a fixed table used for placing a to-be-detected object; the plurality of visual sensors are used for shooting image data of different parts of the surface of the to-be-detected object; the controller is connected with the plurality of visual sensors and is used for acquiring image data of different parts of the surface of the to-be-detected object; obtaining defect identification results of different parts of the surface of the to-be-detected image based on the image data of the different parts of the surface of the to-be-detected object; and outputting the defect grade of the to-be-detected object based on the defect identification results of different parts on the surface of the to-be-detected image.

Description

Technical Field

[0001] The present invention relates to the field of automobile technology, and in particular to a detection device, a surface defect detection method, a device, a device and a storage medium. Background Art

[0002] In the process of processing products of different materials (such as semiconductor crystal products), each process will cause defects on the product surface. Different defects on the product surface will lead to different product grades, and different grades of products require different processing techniques in the subsequent process. Therefore, accurately detecting defects on the product surface and determining the product grade are crucial to improving the quality of downstream processes and reducing the processing costs of downstream processes. Currently, when detecting defects on the surface of an object, it is possible to rely on manual identification of defects on the product surface by naked eyes under strong lighting conditions to determine the product grade.

[0003] However, when manually inspecting defects on the surface of a product, the accuracy of identifying defects with the naked eye is low, and different people may identify different defects, which makes it impossible to accurately determine the grade of the product, resulting in poor subsequent processing effects of the product. This results in low accuracy in detecting defects. Summary of the invention

[0004] The purpose of the present invention is to provide a detection device, a surface defect detection method, a device, an equipment and a storage medium, aiming to solve the problem that when manually detecting defects on the surface of a product, the accuracy of identifying defects is low, and the grade of the product cannot be accurately determined, resulting in poor subsequent processing effects of the product.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme:

[0006] In a first aspect, a detection device is provided, which includes: a fixed table for placing an object to be detected; a plurality of visual sensors, which are used to capture image data of different parts of the surface of the object to be detected; a controller connected to the plurality of visual sensors, and used to obtain image data of different parts of the surface of the object to be detected; based on the image data of different parts of the surface of the object to be detected, defect recognition results of different parts of the surface of the image to be detected are obtained; based on the defect recognition results of different parts of the surface of the image to be detected, the defect level of the object to be detected is output.

[0007] In some embodiments, the fixed table includes: a table top, an air path connector and a vacuum air source; an air path groove is provided on the table top; the air path groove is connected to the vacuum air source through the air path connector; the vacuum air source generates negative pressure, which is transmitted to the air path groove through the air path connector, so that the table top adsorbs the object to be detected.

[0008] In some embodiments, the fixed platform further includes: a rotary motor, which is disposed below the table top, and the rotary motor rotates to drive the table top and the object to be detected on the table top to rotate.

[0009] In some embodiments, the multiple visual sensors include at least: a first visual sensor, a second visual sensor and a third visual sensor; the detection end of the first visual sensor is opposite to a first part of the object to be detected, so that the first visual sensor collects image data of the first part; the first part includes the upper surface and the top edge of the object to be detected; the detection end of the second visual sensor is opposite to a second part of the object to be detected, so that the second visual sensor collects image data of the second part; the second part includes the lower surface and the bottom edge of the object to be detected; the detection end of the third visual sensor is opposite to the second part of the object to be detected, so that the third visual sensor collects image data of the third part; the third part includes the side of the object to be detected.

[0010] In some embodiments, the image data of the first part and the second part are two-dimensional image data; and the image data of the third part are two-dimensional image data and three-dimensional image data.

[0011] In some embodiments, the detection device further includes: a plurality of light sources; the plurality of light sources are used to illuminate the object to be detected.

[0012] In some embodiments, the multiple light sources include at least: a first light source and a second light source; the light outlet of the first light source is opposite to a first part of the object to be detected, so that the first light source illuminates the first part; the first part includes the upper surface and top edge of the object to be detected; the light outlet of the second light source is opposite to a second part of the object to be detected, so that the second light source illuminates the second part; the second part includes the lower surface and bottom edge of the object to be detected.

[0013] In some embodiments, the defect identification result includes at least one of the following: the number of defects, the size of the defects, the type of defects, and the location of the defects.

[0014] In a second aspect, a surface defect detection method is provided, the method comprising: acquiring image data of different parts of the surface of the object to be detected during rotation of the object to be detected; obtaining defect recognition results of different parts of the surface of the image to be detected based on the image data of different parts of the surface of the object to be detected; and outputting the defect level of the object to be detected based on the defect recognition results of different parts of the surface of the image to be detected.

[0015] In some embodiments, different parts of the surface of the object to be detected include: a first part, a second part and a third part; the first part includes the upper surface and top edge of the object to be detected; the second part includes the lower surface and bottom edge of the object to be detected; the third part includes the side of the object to be detected.

[0016] In some embodiments, the image data of the first part and the second part are two-dimensional image data; and the image data of the third part are two-dimensional image data and three-dimensional image data.

[0017] In some embodiments, the defect identification result includes at least one of the following: the number of defects, the size of the defects, the type of defects, and the location of the defects.

[0018] In some embodiments, based on image data of different parts of the surface of the object to be inspected, defect recognition results of different parts of the image surface to be inspected are obtained, including: based on the detection algorithms corresponding to the image data of different parts, the image data of different parts are analyzed and processed to obtain defect recognition results of different parts.

[0019] According to a third aspect, a surface defect detection device is provided, which includes: a transmission module and a processing module; the transmission module is used to obtain image data of different parts of the surface of the object to be detected during the rotation of the object to be detected; the processing module is used to obtain defect recognition results of different parts of the surface of the image to be detected based on the image data of different parts of the surface of the object to be detected; the processing module is also used to output the defect level of the object to be detected based on the defect recognition results of different parts of the surface of the image to be detected.

[0020] In some embodiments, different parts of the surface of the object to be detected include: a first part, a second part and a third part; the first part includes the upper surface and top edge of the object to be detected; the second part includes the lower surface and bottom edge of the object to be detected; the third part includes the side of the object to be detected.

[0021] In some embodiments, the image data of the first part and the second part are two-dimensional image data; and the image data of the third part are two-dimensional image data and three-dimensional image data.

[0022] In some embodiments, the defect identification result includes at least one of the following: the number of defects, the size of the defects, the type of defects, and the location of the defects.

[0023] In some embodiments, the processing module is further used to analyze and process the image data of different parts based on the detection algorithms corresponding to the image data of different parts, so as to obtain defect recognition results of different parts.

[0024] In a fourth aspect, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the method of the above-mentioned second aspect and any possible implementation manner thereof.

[0025] In a fifth aspect, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method of the above-mentioned second aspect and any possible implementation manner thereof.

[0026] In a sixth aspect, a computer program product is provided, which includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the method of the second aspect and any possible implementation manner thereof.

[0027] The present application provides a detection device, wherein multiple visual sensors of the detection device can capture image data of different parts of the surface of an object to be detected placed on a fixed table. Further, the controller of the detection device can obtain defect recognition results of different parts based on the image data of different parts, and output the defect level of the object to be detected based on the defect recognition results of different parts.

[0028] That is, usually, the defects of different parts of the surface of the object to be inspected are different. Therefore, the corresponding parts can be photographed by a visual sensor that matches the parts to obtain more accurate defect recognition results. The defect recognition results of different parts can reflect the degree of defects in different parts. The greater the degree of defects, the higher the defect level, which is convenient for subsequent processing of the object to be inspected according to the defect level and improves the effect of subsequent processing. It solves the technical problem that when manually detecting defects on the surface of products, the accuracy of identifying defects is low, and the level of the product cannot be accurately determined, resulting in poor subsequent processing effects of the product, thereby improving the accuracy of defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 A schematic diagram of the structure of a detection device provided in one embodiment of the present application;

[0031] Figure 2 A structural schematic diagram of a fixing platform provided for one embodiment of the present application;

[0032] Figure 3 A schematic diagram of the structure of an object to be detected provided in one embodiment of the present application;

[0033] Figure 4 A schematic diagram of the structure of a surface defect detection system provided for one embodiment of the present application;

[0034] Figure 5 A schematic diagram of a surface defect detection method provided in an embodiment of the present application Figure 1 ;

[0035] Figure 6 A schematic diagram of a surface defect detection method provided in an embodiment of the present application Figure 2 ;

[0036] Figure 7 A software architecture diagram of a surface defect detection method provided for an embodiment of the present application;

[0037] Figure 8 A block diagram of a surface defect detection device provided for one embodiment of the present application;

[0038] Fig. 9 A block diagram of an electronic device provided for one embodiment of the present application. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0041] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. It can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] In the embodiments of the present invention, the terms "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, article or device including the element.

[0043] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0044] In the description of this specification, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0045] In the process of product processing, defects are inevitable in every step. If defective products flow into the next step, it will cause waste of production resources and costs. Therefore, timely detection of defective products is extremely important for reducing the cost of product processing.

[0046] Ingots are the most upstream products in the processing of semiconductor crystal products, and are also one of the most important process links for semiconductor crystal products. Different surface defects will lead to different grades of ingots, and the subsequent processing techniques of ingots of different grades are quite different. Therefore, timely detection of ingot defects and accurate determination of ingot grades are crucial to improving the quality of downstream processes and reducing the processing costs of downstream processes. In the existing ingot processing process, ingot defects are mainly detected by manual visual identification under strong lighting conditions. This method is not only inefficient, but also has poor consistency.

[0047] In view of the above problems, a surface defect detection method provided in an embodiment of the present application can obtain visual information of different parts of the ingot surface by collecting images of different parts of the ingot surface through multiple visual sensors installed at different positions, and can detect different types of surface defects on the ingot surface by fusing and comprehensively analyzing multiple defect detection algorithms corresponding to multiple visual sensors, thereby being able to detect different types of defects in different parts of the ingot surface, and to achieve the classification of ingot grades in the case of multiple parts and multiple defects. In addition, in the process of collecting the image of the ingot surface, a specific method is used to stably fix the ingot to avoid the position movement of the ingot during the image collection process, thus avoiding the risk of damage to the ingot due to the ingot falling and improving the stability of data collection. In addition, not only can the two-dimensional image of the ingot surface be collected by the visual sensor, but also the three-dimensional image of the ingot surface can be collected, thereby improving the accuracy of defect detection.

[0048] In other words, the present application can stably and accurately collect surface information of different parts and dimensions of the ingot surface, and combine multiple detection algorithms for comprehensive detection and analysis, so as to accurately detect different types of defects in different parts of the ingot surface, and can accurately determine the production grade of the ingot according to the type of ingot surface defect, which provides an important basis for subsequently improving the quality of downstream processes and reducing the processing costs of downstream processes.

[0049] Figure 1 The following is a schematic diagram of a detection device provided in one embodiment of the present application. Figure 1 As shown, the detection device 10 includes: a fixing platform 11, a visual sensor 12, a visual sensor 13, a visual sensor 14, a controller 15, an object to be detected 16, a light source 17 and a light source 18.

[0050] The present application provides a detection device, the detection device 10 comprising: a fixed table 11 for placing an object to be detected 16; a plurality of visual sensors for capturing image data of different parts of the surface of the object to be detected 16; a controller 15, which is connected to the plurality of visual sensors (i.e. Figure 1 The visual sensor 12, the visual sensor 13 and the visual sensor 14 are connected to obtain image data of different parts of the surface of the object to be detected 16. Based on the image data of different parts of the surface of the object to be detected 16, the defect recognition results of different parts of the surface of the image to be detected 16 are obtained. Based on the defect recognition results of different parts of the surface of the image to be detected 16, the defect level of the object to be detected is output.

[0051] Optionally, the object to be detected 16 may be a columnar semiconductor crystal product, such as polycrystalline silicon, single crystal silicon, silicon carbide and other crystals. The image data may include two-dimensional image data and three-dimensional image data. The image data may be image data processed by an image processing operation, and the image processing operation may include operations such as editing and fusion.

[0052] The defect recognition result may include at least one of the following: the number of defects, the size of the defects, the type of defects, and the location of the defects. The size of the defects may be the average diameter of the defects. The type of defects may be convexities, concavities, cracks, or bright spots.

[0053] The controller 15 can obtain the score of a part of a certain inspection object according to the score of each defect recognition result of the part and the weight of each defect recognition result. Further, the scores of each part of different parts are added together to obtain the total score of the object to be inspected, and the defect level of the object to be inspected is obtained according to the total score of the object to be inspected.

[0054] For example, it is assumed that the multiple visual sensors may be 3 visual sensors, namely Figure 1 The visual sensor 12, the visual sensor 13, and the visual sensor 14 in the apparatus are shown in FIG. Then the visual sensor 12 can obtain image data of the first portion of the surface of the object to be detected 16. The visual sensor 13 can obtain image data of the second portion of the surface of the object to be detected 16. The visual sensor 14 can obtain image data of the third portion of the surface of the object to be detected 16.

[0055] Then, suppose that when the number of defects is 0 to 5, the score is 3; when the number of defects is 6 to 10, the score is 5; when the number of defects is more than 10, the score is 10. Suppose that when the average diameter of the defects is 0 to 0.5 microns, the score is 3; when the average diameter of the defects is 0.6 to 1 micron, the score is 5; when the average diameter of the defects is more than 1 micron, the score is 10. When the type of defect is a bright spot, the score is 3; when the type of defect is a convex or concave, the score is 5; when the type of defect is a crack, the score is 10. When the location of the defect is in the central area, the score is 10; when the location of the defect is in the edge area, the score is 5.

[0056] Then, assuming that the number of defects in the first part is 3, the average diameter of the defects is 1.7 microns, the type of defects is cracks, and the location of the defects is in the center of the first part, the score of the first part is 3+5+10+10=28 points. Similarly, if the score of the second part is 20 points and the score of the third part is 25 points, the total score of the object to be tested is 28+20+25=75 points.

[0057] Then, assuming that when the score of the object to be tested is 0 to 40 points, the defect level of the object to be tested is level one; when the score of the object to be tested is 41 to 80 points, the defect level of the object to be tested is level two; when the score of the object to be tested is 81 to 120 points, the defect level of the object to be tested is level three. Then the defect level of the object to be tested is level two.

[0058] It should be noted that the determination of the defect level of the object to be inspected is usually closely related to parameters such as the number of defects, the size of defects, the type of defects and the location of defects of the object to be inspected. Therefore, by comprehensively analyzing parameters such as the number of defects, the size of defects, the type of defects and the location of defects of the object to be inspected, a reasonable determination of the level of the object to be inspected can be made.

[0059] The grade of the object to be detected can provide an important basis for subsequently improving the quality of downstream processes and reducing the processing costs of downstream processes. When the grade of the object to be detected is high (for example, the grade of the object to be detected is level one), the quality of the downstream process needs to be high, and the processing cost of the downstream process will also be high. When the grade of the object to be detected is low (for example, the grade of the object to be detected is level three), the quality of the downstream process can be low, and the processing cost of the downstream process will also be low.

[0060] As a possible implementation, Figure 2 A structural diagram of a fixed platform provided in one embodiment of the present application. Figure 2 As shown, the fixed table 11 includes: a table top 111, an air path connector 112 and a vacuum air source 113; an air path groove 1111 is provided on the table top 111; the air path groove 1111 is connected to the vacuum air source 113 through the air path connector 112; the vacuum air source 113 generates negative pressure, which is transmitted to the air path groove 1111 through the air path connector 112, so that the table top 111 adsorbs the object to be detected 16.

[0061] The present application can fix the ingot by adsorbing the object to be detected through a fixed platform, thereby preventing the ingot from moving or falling during the process of the visual sensor collecting the image of the object to be detected, resulting in inaccurate image acquisition, or the ingot from falling and causing damage, thereby improving the stability of data acquisition.

[0062] As a possible implementation, Figure 2 As shown, the fixed platform 11 further includes: a rotary motor 114 , which is disposed below the table 111 , and the rotary motor 114 rotates to drive the table 111 and the object to be detected 16 on the table 111 to rotate.

[0063] The present application can rotate the object to be inspected at a certain speed through a rotating motor, thereby ensuring that the visual sensor system can collect image data at different positions on the surface of the object to be inspected, that is, collect complete image data on the surface of the object to be inspected, thereby improving the accuracy of subsequent detection of defects in the object to be inspected.

[0064] As a possible implementation, Figure 1 As shown, the multiple visual sensors include at least: a first visual sensor (ie, visual sensor 12 ), a second visual sensor (ie, visual sensor 13 ) and a third visual sensor (ie, visual sensor 14 ).

[0065] Figure 3 A schematic diagram of a structure of an object to be detected is provided in one embodiment of the present application. Figure 3 As shown, the object to be detected 16 includes a first part, a second part and a third part. The first part includes an upper surface 161 and a top edge 162 of the object to be detected 16. The second part includes a lower surface 163 and a bottom edge 164 of the object to be detected 16. The third part includes a side surface 165 of the object to be detected 16.

[0066] The detection end of the first visual sensor is opposite to the first part of the object to be detected 16, so that the first visual sensor collects image data of the first part. The detection end of the second visual sensor is opposite to the second part of the object to be detected, so that the second visual sensor collects image data of the second part. The detection end of the third visual sensor is opposite to the second part of the object to be detected, so that the third visual sensor collects image data of the third part. The third part includes the side of the object to be detected.

[0067] Optionally, the first visual sensor may be an industrial camera, the second visual sensor may be an industrial camera, and the first visual sensor and the second visual sensor have different parameters. The third visual sensor may be a line scan camera.

[0068] It should be noted that since the reflective properties, smoothness and other characteristics of different parts of the object to be detected are different, the visual sensors used to collect data from different parts are also different. Using a visual sensor that matches the characteristics of a certain part to collect image data of that part can improve the accuracy of the collected image data.

[0069] The present application can collect images of different parts of the surface of the object to be inspected through multiple visual sensors, and can comprehensively obtain visual information of different parts, thereby improving the accuracy of subsequent detection of defects of the object to be inspected and determining the grade of the object to be inspected.

[0070] As a possible implementation manner, the image data of the first part and the second part are two-dimensional image data; and the image data of the third part are two-dimensional image data and three-dimensional image data.

[0071] Optionally, the first visual sensor and the second visual sensor may be used to collect two-dimensional image data. The third visual sensor may be used to collect two-dimensional image data and three-dimensional image data.

[0072] The two-dimensional image data of the first part and the second part may be image data containing two-dimensional information such as color and brightness. The two-dimensional image data of the third part may be a grayscale image containing two-dimensional information such as brightness, and the three-dimensional image data may be a depth image containing three-dimensional information such as depth and point cloud. The image data of the third part may be image data obtained by image fusion of the grayscale image of the third part and the depth image of the third part.

[0073] The present application can utilize the characteristics of the side of the object to be detected to collect two-dimensional image data and three-dimensional image data of the side of the object to be detected, and obtain fused image data, so as to better present the surface defect characteristics of the object to be detected. In addition, by collecting two-dimensional image data and three-dimensional image data of the surface of the ingot through a visual sensor, the accuracy of defect detection can be improved.

[0074] As a possible implementation, the detection device 10 further includes: a plurality of light sources; the plurality of light sources are used to illuminate the object to be detected.

[0075] like Figure 1 As shown, the multiple light sources may be two light sources, namely Figure 1 The light source 17 and the light source 18 in FIG.

[0076] Optionally, multiple light sources may be adjusted to appropriate lighting conditions respectively.

[0077] The light source in the present application can provide lighting conditions, thereby improving the accuracy of image data collected by the visual sensor.

[0078] As a possible implementation, Figure 1 As shown, the multiple light sources at least include: a first light source (i.e., light source 17) and a second light source (i.e., light source 18). The light outlet of the first light source is opposite to the first part of the object to be detected, so that the first light source illuminates the first part. The first part includes the upper surface and the top edge of the object to be detected. The light outlet of the second light source is opposite to the second part of the object to be detected, so that the second light source illuminates the second part. The second part includes the lower surface and the bottom edge of the object to be detected.

[0079] It should be noted that the industrial camera used to collect image data of the first part and the second part needs to be illuminated by a light source in order to accurately collect image data of the corresponding parts, while the line scan camera used to collect image data of the third part can accurately collect image data of the corresponding part without the need for light source illumination.

[0080] The present application can use corresponding light sources for lighting according to the characteristics of the visual sensor, thereby improving the accuracy of image data collected by the visual sensor.

[0081] Figure 4 A schematic diagram of the structure of a surface defect detection system provided for one embodiment of the present application; Figure 4 As shown, the surface defect detection system 20 (i.e., the controller) includes: an object fixing module 21 to be detected, a motor control module 22, a visual sensor control module 23, a light source control module 24, a defect detection module 25, an image fusion module 26 and a defect analysis module 27.

[0082] The visual sensor control module 23 includes: a first visual sensor control module 231, a second visual sensor control module 232 and a third visual sensor control module 233. The light source control module 24 includes: a first light source control module 241 and a second light source control module 242. The defect detection module 25 includes: a first defect detection module 251, a second defect detection module 252 and a third defect detection module 253.

[0083] The object fixing module 21 is used to control the fixing table to adsorb the object to be detected; the motor control module 22 is used to control the rotation of the rotary motor; the first visual sensor control module 231 is used to control the first visual sensor to capture image data of the first part of the object to be detected; the second visual sensor control module 232 is used to control the second visual sensor to capture image data of the second part of the object to be detected; the third visual sensor control module 233 is used to control the third visual sensor to capture image data of the third part of the object to be detected.

[0084] The first light source control module 241 is used to control the first light source; the second light source control module 242 is used to control the second light source; the first defect detection module 251 is used to detect the image data of the first part taken by the first visual sensor based on the first detection algorithm corresponding to the first visual sensor, and obtain the defect recognition result of the first part; the second defect detection module 252 is used to detect the image data of the second part taken by the second visual sensor based on the second detection algorithm corresponding to the second visual sensor, and obtain the defect recognition result of the second part; the third defect detection module 253 is used to detect the image data of the third part taken by the second visual sensor based on the third detection algorithm corresponding to the third visual sensor, and obtain the defect recognition result of the third part.

[0085] The image fusion module 26 is used to fuse the two-dimensional image data and the three-dimensional image data of the third part to obtain fused image data; the defect analysis module 27 is used to comprehensively analyze the defect recognition results of the first part, the second part and the third part, and output the level of the object to be detected.

[0086] Figure 5 A flow chart of a surface defect detection method provided in an embodiment of the present application is applied to a controller, such as Figure 5 As shown, the surface defect detection method comprises the following steps:

[0087] S301 . Acquire image data of different parts of the surface of the object to be detected during its rotation.

[0088] Optionally, the object fixing module of the controller can control the fixing table to adsorb the object to be detected, and at the same time, the light source control module of the controller can control the light source to turn on to illuminate the object to be detected. The motor control module of the controller can control the rotary motor to start rotating, so as to drive the object to be detected to rotate through the rotary motor. During the rotation of the object to be detected, the visual sensor control module of the controller can control multiple visual sensors to capture image data of different parts of the surface of the object to be detected. Furthermore, the defect detection module of the controller can obtain image data of different parts of the surface of the object to be detected.

[0089] Exemplarily, the image data of different parts of the surface of the object to be detected may be image data collected during the process of the object to be detected rotating for one, two, three or other full cycles.

[0090] S302 , based on the image data of different parts of the surface of the object to be detected, obtain defect recognition results of different parts of the surface of the image to be detected.

[0091] Optionally, the defect identification result may include at least one of the following: the number of defects, the size of defects, the type of defects and the location of defects.

[0092] The defect detection module of the controller can perform image processing operations on image data of different parts to obtain image data processed by the image processing operations.

[0093] Based on the image data of different parts after the image processing operation, the defect detection module of the controller can obtain defect recognition results of different parts of the surface of the image to be detected through a detection algorithm.

[0094] In one possible implementation, Figure 6 A schematic diagram of a process for detecting surface defects provided by an embodiment of the present application is shown in FIG. Figure 6 As shown, the above step S302 specifically includes the following steps:

[0095] S401 , analyzing and processing the image data of different parts based on the detection algorithms corresponding to the image data of different parts, to obtain defect recognition results of different parts.

[0096] Optionally, based on the detection algorithms corresponding to the image data of different parts, the defect analysis module of the controller can analyze and process the image data of different parts to obtain defect recognition results of different parts.

[0097] Exemplarily, assuming that the multiple visual sensors include a first visual sensor, a second visual sensor, and a third visual sensor, then the detection algorithm corresponding to the first visual sensor may be a first detection algorithm, the detection algorithm corresponding to the second visual sensor may be a second detection algorithm, and the detection algorithm corresponding to the third visual sensor may be a third detection algorithm.

[0098] It should be noted that the image data of different parts are obtained by taking different visual sensors, and the image data taken by different visual sensors need to be analyzed and processed by the detection algorithms corresponding to the visual sensors to improve the accuracy of defect recognition.

[0099] The present application can detect defects in different images based on images collected by multiple visual sensors through detection algorithms, obtain defect recognition results for different parts, and improve the accuracy of defect recognition.

[0100] S303: output the defect level of the object to be inspected based on the defect recognition results of different parts of the surface of the image to be inspected.

[0101] Optionally, based on the defect recognition results of different parts of the surface of the image to be inspected, the defect analysis module of the controller can output the defect level of the object to be inspected.

[0102] In one possible implementation, different parts of the surface of the object to be detected include: a first part, a second part and a third part; the first part includes the upper surface and top edge of the object to be detected; the second part includes the lower surface and bottom edge of the object to be detected; and the third part includes the side of the object to be detected.

[0103] Optionally, the object fixing module of the controller can control the fixing platform to absorb the object to be detected, and at the same time, the first light source control module of the controller can control the first light source to turn on to illuminate the first part. The second light source control module of the controller can control the second light source to turn on to illuminate the second part.

[0104] Furthermore, the motor control module of the controller can control the rotary motor to start rotating, so as to drive the object to be detected to rotate through the rotary motor, and at the same time, the first visual sensor control module of the controller can control the first visual sensor to capture image data of a first part of the object to be detected. The second visual sensor control module of the controller can control the second visual sensor to capture image data of a second part of the object to be detected. The third visual sensor control module of the controller can control the third visual sensor to capture image data of a third part of the object to be detected.

[0105] Furthermore, the first defect detection module of the controller can detect the image data of the first part taken by the first visual sensor based on the first detection algorithm corresponding to the first visual sensor, and obtain the defect recognition result of the first part. The second defect detection module of the controller can detect the image data of the second part taken by the second visual sensor based on the second detection algorithm corresponding to the second visual sensor, and obtain the defect recognition result of the second part. The third defect detection module of the controller can detect the image data of the third part taken by the second visual sensor based on the third detection algorithm corresponding to the third visual sensor, and obtain the defect recognition result of the third part.

[0106] In a possible implementation manner, the image data of the first part and the second part are two-dimensional image data; and the image data of the third part are two-dimensional image data and three-dimensional image data.

[0107] Optionally, for the image data of the third part, the image fusion module of the controller may fuse the two-dimensional image data and the three-dimensional image data of the third part to obtain fused image data, so as to obtain a defect recognition result of the third part based on the fused image data.

[0108] It should be noted that in the process of acquiring surface images of objects to be inspected based on multiple visual sensors, and in the process of detecting surface defects using multiple detection algorithms, in order to ensure that each step can be performed synchronously, a multi-threaded parallel approach needs to be adopted in the software architecture.

[0109] In one possible embodiment, Figure 7 A software architecture diagram of a surface defect detection method provided for an embodiment of the present application, such as Figure 7 As shown, the software architecture diagram includes: 1 main thread and 3 sub-threads (i.e., sub-thread 1, sub-thread 2, and sub-thread 3).

[0110] Complete the initialization of software and hardware in the main thread, and start sub-thread 1, sub-thread 2 and sub-thread 3. Further, in the main thread, the fixed platform is controlled to adsorb the object to be detected through the object fixing module, and at the same time, in sub-thread 1, the first light source is controlled to turn on through the first light source control module, and in sub-thread 2, the second light source is controlled to turn on through the second light source control module. Further, in the main thread, the rotary motor is controlled to start rotating through the motor control module, and at the same time, in sub-thread 1, the first visual sensor control module is controlled to start periodically capturing the image data of the first part, in sub-thread 2, the second visual sensor control module is controlled to start periodically capturing the image data of the second part, and, in sub-thread 3, the third visual sensor control module is controlled to start periodically capturing the two-dimensional image data and three-dimensional image data of the third part.

[0111] Furthermore, when the rotary motor completes a full rotation, in the main thread, the motor control module is used to control the rotary motor to stop rotating. At the same time, in sub-thread 1, the first visual sensor control module is used to control the first visual sensor to stop capturing image data of the first part. In sub-thread 2, the second visual sensor control module is used to control the second visual sensor to stop capturing image data of the second part. Moreover, in sub-thread 3, the third visual sensor control module is used to control the third visual sensor to stop capturing two-dimensional image data and three-dimensional image data of the third part.

[0112] Further, in sub-thread 1, the first light source is controlled to be turned off by the first light source control module, and at the same time, in sub-thread 2, the second light source is controlled to be turned off by the second light source control module. And, in sub-thread 3, the two-dimensional image data and the three-dimensional image data of the third part are fused by the image fusion module to obtain fused image data. Further, in sub-thread 1, the image data of the first part is detected by the first detection algorithm of the first defect detection module to obtain the defect recognition result of the first part, and at the same time, in sub-thread 2, the image data of the second part is detected by the second detection algorithm of the second defect detection module to obtain the defect recognition result of the second part, and in sub-thread 3, the fused image data is detected by the third detection algorithm of the third defect detection module to obtain the defect recognition result of the third part. Further, in the main thread, the defect recognition results of the first part, the second part and the third part are comprehensively analyzed by the defect analysis module, and the level of the object to be detected is output.

[0113] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of the method. In order to achieve the above functions, the surface defect detection device or electronic device includes a hardware structure and / or software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0114] The embodiment of the present application can exemplarily divide the functional modules of the surface defect detection device or electronic device according to the above method. For example, the surface defect detection device or electronic device can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0115] Figure 8 A block diagram of a surface defect detection device provided in accordance with an embodiment of the present application. Figure 8 The surface defect detection device 110 includes: a transmission module 1101 and a processing module 1102.

[0116] The transmission module 1101 is used to obtain image data of different parts of the surface of the object to be detected during the rotation of the object to be detected. The processing module 1102 is used to obtain defect recognition results of different parts of the surface of the image to be detected based on the image data of different parts of the surface of the object to be detected. The processing module 1102 is also used to output the defect level of the object to be detected based on the defect recognition results of different parts of the surface of the image to be detected.

[0117] In some embodiments, different parts of the surface of the object to be detected include: a first part, a second part and a third part; the first part includes the upper surface and top edge of the object to be detected; the second part includes the lower surface and bottom edge of the object to be detected; the third part includes the side of the object to be detected.

[0118] In some embodiments, the image data of the first part and the second part are two-dimensional image data; and the image data of the third part are two-dimensional image data and three-dimensional image data.

[0119] In some embodiments, the defect identification result includes at least one of the following: the number of defects, the size of the defects, the type of defects, and the location of the defects.

[0120] In some embodiments, the processing module 1102 is further used to analyze and process the image data of different parts based on the detection algorithms corresponding to the image data of different parts, so as to obtain defect recognition results of different parts.

[0121] Fig. 9 A block diagram of an electronic device provided in accordance with an embodiment of the present application. Fig. 9 As shown, the electronic device 130 includes but is not limited to: a processor 1301 and a memory 1302 .

[0122] The memory 1302 is used to store executable instructions of the processor 1301. It can be understood that the processor 1301 is configured to execute instructions to implement the surface defect detection method in the above embodiment.

[0123] It should be noted that those skilled in the art can understand that Fig. 9 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and the electronic device may include Fig. 9 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0124] The processor 1301 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 1302, and calling data stored in the memory 1302, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 1301 may include one or more processing modules. Optionally, the processor 1301 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1301.

[0125] The memory 1302 may be used to store software programs and various data. The memory 1302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one functional module (such as an acquisition unit, a determination module, a processing unit, etc.), etc. In addition, the memory 1302 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0126] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 1302 including instructions, and the above instructions can be executed by the processor 1301 of the electronic device 130 to implement the surface defect detection method in the above embodiment.

[0127] In actual implementation, Figure 8 The functions of the transmission module 1101 and the processing module 1102 in Fig. 9 The processor 1301 in the embodiment calls the computer program stored in the memory 1302. The specific execution process can refer to the description of the surface defect detection method in the above embodiment, which will not be repeated here.

[0128] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0129] In an exemplary embodiment, the present application also provides a computer program product including one or more instructions, which can be executed by the processor 1301 of the electronic device to complete the surface defect detection method in the above embodiment.

[0130] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned surface defect detection method embodiment are implemented, and the same technical effect as the above-mentioned surface defect detection method can be achieved. To avoid repetition, they will not be repeated here.

[0131] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0132] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0134] In addition, each functional unit in each embodiment of the present application 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0135] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, RAM, disk or CD and other media that can store program code.

[0136] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A detection device, characterized in that: The detection device comprises: A fixed table for placing the object to be detected; A plurality of visual sensors, wherein the plurality of visual sensors are used to capture image data of different parts of the surface of the object to be detected; A controller is connected to the multiple visual sensors and is used to obtain image data of different parts of the surface of the object to be detected; based on the image data of different parts of the surface of the object to be detected, defect recognition results of different parts of the surface of the image to be detected are obtained; based on the defect recognition results of different parts of the surface of the image to be detected, the defect level of the object to be detected is output.

2. The detection device according to claim 1, characterized in that: The fixed table includes: a table top, an air path connector and a vacuum air source; an air path groove is provided on the table top; the air path groove is connected to the vacuum air source through the air path connector; the vacuum air source generates negative pressure, which is transmitted to the air path groove through the air path connector, so that the table top adsorbs the object to be detected.

3. The detection device according to claim 2, characterized in that: The fixed platform also includes: A rotary motor is disposed below the table top, and the rotary motor rotates to drive the table top and the object to be detected on the table top to rotate.

4. The detection device according to claim 1, characterized in that: The plurality of visual sensors at least include: a first visual sensor, a second visual sensor and a third visual sensor; The detection end of the first visual sensor is opposite to the first part of the object to be detected, so that the first visual sensor collects image data of the first part; the first part includes the upper surface and the top edge of the object to be detected; The detection end of the second visual sensor is opposite to the second part of the object to be detected, so that the second visual sensor collects image data of the second part; the second part includes the lower surface and the bottom edge of the object to be detected; The detection end of the third visual sensor is opposite to the second part of the object to be detected, so that the third visual sensor collects image data of the third part; the third part includes the side of the object to be detected.

5. The detection device according to claim 4, characterized in that: The image data of the first part and the second part are two-dimensional image data; the image data of the third part are two-dimensional image data and three-dimensional image data.

6. The detection device according to claim 1, characterized in that: The detection device further includes: a plurality of light sources; the plurality of light sources are used to illuminate the object to be detected.

7. The detection device according to claim 6, characterized in that: The multiple light sources include at least: a first light source and a second light source; a light outlet of the first light source is opposite to a first part of the object to be detected, so that the first light source illuminates the first part; the first part includes an upper surface and a top edge of the object to be detected; a light outlet of the second light source is opposite to a second part of the object to be detected, so that the second light source illuminates the second part; the second part includes a lower surface and a bottom edge of the object to be detected.

8. The detection device according to claim 1, characterized in that: The defect identification result includes at least one of the following: the number of defects, the size of defects, the type of defects and the location of defects.

9. A surface defect detection method, characterized in that: The method comprises: During the rotation of the object to be detected, image data of different parts of the surface of the object to be detected are obtained; Based on the image data of different parts of the surface of the object to be detected, defect recognition results of different parts of the surface of the image to be detected are obtained; Based on the defect recognition results of different parts of the surface of the image to be detected, the defect level of the object to be detected is output.

10. The method according to claim 9, characterized in that The different parts of the surface of the object to be detected include: a first part, a second part and a third part; the first part includes the upper surface and top edge of the object to be detected; the second part includes the lower surface and bottom edge of the object to be detected; the third part includes the side of the object to be detected.

11. The method according to claim 10, characterized in that The image data of the first part and the second part are two-dimensional image data; the image data of the third part are two-dimensional image data and three-dimensional image data.

12. The method according to claim 9, characterized in that The defect identification result includes at least one of the following: the number of defects, the size of defects, the type of defects and the location of defects.

13. The method according to claim 9, characterized in that The defect recognition results of different parts of the surface of the image to be detected are obtained based on the image data of different parts of the surface of the object to be detected, including: Based on the detection algorithms corresponding to the image data of the different parts, the image data of the different parts are analyzed and processed to obtain defect recognition results of the different parts.

14. A surface defect detection device, characterized in that: The device comprises a transmission module and a processing module; The transmission module is used to obtain image data of different parts of the surface of the object to be detected during the rotation of the object to be detected. The processing module is used to obtain defect recognition results of different parts of the surface of the image to be detected based on the image data of different parts of the surface of the object to be detected; The processing module is further used to output the defect level of the object to be detected based on the defect recognition results of different parts of the surface of the image to be detected.

15. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method as claimed in any one of claims 9 to 13.

16. A computer-readable storage medium, characterized in that: When the computer-executable instructions stored in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is capable of performing the method as claimed in any one of claims 9 to 13.

17. A computer program product, characterized in that The computer program product comprises computer instructions, and when the computer instructions are executed on an electronic device, the electronic device performs the method according to any one of claims 9 to 13.

Images