Defect detection method, device, system, and storage medium

Abstract

This invention discloses a defect detection method, apparatus, system, and storage medium. The method is applied to a defect detection system, which includes a camera ring-shaped fixed guide rail, a camera sliding module, a camera, a support platform, and a material to be inspected. The camera sliding module is connected to the camera ring-shaped fixed guide rail and the camera. The support platform supports the material to be inspected. The defect detection method includes: upon receiving a defect detection command, determining the camera's shooting position; controlling the camera to move to the shooting position to capture an image to be inspected; and performing defect detection on the image to be inspected to obtain a defect detection result. Because this invention allows the camera to be moved to the shooting position via the camera ring-shaped fixed guide rail to capture an image to be inspected, and then performs defect detection on that image, this invention can complete omnidirectional inspection of the material to be inspected through the camera ring-shaped fixed guide rail, improving inspection efficiency.

Description

Technical Field

[0001] This invention relates to the field of defect detection technology, and in particular to a defect detection method, apparatus, system and storage medium. Background Technology

[0002] To detect specific defects in screens and assemblies, traditional defect detection methods require installing a fixed camera at a specific location to capture images, followed by conventional image processing. However, these methods cannot achieve comprehensive inspection of screens and assemblies of various sizes. When different types of defects need to be detected, cameras need to be installed at different locations on the production line. Traditional methods cannot meet actual production needs in terms of detection methods and efficiency, and cannot simultaneously capture and detect various defect types.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a defect detection method, apparatus, system, and storage medium, aiming to solve the technical problem of low efficiency in defect detection in the prior art.

[0005] To achieve the above objectives, the present invention provides a defect detection method applied to a defect detection system. The defect detection system includes a camera annular fixed guide rail, a camera sliding module, a camera, a support platform, and a material to be inspected. The camera sliding module is connected to the camera annular fixed guide rail and the camera. The support platform is used to support the material to be inspected. The defect detection method includes the following steps:

[0006] Upon receiving a defect detection command, the camera's shooting position is determined;

[0007] The camera is controlled to move to the shooting position to take a picture and obtain the image to be detected;

[0008] Defect detection is performed on the image to be detected to obtain the defect detection results.

[0009] Optionally, after the step of performing defect detection on the image to be detected and obtaining the defect detection result, the method further includes:

[0010] Based on the defect detection results, defects are marked on the image to be detected to obtain the target image;

[0011] The target image is stitched together using a preset image stitching algorithm to obtain the all-round defect detection results of the material to be inspected.

[0012] Optionally, the step of stitching the target image using a preset image stitching algorithm includes:

[0013] Select a reference image from the target image;

[0014] Feature points are extracted from the reference image and the target image adjacent to the reference image to obtain image feature points;

[0015] Feature point matching is performed on the image feature points to obtain a feature point mapping matrix;

[0016] The reference image and the target image adjacent to the reference image are stitched together according to the feature point mapping matrix to obtain the stitched image;

[0017] The stitched image is used as the reference image, and the process returns to the step of extracting feature points from the reference image and the target image adjacent to the reference image to obtain image feature points.

[0018] Optionally, the step of performing defect detection on the image to be detected and obtaining defect detection results includes:

[0019] Determine the category of the image to be detected;

[0020] Defect detection is performed on the image to be detected according to its category to obtain an edge image;

[0021] The target contour of the material to be inspected is determined based on the edge image;

[0022] The defect detection result is determined based on the target contour and the preset comparison contour.

[0023] Optionally, the step of performing defect detection on the image to be detected according to the category of the image to be detected to obtain an edge image includes:

[0024] When the image to be detected is a screen image, edge-preserving filtering is performed on the image to be detected to obtain a filtered image;

[0025] The filtered image is contrast-enhanced to obtain the enhanced image;

[0026] Edges are extracted from the stretched image using a preset Sobel operator to obtain an edge image.

[0027] Optionally, the step of performing defect detection on the image to be detected according to the category of the image to be detected to obtain an edge image includes:

[0028] When the image to be detected is an assembly image, edge-preserving filtering is performed on the image to be detected to obtain a filtered image;

[0029] Edge extraction is performed on the filtered image using a preset Canny operator to obtain an edge image.

[0030] Optionally, the step of determining the camera's shooting position upon receiving a defect detection command includes:

[0031] Upon receiving a defect detection instruction, the size information of the material to be inspected is determined based on the defect detection instruction;

[0032] The camera's shooting position is determined based on the size information and the diameter of the camera's annular fixed guide rail.

[0033] Furthermore, to achieve the above objectives, the present invention also provides a defect detection device, the device comprising:

[0034] The shooting position determination module is used to determine the shooting position of the camera when a defect detection command is received;

[0035] The shooting module is used to control the camera to move to the shooting position to take a picture and obtain the image to be detected;

[0036] The defect detection module is used to perform defect detection on the image to be detected and obtain the defect detection result.

[0037] Furthermore, to achieve the above objectives, the present invention also proposes a defect detection system, characterized in that the system includes: a camera ring-shaped fixed guide rail, a camera sliding module, a camera, a support platform, and a material to be inspected; the camera sliding module is connected to the camera ring-shaped fixed guide rail and the camera; the support platform is used to support the material to be inspected; the system further includes: a memory, a processor, and a defect detection program stored in the memory and executable on the processor; the defect detection program is configured to implement the steps of the defect detection method described above.

[0038] In addition, to achieve the above objectives, the present invention also proposes a storage medium storing a defect detection program, which, when executed by a processor, implements the steps of the defect detection method described above.

[0039] This invention relates to a defect detection method applied to a defect detection system. The system includes a camera ring-shaped fixed guide rail, a camera sliding module, a camera, a support platform, and a material to be inspected. The camera sliding module is connected to the camera ring-shaped fixed guide rail and the camera. The support platform supports the material to be inspected. The defect detection method includes: upon receiving a defect detection command, determining the camera's shooting position; controlling the camera to move to the shooting position to capture an image to be inspected; and performing defect detection on the image to be inspected to obtain a defect detection result. Because this invention allows the camera to be moved to the shooting position via the camera ring-shaped fixed guide rail to capture an image to be inspected, and then performs defect detection on that image, this invention enables omnidirectional inspection of the material to be inspected via the camera ring-shaped fixed guide rail, improving inspection efficiency. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the structure of a defect detection device for the hardware operating environment involved in the embodiments of the present invention;

[0041] Figure 2 This is a flowchart illustrating the first embodiment of the defect detection method of the present invention;

[0042] Figure 3 This is a schematic diagram of a defect detection system according to an embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of the camera sliding area according to an embodiment of the defect detection method of the present invention;

[0044] Figure 5 This is a flowchart illustrating the second embodiment of the defect detection method of the present invention;

[0045] Figure 6 This is a flowchart illustrating the third embodiment of the defect detection method of the present invention;

[0046] Figure 7 This is a structural block diagram of the first embodiment of the defect detection device of the present invention.

[0047] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0048] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0049] Reference Figure 1 , Figure 1 This is a schematic diagram of the defect detection device structure of the hardware operating environment involved in the embodiment of the present invention.

[0050] like Figure 1As shown, the defect detection device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0051] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the defect detection equipment and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0052] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a defect detection program.

[0053] exist Figure 1 In the defect detection device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the defect detection device of the present invention can be set in the defect detection device, and the defect detection device calls the defect detection program stored in the memory 1005 through the processor 1001 and executes the defect detection method provided in the embodiment of the present invention.

[0054] Based on the aforementioned defect detection equipment, this embodiment of the invention provides a defect detection method, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the defect detection method of the present invention.

[0055] In this embodiment, the defect detection method is applied to a defect detection system, which includes a camera ring-shaped fixed guide rail, a camera sliding module, a camera, a support platform, and a material to be inspected. The camera sliding module is connected to the camera ring-shaped fixed guide rail and the camera, and the support platform is used to support the material to be inspected.

[0056] It should be noted that this can be referred to Figure 3 , Figure 3 This is a schematic diagram of a defect detection system according to an embodiment of the present invention. The defect detection system includes: an industrial control computer, a switch, a PLC, a camera ring-shaped fixed guide rail, a camera sliding module, a top camera, a bottom camera, a horizontal camera 1, a horizontal camera 2, a top side camera 1, a top side camera 2, a bottom side camera 1, a bottom side camera 2, a support platform, and the material to be inspected.

[0057] The material to be inspected is placed on the screen support platform; the camera's circular fixed guide rail surrounds both the support platform and the material. The top camera, bottom camera, horizontal camera 1, and horizontal camera 2 are all fixed to the camera's circular fixed guide rail. The top side camera 1, top side camera 2, bottom side camera 1, and bottom side camera 2 are all fixed to the camera's circular fixed guide rail via camera sliding modules and can slide to any position on the camera's circular fixed guide rail. Network connection cables, camera power cables, and PLC control cables are installed on the camera's circular fixed guide rail. All cameras are connected to a switch via network connection cables, the camera sliding modules are connected to the switch via PLC control cables, and the switch is connected to an industrial control computer via network connection cables. The top camera captures an image of the material to be inspected facing upwards; the bottom camera captures an image of the material to be inspected facing downwards; horizontal cameras 1 and 2 capture images of the left and right vertical surfaces of the material to be inspected; top side cameras 1 and 2 capture images of the material to be inspected facing upwards at a vertical angle; and bottom side cameras 1 and 2 capture images of the material to be inspected facing downwards at a vertical angle.

[0058] The defect detection method includes the following steps:

[0059] Step S10: Upon receiving a defect detection instruction, determine the shooting position of the camera.

[0060] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a mobile phone, tablet computer, or personal computer, or an electronic device or defect detection device capable of performing the above functions. The following description uses the defect detection device as an example to illustrate this embodiment and the subsequent embodiments.

[0061] It should be noted that the defect detection command can be a command triggered by the user through an industrial control computer to detect the material to be inspected. The shooting position can be the shooting position of the top side camera 1, the top side camera 2, the bottom side camera 1, and the bottom side camera 2.

[0062] Furthermore, in order to improve the efficiency of defect detection, step S10 may include: upon receiving a defect detection instruction, determining the size information of the material to be inspected based on the defect detection instruction; and determining the shooting position of the camera based on the size information and the diameter of the camera's annular fixed guide rail.

[0063] It should be noted that the size information of the material to be inspected can be the width of the material. The determination of the camera's shooting position based on the size information and the diameter of the camera's annular fixed guide rail can be achieved by determining the shooting positions of the top side camera 1, top side camera 2, bottom side camera 1, and bottom side camera 2 using the following formula:

[0064]

[0065] Among them, roundup() is used to represent the rounding up operation, D p The degree value used to characterize the camera position, R is used to characterize the radius of the camera's annular fixed guide rail, and w is used to characterize the width of the material to be inspected.

[0066] It should be noted that, in order to detect defects in materials of different sizes, the positions of the top side camera 1, top side camera 2, bottom side camera 1, and bottom side camera 2 need to be determined based on the dimensions of the materials. The radius of the camera ring-shaped fixing guide rail is R, dividing the entire camera ring-shaped fixing guide rail into four areas, each occupying a 90-degree range, as shown in the reference. Figure 4 , Figure 4 This is a schematic diagram of the camera sliding area according to an embodiment of the defect detection method of the present invention. The width of the material to be inspected is w. First, a camera position lookup table is generated for the four areas of the camera's annular fixed guide rail. The generated camera position lookup table is shown below:

[0067]

[0068] As shown in the table above and Figure 4As shown, each region is divided into four sectors by dashed lines, with each sector having an angle of 15 degrees. The left side of the lookup table represents the position code that the PLC can recognize, and the right side represents the degree value. For example, for region 1, the position code corresponding to 0-15 degrees is 1, 16-30 degrees is 2, 31-45 degrees is 3, and 46-60 degrees is 4. For region 1, the degree value starts from the vertical direction, with counterclockwise as positive, and the position code corresponding to 0-15 degrees is 1; for region 2, the degree value starts from the vertical direction, with clockwise as positive, and the position code corresponding to 0-15 degrees is 1; for region 3, the degree value starts from the vertical direction, with clockwise as positive, and the position code corresponding to 0-15 degrees is 1; for region 4, the degree value starts from the vertical direction, with counterclockwise as positive, and the position code corresponding to 0-15 degrees is 1. For example, in region 1, starting vertically and moving counter-clockwise, a camera anchor point is set every 15 degrees, resulting in a total of 4 camera anchor points in region 1. During each detection, the camera simply needs to be moved to the required anchor point. Other regions follow the same rules to set up a camera anchor point lookup table.

[0069] In practice, the shooting positions of the top side camera 1, top side camera 2, bottom side camera 1, and bottom side camera 2 are determined using the above formula. The obtained shooting positions are in degrees. The position code is then obtained by looking up the camera position lookup table based on the degree information, and subsequently, the top side camera 1, top side camera 2, bottom side camera 1, and bottom side camera 2 are controlled to slide to the corresponding positions. For example, if the width of the material to be inspected is 30 and the radius of the camera's circular fixed guide rail is 50, substituting w / 2R*60 gives a result of 18. Rounding 18 up according to the camera position lookup table gives a degree result of 30. The position code corresponding to degree 30 is then determined to be 2. Therefore, the top side camera 1, top side camera 2, bottom side camera 1, and bottom side camera 2 are moved to the area corresponding to position code 2 for shooting.

[0070] Step S20: Control the camera to move to the shooting position to take a picture and obtain the image to be detected.

[0071] It should be noted that controlling the camera to move to the shooting position to take a picture and obtain the image to be detected can be achieved by controlling the top side camera 1, top side camera 2, bottom side camera 1 and bottom side camera 2 to move to the corresponding shooting positions to take a picture, and controlling the top camera, horizontal camera 1, horizontal camera 2 and bottom camera to take pictures at the corresponding positions to obtain multiple images to be detected.

[0072] Step S30: Perform defect detection on the image to be detected and obtain the defect detection result.

[0073] It should be noted that the defect detection of the image to be detected may involve extracting features from the image to be detected, obtaining image features, comparing the image features with the image features of a pre-set normal device, and determining the defect detection result.

[0074] This embodiment includes determining the camera's shooting position upon receiving a defect detection command; controlling the camera to move to the shooting position to capture an image to be inspected; and performing defect detection on the image to be inspected to obtain a defect detection result. Because this embodiment allows the camera to be moved to the shooting position via a camera ring-shaped fixed guide rail to capture the image to be inspected, and then performing defect detection on that image, this embodiment can achieve omnidirectional inspection of the material to be inspected through the camera ring-shaped fixed guide rail, improving inspection efficiency.

[0075] refer to Figure 5 , Figure 5 This is a flowchart illustrating the second embodiment of the defect detection method of the present invention.

[0076] Based on the first embodiment described above, in this embodiment, step S30 includes:

[0077] Step S301: Determine the category of the image to be detected.

[0078] It should be noted that this embodiment performs omnidirectional inspection of the material to be inspected. The images to be inspected are different depending on the shooting angle. The image to be inspected is an image of a certain side of the material to be inspected. In order to improve the efficiency of defect detection, this embodiment determines the category of each image to be inspected, so as to detect the image to be inspected according to the category of the image to be inspected, thereby improving the accuracy of the detection results of the image to be inspected.

[0079] Step S302: Perform defect detection on the image to be detected according to the category of the image to be detected to obtain an edge image.

[0080] It should be noted that the step of performing defect detection on the image to be detected according to the category of the image to be detected and obtaining an edge image can be performed as follows: when the image to be detected is a screen image, the image to be detected is subjected to edge-preserving filtering to obtain a filtered image; the contrast of the filtered image is increased to obtain an increased image; and the edge is extracted from the increased image according to a preset Sobel operator to obtain an edge image.

[0081] It should be noted that the preset Sobel operator can be the Sobel operator. The Sobel operator is primarily used to obtain the first-order gradient of a digital image. The Sobel operator calculates the weighted difference between the gray values ​​of each pixel's four neighborhoods (top, bottom, left, and right) and reaches an extreme value at the edge to detect edges. This yields the edge image of the image. The edge-preserving filtering of the image to be detected can be performed using methods such as Gaussian bilateral filtering or mean shift filtering.

[0082] In specific implementation, in order to improve the efficiency of defect detection, step S302 may include: when the image to be detected is an assembly image, performing edge-preserving filtering on the image to be detected to obtain a filtered image; and performing edge extraction on the filtered image according to a preset Canny operator to obtain an edge image.

[0083] It should be noted that the preset Canny operator can be the Canny edge detection operator, which can be a multi-level edge detection algorithm used to perform multi-level edge detection on an image.

[0084] Step S303: Determine the target contour of the material to be inspected based on the edge image.

[0085] It should be noted that determining the target contour of the material to be inspected based on the edge image can be achieved by extracting the contour information of the material to be inspected from the edge image. The target contour includes information such as the contrast between the inside and outside of the contour, the size of the contour, and the position of the contour.

[0086] Step S304: Determine the defect detection result based on the target contour and the preset comparison contour.

[0087] It should be noted that the preset comparison contour can be a pre-determined contour information of the material to be inspected under normal conditions. Determining the defect detection result based on the target contour and the preset comparison contour can involve comparing the target contour and the preset comparison contour, and determining the defect detection result based on the comparison result.

[0088] This embodiment determines the category of the image to be inspected; performs defect detection on the image to be inspected according to the category to obtain an edge image; determines the target contour of the material to be inspected based on the edge image; and determines the defect detection result based on the target contour and a preset contrast contour. This embodiment performs defect detection on the material to be inspected based on images acquired from different orientations, which can improve the accuracy of the defect detection results.

[0089] refer to Figure 6 , Figure 6This is a flowchart illustrating the third embodiment of the defect detection method of the present invention.

[0090] Based on the above embodiments, in this embodiment, after step S30, the method further includes:

[0091] Step S40: Mark defects on the image to be detected according to the defect detection results to obtain the target image.

[0092] It should be noted that marking defects on the image to be detected based on the defect detection results can be done by marking the defects in the defect detection results on the corresponding image to be detected to obtain the target image.

[0093] Step S50: Use a preset image stitching algorithm to stitch the target image to obtain the all-round defect detection results of the material to be inspected.

[0094] It should be noted that the method of stitching the target image using a preset image stitching algorithm can be to use an existing image fusion algorithm to stitch together target images acquired by cameras from different directions and which have been marked with defects, in order to obtain a comprehensive defect detection image result of the material to be inspected.

[0095] Furthermore, to make the defect detection results more intuitive and facilitate users in viewing the comprehensive defect detection results of the material to be inspected, the step of stitching the target image using a preset image stitching algorithm may include: selecting a reference image from the target image; extracting feature points from the reference image and the target images adjacent to the reference image to obtain image feature points; performing feature point matching on the image feature points to obtain a feature point mapping matrix; stitching the reference image and the target images adjacent to the reference image according to the feature point mapping matrix to obtain a stitched image; using the stitched image as the reference image, and returning to the step of extracting feature points from the reference image and the target images adjacent to the reference image to obtain image feature points.

[0096] It should be noted that the reference image can be the image selected from the target images for initial image stitching. For example, the target image acquired by the horizontal camera 1 and marked with defects is used as the reference image. In the first stitching process, the target image corresponding to the horizontal camera 1 and the target image corresponding to the top side camera 1 adjacent to the horizontal camera are acquired. Feature points are extracted from these two target images to obtain image feature points. Feature point matching is performed on the image feature points to obtain a feature point mapping matrix. The reference image and the target images adjacent to the reference image are stitched together according to the feature point mapping matrix to obtain the stitched image. At this time, the stitched image is an image that only stitches together the target images corresponding to the horizontal camera 1 and the top side camera 1. To obtain a comprehensive defect detection image of the material to be inspected, further stitching is required. That is, according to the adjacent image order, the target images corresponding to the top camera, top side camera 2, horizontal camera 2, bottom side camera 2, bottom camera, and bottom side camera 1 are stitched together sequentially until a comprehensive defect detection image of the material to be inspected is obtained, that is, the comprehensive defect detection result of the material to be inspected.

[0097] This embodiment selects a reference image from the target image; extracts feature points from the reference image and adjacent target images to obtain image feature points; performs feature point matching on the image feature points to obtain a feature point mapping matrix; stitches the reference image and adjacent target images according to the feature point mapping matrix to obtain a stitched image; uses the stitched image as the reference image, and returns to the step of extracting feature points from the reference image and adjacent target images to obtain image feature points. This embodiment, through the above method, can stitch together target images to obtain comprehensive defect detection results for the material to be inspected.

[0098] Reference Figure 7 , Figure 7 This is a structural block diagram of the first embodiment of the defect detection device of the present invention.

[0099] like Figure 7 As shown, the defect detection device proposed in this embodiment of the invention includes:

[0100] The shooting position determination module 10 is used to determine the shooting position of the camera when a defect detection command is received;

[0101] The shooting module 20 is used to control the camera to move to the shooting position to take a picture and obtain the image to be detected;

[0102] The defect detection module 30 is used to perform defect detection on the image to be detected and obtain the defect detection result.

[0103] This embodiment includes determining the camera's shooting position upon receiving a defect detection command; controlling the camera to move to the shooting position to capture an image to be inspected; and performing defect detection on the image to be inspected to obtain a defect detection result. Because this embodiment allows the camera to be moved to the shooting position via a camera ring-shaped fixed guide rail to capture the image to be inspected, and then performing defect detection on that image, this embodiment can achieve omnidirectional inspection of the material to be inspected through the camera ring-shaped fixed guide rail, improving inspection efficiency.

[0104] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0105] In addition, for technical details not described in detail in this embodiment, please refer to the defect detection method provided in any embodiment of the present invention, which will not be repeated here.

[0106] Based on the first embodiment of the defect detection device of the present invention, a second embodiment of the defect detection device of the present invention is proposed.

[0107] In this embodiment, the defect detection module 30 is further configured to mark defects on the image to be detected based on the defect detection result, thereby obtaining a target image;

[0108] The target image is stitched together using a preset image stitching algorithm to obtain the all-round defect detection results of the material to be inspected.

[0109] Furthermore, the defect detection module 30 is also used to select a reference image from the target image;

[0110] Feature points are extracted from the reference image and the target image adjacent to the reference image to obtain image feature points;

[0111] Feature point matching is performed on the image feature points to obtain a feature point mapping matrix;

[0112] The reference image and the target image adjacent to the reference image are stitched together according to the feature point mapping matrix to obtain the stitched image;

[0113] The stitched image is used as the reference image, and the process returns to the step of extracting feature points from the reference image and the target image adjacent to the reference image to obtain image feature points.

[0114] Furthermore, the defect detection module 30 is also used to determine the category of the image to be detected;

[0115] Defect detection is performed on the image to be detected according to its category to obtain an edge image;

[0116] The target contour of the material to be inspected is determined based on the edge image;

[0117] The defect detection result is determined based on the target contour and the preset comparison contour.

[0118] Furthermore, the defect detection module 30 is also used to perform edge-preserving filtering on the image to be detected when the image to be detected is a screen image, to obtain a filtered image;

[0119] The filtered image is contrast-enhanced to obtain the enhanced image;

[0120] Edges are extracted from the stretched image using a preset Sobel operator to obtain an edge image.

[0121] Furthermore, the defect detection module 30 is also used to perform edge-preserving filtering on the image to be detected when the image to be detected is an assembly image, to obtain a filtered image;

[0122] Edge extraction is performed on the filtered image using a preset Canny operator to obtain an edge image.

[0123] Furthermore, the shooting position determination module 10 is also used to determine the size information of the material to be inspected based on the defect detection instruction when a defect detection instruction is received;

[0124] The camera's shooting position is determined based on the size information and the diameter of the camera's annular fixed guide rail.

[0125] Other embodiments or specific implementations of the defect detection device of the present invention can be referred to the above-described method embodiments, and will not be repeated here.

[0126] Furthermore, embodiments of the present invention also propose a storage medium storing a defect detection program, wherein the defect detection program, when executed by a processor, implements the steps of the defect detection method described above.

[0127] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0128] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0129] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0130] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A defect detection method, characterized in that, The defect detection method is applied to a defect detection system, which includes a camera ring-shaped fixed guide rail, a camera sliding module, a camera, a support platform, and a material to be inspected. The camera sliding module is connected to the camera ring-shaped fixed guide rail and the camera. The support platform is used to support the material to be inspected. The defect detection method includes the following steps: Upon receiving a defect detection command, the camera's shooting position is determined; The camera is controlled to move to the shooting position to capture an image to be detected. Defect detection is performed on the image to be detected to obtain the defect detection results; Determining the camera's shooting position upon receiving a defect detection command includes: Upon receiving a defect detection instruction, the size information of the material to be inspected is determined based on the defect detection instruction; The camera's shooting position is determined based on the size information and the diameter of the camera's annular fixed guide rail; The size information of the material to be inspected includes the width of the material. The shooting positions of the camera, the first top side camera, the second top side camera, the first bottom side camera, and the second bottom side camera are determined based on the size information and the diameter of the camera's annular fixed guide rail using the following formula: in, Used to characterize the rounding up operation. The degree value is used to characterize the camera position, R is used to characterize the radius of the camera's annular fixed guide rail, and w is used to characterize the width of the material to be inspected.

2. The defect detection method as described in claim 1, characterized in that, After the step of performing defect detection on the image to be detected and obtaining the defect detection result, the method further includes: Based on the defect detection results, defects are marked on the image to be detected to obtain the target image; The target image is stitched together using a preset image stitching algorithm to obtain the all-round defect detection results of the material to be inspected.

3. The defect detection method as described in claim 2, characterized in that, The step of stitching the target image using a preset image stitching algorithm includes: Select a reference image from the target image; Feature points are extracted from the reference image and the target image adjacent to the reference image to obtain image feature points; Feature point matching is performed on the image feature points to obtain a feature point mapping matrix; The reference image and the target image adjacent to the reference image are stitched together according to the feature point mapping matrix to obtain the stitched image; The stitched image is used as the reference image, and the process returns to the step of extracting feature points from the reference image and the target image adjacent to the reference image to obtain image feature points.

4. The defect detection method as described in claim 1, characterized in that, The step of performing defect detection on the image to be detected and obtaining defect detection results includes: Determine the category of the image to be detected; Defect detection is performed on the image to be detected according to its category to obtain an edge image; The target contour of the material to be inspected is determined based on the edge image; The defect detection result is determined based on the target contour and the preset comparison contour.

5. The defect detection method as described in claim 4, characterized in that, The step of performing defect detection on the image to be detected according to the category of the image to be detected to obtain an edge image includes: When the image to be detected is a screen image, edge-preserving filtering is performed on the image to be detected to obtain a filtered image; The filtered image is contrast-enhanced to obtain the enhanced image; Edges are extracted from the stretched image using a preset Sobel operator to obtain an edge image.

6. The defect detection method as described in claim 4, characterized in that, The step of performing defect detection on the image to be detected according to the category of the image to be detected to obtain an edge image includes: When the image to be detected is an assembly image, edge-preserving filtering is performed on the image to be detected to obtain a filtered image; Edge extraction is performed on the filtered image using a preset Canny operator to obtain an edge image.

7. A defect detection device, characterized in that, The defect detection device includes: The shooting position determination module is used to determine the shooting position of the camera when a defect detection command is received; The shooting module is used to control the camera to move to the shooting position to take a picture and obtain the image to be detected; The defect detection module is used to perform defect detection on the image to be detected and obtain defect detection results; Determining the camera's shooting position upon receiving a defect detection command includes: Upon receiving a defect detection instruction, the size information of the material to be inspected is determined based on the defect detection instruction; The camera's shooting position is determined based on the size information and the diameter of the camera's annular fixed guide rail; The size information of the material to be inspected includes the width of the material. The shooting positions of the camera, the first top side camera, the second top side camera, the first bottom side camera, and the second bottom side camera are determined based on the size information and the diameter of the camera's annular fixed guide rail using the following formula: in, Used to characterize the rounding up operation. The degree value is used to characterize the camera position, R is used to characterize the radius of the camera's annular fixed guide rail, and w is used to characterize the width of the material to be inspected.

8. A defect detection system, characterized in that, The system includes: a camera ring-shaped fixed guide rail, a camera sliding module, a camera, a support platform, and a material to be inspected. The camera sliding module is connected to the camera ring-shaped fixed guide rail and the camera. The support platform is used to support the material to be inspected. The system also includes: a memory, a processor, and a defect detection program stored in the memory and executable on the processor. The defect detection program is configured to implement the steps of the defect detection method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores a defect detection program, which, when executed by a processor, implements the steps of the defect detection method as described in any one of claims 1 to 6.

Images