Defect detection method, device and system

Abstract

The invention discloses a defect detection method, device and system, and belongs to the technical field of defect detection. The method comprises the following steps: acquiring a first detection image of the photovoltaic glass under the condition that the photovoltaic glass runs along a first direction and a light source system irradiating the photovoltaic glass flickers according to frequency; the light source system is used for forming a dark field area and a bright field area of the photovoltaic glass, the first detection image comprises multiple mode images arranged in the second direction, the mode images comprise dark field images and bright field images sequentially arranged in the first direction, the dark field images correspond to the dark field area, and the bright field images correspond to the bright field area; the length of the dark field area in the first direction is 1.5-2.5 times of the length of the bright field area in the first direction, and the first direction intersects with the second direction; removing the bright field images, and splicing the plurality of dark field images to obtain a target detection image; and performing defect detection on the target detection image to obtain a defect detection result. Power consumption of a detection system can be reduced, and detection accuracy is improved.

Description

Technical Field

[0001] The present application belongs to the field of defect detection technology, and in particular, relates to a defect detection method, device and system. Background Art

[0002] With the continuous growth of demand for renewable energy, the photovoltaic industry has developed rapidly. As an important component of solar panels, the quality of photovoltaic glass directly affects the performance and life of the entire photovoltaic module. With the continuous improvement of the production scale of solar rolled glass, the level of production line equipment, and the quality awareness of enterprises in my country, the key to improving the total yield of photovoltaic glass production lines, namely, plate defect detection technology, has become a hot topic in the research field.

[0003] During the production process of solar rolled glass, due to operator errors, incorrect raw material matching, production equipment failures and other reasons, various defects such as bubbles, streak formation, scratches and dirt will occur. Different defects have different physical characteristics, and a single workstation cannot meet the needs of multiple types of defect detection. Therefore, a more advanced detection method is to set up a photovoltaic glass detection system at the process end, and perform multi-mode detection through a camera with multi-light source strobe.

[0004] However, multi-mode detection usually requires multiple light sources to flash multiple times. Too many flashes will increase system power consumption. In addition, the accuracy of defect detection results obtained by using the detection images obtained based on the current light source flash scheme has room for improvement. Summary of the invention

[0005] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes a defect detection method, device and system, which can reduce the power consumption of the detection system and improve the accuracy of the defect detection results.

[0006] In a first aspect, the present application provides a defect detection method, the method comprising:

[0007] When the photovoltaic glass moves along a first direction and a light source system irradiating the photovoltaic glass flashes at a frequency, a first detection image of the photovoltaic glass is acquired;

[0008] The light source system is used to form a dark field area and a bright field area corresponding to the photovoltaic glass, the first detection image includes a plurality of pattern images arranged along the second direction, the pattern images include dark field images and bright field images arranged in sequence along the first direction, the dark field image corresponds to the dark field area, the bright field image corresponds to the bright field area, the length of the dark field area along the first direction is 1.5-2.5 times the length of the bright field area along the first direction, and the first direction intersects with the second direction;

[0009] Removing the bright field image, and combining the plurality of dark field images to obtain a target detection image;

[0010] Defect detection is performed on the target detection image to obtain a defect detection result.

[0011] According to the defect detection method of the present application, by lighting up the photovoltaic glass with three modules as a cycle and two modules at intervals, dark field areas and bright field areas corresponding to the photovoltaic glass are formed, and a first detection image of the photovoltaic glass is obtained. The first detection image includes multiple pattern images arranged along the second direction, and each pattern image includes a dark field image and a bright field image arranged in sequence along the first direction. By increasing the number of dark field areas within a single strobe cycle corresponding to a row of photovoltaic glass, the overall strobe times corresponding to generating the first detection image can be reduced, thereby reducing system power consumption. In addition, the lighting spacing between modules can be reduced, the contrast of defect imaging can be improved, and the accuracy of defect detection results can be improved.

[0012] According to one embodiment of the present application, removing the bright field image includes:

[0013] Determine a plurality of target segmentation points based on grayscale difference information corresponding to the first detection image, wherein the grayscale difference information is used to characterize the grayscale difference between the same coordinate points of each of the pattern images in the first direction;

[0014] Based on the plurality of target segmentation points, the dark field image and the bright field image are segmented from the first detection image, the bright field image is removed, and the dark field image is retained.

[0015] According to an embodiment of the present application, determining a plurality of target segmentation points based on grayscale difference information corresponding to the first detection image includes:

[0016] generating at least one grayscale difference curve corresponding to the first detection image, each grayscale difference curve being used to represent the grayscale difference between the same coordinate points of the two pattern images in the first direction;

[0017] A first function point in the grayscale difference curve is determined as the target segmentation point, wherein a product of two function points adjacent to the first function point is less than 0.

[0018] According to an embodiment of the present application, generating at least one grayscale difference curve corresponding to the first detection image includes:

[0019] Generating a grayscale change curve corresponding to each of the pattern images, wherein the grayscale change curve is used to characterize the grayscale change of the pattern image along a first direction;

[0020] The grayscale difference curve is determined based on the difference between the two grayscale change curves at the same coordinate points in the first direction.

[0021] According to an embodiment of the present application, the positions corresponding to the dark field images in different pattern images are different, and the positions corresponding to the bright field images in different pattern images are different.

[0022] In a second aspect, the present application provides a defect detection device, the device comprising:

[0023] An acquisition module, used for acquiring a first detection image of the photovoltaic glass when the photovoltaic glass moves along a first direction and a light source system irradiating the photovoltaic glass flashes at a frequency;

[0024] The light source system is used to form a dark field area and a bright field area corresponding to the photovoltaic glass, the first detection image includes a plurality of pattern images arranged along the second direction, the pattern images include dark field images and bright field images arranged in sequence along the first direction, the dark field image corresponds to the dark field area, the bright field image corresponds to the bright field area, the length of the dark field area along the first direction is 1.5-2.5 times the length of the bright field area along the first direction, and the first direction intersects with the second direction;

[0025] A first processing module, used for removing the bright field image and combining a plurality of the dark field images to obtain a target detection image;

[0026] The second processing module is used to perform defect detection on the target detection image to obtain a defect detection result.

[0027] According to the defect detection device of the present application, by lighting up the photovoltaic glass with three modules as a cycle and two modules at intervals, dark field areas and bright field areas corresponding to the photovoltaic glass are formed, and a first detection image of the photovoltaic glass is obtained. The first detection image includes multiple pattern images arranged along the second direction, and each pattern image includes a dark field image and a bright field image arranged in sequence along the first direction. By increasing the number of dark field areas within a single strobe cycle corresponding to a row of the photovoltaic glass, the overall strobe times corresponding to the generation of the first detection image can be reduced, thereby reducing system power consumption. In addition, the lighting spacing between modules can be reduced, the contrast of defect imaging can be improved, and the accuracy of defect detection results can be improved.

[0028] In a third aspect, the present application provides a defect detection system, the system comprising:

[0029] A conveying device, the photovoltaic glass is arranged on the conveying device, and the conveying device is used to drive the photovoltaic glass to move along a first direction;

[0030] A light source system, the light source system irradiates the transmission device, and the light source system is used to flash according to a frequency;

[0031] An image acquisition device, wherein the image acquisition device is used to obtain a first detection image of the photovoltaic glass when the transmission device drives the photovoltaic glass to move along the first direction and the light source system flashes at a frequency;

[0032] As in the defect detection device described in the second aspect above, the defect detection device is connected to the image acquisition device.

[0033] According to the defect detection system of the present application, a first detection image of the photovoltaic glass is obtained by lighting up two modules at intervals with three modules as a cycle in the photovoltaic glass to form dark field areas and bright field areas corresponding to the photovoltaic glass. The first detection image includes multiple pattern images arranged along the second direction, and each pattern image includes a dark field image and a bright field image arranged in sequence along the first direction. By increasing the number of dark field areas within a single strobe cycle corresponding to a row of the photovoltaic glass, the overall strobe times corresponding to generating the first detection image can be reduced, thereby reducing system power consumption. In addition, the lighting spacing between modules can be reduced to improve the contrast of defect imaging, thereby improving the accuracy of defect detection results.

[0034] In a fourth aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the defect detection method as described in the first aspect above is implemented.

[0035] In a fifth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the defect detection method as described in the first aspect above is implemented.

[0036] In a sixth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the defect detection method as described in the first aspect above.

[0037] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0039] Figure 1 It is a flowchart of a defect detection method provided in an embodiment of the present application;

[0040] Figure 2 is a schematic diagram of a grayscale change curve provided in an embodiment of the present application;

[0041] Figure 3 is a schematic diagram of a grayscale difference curve provided in an embodiment of the present application;

[0042] Figure 4 is a schematic diagram of target segmentation points provided in an embodiment of the present application;

[0043] Figure 5 It is one of the schematic diagrams of the detection image in the related art;

[0044] Figure 6 is one of the schematic diagrams of the target detection image provided in the embodiment of the present application;

[0045] Figure 7 This is the second schematic diagram of the detection image in the related art;

[0046] Figure 8 This is the second schematic diagram of the target detection image provided in the embodiment of the present application;

[0047] Fig. 9 is a schematic diagram of the structure of a defect detection device provided in an embodiment of the present application;

[0048] Fig.10 is a schematic diagram of the structure of a defect detection system provided in an embodiment of the present application;

[0049] Fig.11 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0050] Reference numerals:

[0051] Transmission device 1001, light source 1002, image acquisition device 1003, photovoltaic glass 1004. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0053] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0054] The defect detection method, defect detection device, defect detection system, electronic device and readable storage medium provided in the embodiments of the present application are described in detail below in combination with the accompanying drawings through specific embodiments and their application scenarios.

[0055] The defect detection method may be applied to a terminal, and may be specifically executed by hardware or software in the terminal.

[0056] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that in some embodiments, the terminal may not be a portable communication device, but a desktop computer with a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0057] In the following various embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse and a joystick.

[0058] The defect detection method provided in the embodiment of the present application may be executed by an electronic device or a functional module or functional entity in the electronic device that can implement the defect detection method. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablet computers, computers, cameras, and wearable devices. The defect detection method provided in the embodiment of the present application is described below using the electronic device as an example of the execution subject.

[0059] like Figure 1 As shown, the defect detection method includes: step 110, step 120 and step 130.

[0060] Step 110 , when the photovoltaic glass 1004 moves along a first direction and a light source system irradiating the photovoltaic glass 1004 flashes at a frequency, a first detection image of the photovoltaic glass 1004 is obtained.

[0061] The light source system is used to form a dark field area and a bright field area corresponding to the photovoltaic glass 1004. The first detection image includes multiple pattern images arranged along the second direction. The pattern images include dark field images and bright field images arranged in sequence along the first direction. The dark field image corresponds to the dark field area, and the bright field image corresponds to the bright field area. The length of the dark field area along the first direction is 1.5-2.5 times the length of the bright field area along the first direction, and the first direction intersects with the second direction.

[0062] The photovoltaic glass 1004 is a glass material disposed on the surface of the solar panel, which can be used as a protective layer for the solar panel and ensure that as much sunlight as possible can be transmitted to be converted into electrical energy.

[0063] In this embodiment, the photovoltaic glass 1004 can be placed on a conveying device 1001 such as a conveyor belt, and the conveyor belt moves in a first direction, driving the photovoltaic glass 1004 to move along the first direction.

[0064] A light source system may be provided above the conveyor belt. The light source system may include a plurality of light sources 1002. Light emitted by the plurality of light sources 1002 may be irradiated toward the photovoltaic glass 1004 on the conveyor belt. The light source system includes a stroboscopic light source, i.e., a light source 1002 that is turned on and off at a set frequency.

[0065] The conveyor belt may also be a light-transmitting structure, and the light source 1002 in the light source system may also be arranged below the conveyor belt, wherein the upper side of the conveyor belt is the side where the photovoltaic glass 1004 is placed, and the lower side of the conveyor belt is the side facing away from the upper side.

[0066] An image acquisition device 1003 such as a camera may be provided above the conveyor belt, with the lens of the camera facing the conveyor belt, so as to photograph the photovoltaic glass 1004 on the conveyor belt.

[0067] In this step, the photovoltaic glass 1004 runs along the first direction, and the light source system flashes at a set frequency. The area of ​​the photovoltaic glass 1004 illuminated by the light source 1002 is the bright field area, and the area not illuminated by the light source 1002 is the dark field area. The camera takes pictures to obtain corresponding bright field images and dark field images.

[0068] The photovoltaic glass 1004 can be divided into multiple rows along the second direction, and each row of the photovoltaic glass 1004 can be subjected to stroboscopic irradiation. The stroboscopic frequency corresponding to each row is the same. A pattern image is obtained by stroboscopic irradiation of one row of the photovoltaic glass 1004. In the first detection image, multiple pattern images are arranged in sequence along the second direction according to the corresponding rows in the photovoltaic glass 1004. Each pattern image includes a dark field image and a bright field image arranged in sequence along the first direction, that is, the dark field image and the bright field image are arranged at intervals.

[0069] In this embodiment, the flashing frequency of the light source system can be determined according to the speed at which the photovoltaic glass 1004 moves along the first direction, thereby ensuring that the length of the dark field area along the first direction is 1.5-2.5 times the length of the bright field area along the first direction.

[0070] For example, the length of the dark field area along the first direction is twice the length of the bright field area along the first direction. The row corresponding to the photovoltaic glass 1004 can be divided into multiple modules, each module has the same length along the first direction, and one module is lit every two modules.

[0071] Step 120: remove the bright field image, and combine multiple dark field images to obtain a target detection image.

[0072] In this embodiment, the bright field image and the dark field image in the first detection image are located, the bright field image is subtracted, the dark field image is retained, and the adjacent dark field images are moved closer to fill the corresponding gaps after the bright field image is subtracted, so that the multiple dark field images are stitched together, and the stitched dark field image is used as the target detection image.

[0073] Step 130: perform defect detection on the target detection image to obtain a defect detection result.

[0074] In this step, after obtaining the target detection image, the target detection image can be preprocessed such as denoising, and defect detection methods such as template matching and deep learning can be used to detect whether the photovoltaic glass 1004 has defects such as bubbles.

[0075] In the related art, four modules are usually used as a cycle, and three modules are lit up at intervals to form bright blocks and dark fields.

[0076] In the embodiment of the present application, three modules are used as a cycle, and two modules are lit up at intervals to form a dark field area and a bright field area. Compared with lighting up three modules at intervals in the related art, the number of dark field areas can be increased within a single strobe cycle corresponding to a row. Photovoltaic glass 1004 of the same specification can reduce the overall strobe times corresponding to generating the first detection image, thereby reducing system power consumption.

[0077] In addition, compared with the related art of lighting up three modules at intervals, lighting up two modules at intervals can reduce the lighting spacing between modules, improve the contrast of defect imaging, and thus improve the accuracy of defect detection results.

[0078] According to the defect detection method provided in the embodiment of the present application, by lighting up the photovoltaic glass 1004 with three modules as a cycle and two modules at intervals, a dark field area and a bright field area corresponding to the photovoltaic glass 1004 are formed, and a first detection image of the photovoltaic glass 1004 is obtained. The first detection image includes a plurality of pattern images arranged along the second direction, and each pattern image includes a dark field image and a bright field image arranged in sequence along the first direction. By increasing the number of dark field areas within a single strobe cycle corresponding to a row of the photovoltaic glass 1004, the overall strobe times corresponding to the generation of the first detection image can be reduced, thereby reducing system power consumption. In addition, the lighting spacing between modules can be reduced, the contrast of defect imaging can be improved, and the accuracy of defect detection results can be improved.

[0079] In some embodiments, removing the bright field image comprises:

[0080] Determining a plurality of target segmentation points based on grayscale difference information corresponding to the first detection image;

[0081] Based on multiple target segmentation points, a dark field image and a bright field image are segmented in the first detection image, the bright field image is removed, and the dark field image is retained.

[0082] The grayscale difference information is used to characterize the grayscale difference between the same coordinate points of each pattern image in the first direction.

[0083] For example, the first detection image includes three pattern images, namely pattern image a, pattern image b and pattern image c. The first direction is the x direction. The grayscale difference information may include the difference in grayscale values ​​between pattern image a and pattern image b at each coordinate point in the x direction, the difference in grayscale values ​​between pattern image a and pattern image c at each coordinate point in the x direction, and the difference in grayscale values ​​between pattern image b and pattern image c at each coordinate point in the x direction.

[0084] It should be noted that the mode image may include multiple pixel points along the second direction, and the grayscale values ​​of the pixel points in the second direction may be averaged to serve as the grayscale value of the corresponding coordinate point of the mode image in the first direction.

[0085] In this embodiment, the coordinate point where the grayscale difference between the two pattern images is within a set range may be determined as the target segmentation point.

[0086] The target segmentation point is positioned at the first detection image, a region of interest (ROI) is cropped in the first detection image, a dark field image and a bright field image are divided, the bright field image is removed, and the dark field image is retained.

[0087] In some embodiments, determining a plurality of target segmentation points based on grayscale difference information corresponding to the first detection image includes:

[0088] Generate at least one grayscale difference curve corresponding to the first detection image, each grayscale difference curve is used to represent the grayscale difference between the same coordinate points of the two pattern images in the first direction;

[0089] A first function point in the grayscale difference curve is determined as a target segmentation point, wherein a product of two function points adjacent to the first function point is less than 0.

[0090] In this embodiment, a plurality of difference points may be obtained by calculating the difference in grayscale values ​​between the same coordinate points of the two pattern images in the first direction, and a grayscale difference curve may be obtained based on the plurality of difference points.

[0091] It can be understood that there is a grayscale difference curve corresponding to each two pattern images. For example, if there are n pattern images, the grayscale difference curve can be

[0092] In this embodiment, the grayscale difference curve includes multiple continuous function points. When the product of two adjacent function points of a function point, that is, the previous function point and the next function point of the function point is a negative number, the function point is the first function point, and the first function point is determined as the target segmentation point.

[0093] In some embodiments, generating at least one grayscale difference curve corresponding to the first detection image includes:

[0094] Generate a grayscale change curve corresponding to each pattern image, where the grayscale change curve is used to characterize the grayscale change of the pattern image along a first direction;

[0095] A grayscale difference curve is determined based on a difference between the two grayscale change curves at the same coordinate points in the first direction.

[0096] The pattern image may include multiple pixel points along the second direction, and the number of pixel points may correspond to the row height. Each pattern image includes the same number of pixel points along the second direction, that is, the row height of each pattern image is the same. According to the row height of the pattern image, multiple pattern images are segmented in the first detection image, and one pattern image corresponds to one stroboscopic cycle.

[0097] The grayscale values ​​of each pixel point in the second direction of the pattern image can be averaged as the grayscale value of the corresponding coordinate point of the pattern image in the first direction, and the grayscale change curve corresponding to the pattern image can be obtained according to the grayscale value of each coordinate point.

[0098] For example, there are 3 pattern images, such as Figure 2 As shown, the three mode images correspond to the light blue grayscale change curve, the light green grayscale change curve and the orange grayscale change curve, respectively.

[0099] The column average grayscale is subjected to differential processing, that is, the values ​​of the two grayscale change curves at the same coordinate points in the first direction are subtracted, and the grayscale difference curve is determined according to the difference values ​​corresponding to each coordinate point, such as Figure 3 As shown, there are red grayscale difference curves, dark green grayscale difference curves and dark blue grayscale difference curves, such as Figure 4 As shown, the red solid points, dark green solid points and dark blue solid points are target segmentation points.

[0100] In this embodiment, the coordinate values ​​corresponding to the target segmentation points can be saved as fusion parameters, the pre-saved fusion parameters can be read through the program, the corresponding dark field areas can be cropped according to the fusion parameters, the beginning and end of each dark field area can be continuously spliced, and finally a complete dark field image, i.e., a target detection image, is generated, and the mode fusion is completed.

[0101] like Figure 5 As shown in FIG. 1 , a detection image is generated in the related art, such as Figure 6 As shown, the target detection image obtained by the present application corresponds to the same photovoltaic glass 1004.

[0102] like Figure 7 As shown in FIG. 1 , a detection image is generated in the related art, such as Figure 8 As shown, the target detection image obtained by the present application corresponds to the same photovoltaic glass 1004.

[0103] It can be seen that the target detection image obtained in the present application has a higher contrast in the defect area than the detection image generated in the related art.

[0104] In some embodiments, the positions corresponding to the dark field images in different pattern images are different, and the positions corresponding to the bright field images in different pattern images are different.

[0105] For example, the first detection image includes two pattern images. The first pattern image can be an arrangement of dark field image, bright field image, dark field image, and bright field image. The second pattern image can be an arrangement of bright field image, dark field image, bright field image, and dark field image. That is, the bright field images and dark field images are alternately arranged between adjacent pattern images, which can avoid the concentration of bright field images, thereby further enhancing the contrast of the defect area.

[0106] The defect detection method provided in the embodiment of the present application can increase the number of dark fields generated in a single strobe cycle and effectively reduce the overall strobe times of the light source system. In combination with the corresponding mode fusion scheme, i.e., a scheme for obtaining a target detection image based on a first detection image, it can effectively improve the imaging contrast of defects such as bubbles without interfering with other defect detection steps, reduce hardware costs, system complexity, overall equipment power consumption, etc., and has good adaptability and scalability.

[0107] The defect detection method provided in the embodiment of the present application can be executed by a defect detection device. In the embodiment of the present application, the defect detection device provided in the embodiment of the present application is described by taking the defect detection method executed by the defect detection device as an example.

[0108] The embodiment of the present application also provides a defect detection device.

[0109] like Fig. 9 As shown, the defect detection device comprises:

[0110] An acquisition module 910 is used to acquire a first detection image of the photovoltaic glass 1004 when the photovoltaic glass 1004 moves along a first direction and a light source system irradiating the photovoltaic glass 1004 flashes at a frequency;

[0111] The light source system is used to form a dark field area and a bright field area corresponding to the photovoltaic glass 1004, the first detection image includes a plurality of pattern images arranged along the second direction, the pattern images include dark field images and bright field images arranged in sequence along the first direction, the dark field image corresponds to the dark field area, the bright field image corresponds to the bright field area, the length of the dark field area along the first direction is 1.5-2.5 times the length of the bright field area along the first direction, and the first direction intersects with the second direction;

[0112] A first processing module 920 is used to remove the bright field image and combine multiple dark field images to obtain a target detection image;

[0113] The second processing module 930 is used to perform defect detection on the target detection image to obtain a defect detection result.

[0114] According to the defect detection device provided in the embodiment of the present application, by lighting up the photovoltaic glass 1004 with three modules as a cycle and two modules at intervals, a dark field area and a bright field area corresponding to the photovoltaic glass 1004 are formed, and a first detection image of the photovoltaic glass 1004 is obtained. The first detection image includes a plurality of pattern images arranged along the second direction, and each pattern image includes a dark field image and a bright field image arranged in sequence along the first direction. By increasing the number of dark field areas within a single strobe cycle corresponding to a row of the photovoltaic glass 1004, the overall strobe times corresponding to the generation of the first detection image can be reduced, thereby reducing system power consumption. In addition, the lighting interval between modules can be reduced, the contrast of defect imaging can be improved, and the accuracy of defect detection results can be improved.

[0115] In some embodiments, the first processing module 920 is used to determine a plurality of target segmentation points based on grayscale difference information corresponding to the first detection image, where the grayscale difference information is used to characterize the grayscale difference between the same coordinate points of each pattern image in the first direction;

[0116] Based on multiple target segmentation points, a dark field image and a bright field image are segmented in the first detection image, the bright field image is removed, and the dark field image is retained.

[0117] In some embodiments, the first processing module 920 is used to generate at least one grayscale difference curve corresponding to the first detection image, each grayscale difference curve is used to represent the grayscale difference between the same coordinate points of two pattern images in the first direction;

[0118] A first function point in the grayscale difference curve is determined as a target segmentation point, wherein a product of two function points adjacent to the first function point is less than 0.

[0119] In some embodiments, the first processing module 920 is used to generate a grayscale change curve corresponding to each pattern image, where the grayscale change curve is used to characterize the grayscale change of the pattern image along the first direction;

[0120] A grayscale difference curve is determined based on a difference between the two grayscale change curves at the same coordinate points in the first direction.

[0121] In some embodiments, the positions corresponding to the dark field images in different pattern images are different, and the positions corresponding to the bright field images in different pattern images are different.

[0122] The defect detection device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0123] The defect detection device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0124] The defect detection device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0125] The embodiment of the present application also provides a defect detection system.

[0126] like Fig.10 As shown, the defect detection system includes a conveying device 1001, a light source system, an image acquisition device 1003 and the above-mentioned defect detection device.

[0127] The photovoltaic glass 1004 is disposed on the conveying device 1001, and the conveying device 1001 is used to drive the photovoltaic glass 1004 to move along a first direction, where the first direction is the x direction.

[0128] The light source system irradiates toward the transmission device 1001 . The light source system is used to flash according to a frequency. The light source system may include a plurality of light sources 1002 .

[0129] The image acquisition device 1003 is used to obtain a first detection image of the photovoltaic glass 1004 when the transmission device 1001 drives the photovoltaic glass 1004 to move along the first direction and the light source system flashes at a frequency.

[0130] The defect detection device is connected to the image acquisition device 1003 .

[0131] According to the defect detection system provided in the embodiment of the present application, by lighting up the photovoltaic glass 1004 with three modules as a cycle and two modules at intervals, a dark field area and a bright field area corresponding to the photovoltaic glass 1004 are formed, and a first detection image of the photovoltaic glass 1004 is obtained. The first detection image includes a plurality of pattern images arranged along the second direction, and each pattern image includes a dark field image and a bright field image arranged in sequence along the first direction. By increasing the number of dark field areas within a single strobe cycle corresponding to a row of the photovoltaic glass 1004, the overall strobe times corresponding to the generation of the first detection image can be reduced, thereby reducing system power consumption. In addition, the lighting interval between modules can be reduced, the contrast of defect imaging can be improved, and the accuracy of defect detection results can be improved.

[0132] In some embodiments, Fig.11 As shown, an embodiment of the present application also provides an electronic device 1100, including a processor 1101, a memory 1102, and a computer program stored in the memory 1102 and executable on the processor 1101. When the program is executed by the processor 1101, each process of the above-mentioned defect detection method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0133] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0134] An embodiment of the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned defect detection method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0135] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0136] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above-mentioned defect detection method when executed by a processor.

[0137] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0138] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned defect detection method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0139] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0140] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, 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, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0142] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0144] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A defect detection method, characterized in that: include: When the photovoltaic glass moves along a first direction and a light source system irradiating the photovoltaic glass flashes at a frequency, a first detection image of the photovoltaic glass is acquired; The light source system is used to form a dark field area and a bright field area corresponding to the photovoltaic glass, the first detection image includes a plurality of pattern images arranged along the second direction, the pattern images include dark field images and bright field images arranged in sequence along the first direction, the dark field image corresponds to the dark field area, the bright field image corresponds to the bright field area, the length of the dark field area along the first direction is 1.5-2.5 times the length of the bright field area along the first direction, and the first direction intersects with the second direction; Removing the bright field image, and combining the plurality of dark field images to obtain a target detection image; Defect detection is performed on the target detection image to obtain a defect detection result.

2. The defect detection method according to claim 1, characterized in that: The removing of the bright field image comprises: Determine a plurality of target segmentation points based on grayscale difference information corresponding to the first detection image, wherein the grayscale difference information is used to characterize the grayscale difference between the same coordinate points of each of the pattern images in the first direction; Based on the plurality of target segmentation points, the dark field image and the bright field image are segmented from the first detection image, the bright field image is removed, and the dark field image is retained.

3. The defect detection method according to claim 2, characterized in that: The step of determining a plurality of target segmentation points based on the grayscale difference information corresponding to the first detection image includes: generating at least one grayscale difference curve corresponding to the first detection image, each grayscale difference curve being used to represent the grayscale difference between the same coordinate points of the two pattern images in the first direction; A first function point in the grayscale difference curve is determined as the target segmentation point, wherein a product of two function points adjacent to the first function point is less than 0.

4. The defect detection method according to claim 3, characterized in that: The generating at least one grayscale difference curve corresponding to the first detection image includes: Generating a grayscale change curve corresponding to each of the pattern images, wherein the grayscale change curve is used to characterize the grayscale change of the pattern image along a first direction; The grayscale difference curve is determined based on the difference between the two grayscale change curves at the same coordinate points in the first direction.

5. The defect detection method according to any one of claims 1 to 4, characterized in that: The positions corresponding to the dark field images in different pattern images are different, and the positions corresponding to the bright field images in different pattern images are different.

6. A defect detection device, characterized in that: include: An acquisition module, used for acquiring a first detection image of the photovoltaic glass when the photovoltaic glass moves along a first direction and a light source system irradiating the photovoltaic glass flashes at a frequency; The light source system is used to form a dark field area and a bright field area corresponding to the photovoltaic glass, the first detection image includes a plurality of pattern images arranged along the second direction, the pattern images include dark field images and bright field images arranged in sequence along the first direction, the dark field image corresponds to the dark field area, the bright field image corresponds to the bright field area, the length of the dark field area along the first direction is 1.5-2.5 times the length of the bright field area along the first direction, and the first direction intersects with the second direction; A first processing module, used for removing the bright field image and combining a plurality of the dark field images to obtain a target detection image; The second processing module is used to perform defect detection on the target detection image to obtain a defect detection result.

7. A defect detection system, characterized in that: include: A conveying device, the photovoltaic glass is arranged on the conveying device, and the conveying device is used to drive the photovoltaic glass to move along a first direction; A light source system, the light source system irradiates the transmission device, and the light source system is used to flash according to a frequency; An image acquisition device, wherein the image acquisition device is used to obtain a first detection image of the photovoltaic glass when the transmission device drives the photovoltaic glass to move along the first direction and the light source system flashes at a frequency; The defect detection device as described in claim 6, wherein the defect detection device is connected to the image acquisition device.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the defect detection method according to any one of claims 1 to 5 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the defect detection method according to any one of claims 1 to 5 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the defect detection method according to any one of claims 1 to 5 is implemented.

Images