Foreign matter detection method for display panel and related device

Abstract

The invention discloses a foreign matter detection method for a display panel and a related device, and relates to the technical field of display, and the method comprises the steps: obtaining a first image which is an image obtained by carrying out the image collection of a to-be-detected display panel; performing foreign matter detection on the first image based on a first detection model, wherein an obtained detection result is used for representing a foreign matter area and / or a suspected foreign matter area existing in the first image; if the suspected foreign matter area exists in the first image, cutting the suspected foreign matter area to obtain a second image of the suspected foreign matter area; conducting particle positioning is conducted on the second image, and a conducting particle positioning result is obtained; and determining whether the suspected foreign matter is the foreign matter of the display panel or not according to the distribution information of the conductive particles in the region of the suspected foreign matter represented by the conductive particle positioning result. According to the invention, foreign matter removal detection based on conductive particle positioning is carried out on the display panel, so that the accuracy of foreign matter detection of the display panel is improved, and false detection is avoided.

Description

Technical Field

[0001] The present application relates to the field of display technology, and in particular to a method for detecting foreign matter in a display panel and a related device. Background Art

[0002] During the production process of display panels such as FOG (Film on Glass) panels, due to environmental and process limitations, some tiny foreign matter may appear on the panel, such as Figure 1 The part within the rectangular frame. If these foreign objects are too large or too many, they will affect the conductivity of the panel particles, which may affect the display effect of the panel and even cause the product to be unqualified. Therefore, it is necessary to detect foreign objects on display panels such as FOG panels to ensure product quality.

[0003] However, the foreign matter detection method in the prior art has the problem of low detection accuracy. For example, it is easy to misdetect adhered particles as foreign matter. Summary of the invention

[0004] In view of this, the present application provides a method and related device for detecting foreign matter in a display panel, which are used to improve the accuracy of foreign matter detection in the display panel and avoid false detection by performing foreign matter removal inspection on the display panel based on conductive particle positioning.

[0005] The specific technical solutions are as follows:

[0006] A method for detecting foreign matter in a display panel, comprising:

[0007] Acquire a first image; the first image is an image obtained by capturing an image of the display panel to be detected;

[0008] Performing foreign body detection on the first image based on a first detection model to obtain a detection result; the detection result is used to characterize a foreign body region and / or a suspected foreign body region in the first image;

[0009] If the detection result indicates that there is a region suspected of being a foreign object in the first image, cropping the region suspected of being a foreign object to obtain a second image of the region suspected of being a foreign object;

[0010] Performing conductive particle positioning on the second image to obtain a conductive particle positioning result;

[0011] It is determined whether the suspected foreign matter is a foreign matter of the display panel according to the distribution information of the conductive particles in the region of the suspected foreign matter represented by the conductive particle positioning result.

[0012] Optionally, acquiring the first image includes:

[0013] A first image is acquired by photographing the display panel using a camera that meets a resolution requirement.

[0014] Optionally, before performing foreign object detection on the first image based on the first detection model, the method further includes at least one of the following:

[0015] Preprocessing the first image, where the preprocessing is used to improve the quality of the first image;

[0016] Based on a cropping rule, the first image or the preprocessed first image is cropped into a plurality of sub-images.

[0017] Optionally, performing foreign body detection on the first image based on the first detection model to obtain a detection result includes:

[0018] Perform foreign body detection on each of the sub-images based on the first detection model to obtain sub-detection results corresponding to each of the sub-images; the detection results include sub-detection results corresponding to each of the sub-images;

[0019] If the detection result indicates that there is a region suspected of being a foreign object in the first image, cropping the region suspected of being a foreign object to obtain a second image of the region suspected of being a foreign object includes:

[0020] If the sub-detection result corresponding to the corresponding sub-image indicates that there is an area suspected of being a foreign object in the corresponding sub-image, the area suspected of being a foreign object in the corresponding sub-image is cropped according to a predetermined area size to obtain a second image of the area suspected of being a foreign object.

[0021] Optionally, performing conductive particle positioning on the second image to obtain a conductive particle positioning result includes:

[0022] Based on the dense point positioning method, conductive particle positioning is performed on the second image to obtain a conductive particle positioning result.

[0023] Optionally, performing conductive particle positioning on the second image based on the dense point positioning method to obtain a conductive particle positioning result includes:

[0024] Based on the second detection model, a FIDT graph corresponding to the second image is generated according to the second image; the pixel value of each pixel on the FIDT graph represents the probability that conductive particles exist at the display panel position corresponding to the pixel on the second image;

[0025] extracting a local maximum value from the FIDT image, and determining a particle position of the conductive particle on the second image based on the extracted local maximum value;

[0026] By determining the K nearest neighbor distances of the particle position of each conductive particle, the size of the conductive particle at each detected particle position is estimated to obtain the size of each conductive particle;

[0027] The conductive particle positioning result includes the particle position and size of the conductive particles.

[0028] Optionally, determining whether the suspected foreign matter is a foreign matter on the display panel according to the distribution information of the conductive particles in the region of the suspected foreign matter represented by the conductive particle positioning result includes:

[0029] Determining the number of conductive particles in a predetermined peripheral area of ​​the suspected foreign matter based on distribution information of conductive particles in the area of ​​the suspected foreign matter characterized by particle positions and sizes of the conductive particles;

[0030] If the number of the conductive particles is not higher than a threshold, determining that the suspected foreign matter is a foreign matter of the display panel;

[0031] If the number of the conductive particles is higher than a threshold, it is determined that the suspected foreign matter is not a foreign matter of the display panel.

[0032] A foreign body detection device for a display panel, comprising:

[0033] An acquisition module, used for acquiring a first image; the first image is an image acquired by acquiring an image of the display panel to be detected;

[0034] A detection module, configured to perform foreign body detection on the first image based on a first detection model to obtain a detection result; the detection result is used to characterize a foreign body region and / or a suspected foreign body region in the first image;

[0035] A cropping module, configured to crop the area suspected of being a foreign body, to obtain a second image of the area suspected of being a foreign body, when the detection result indicates that there is an area suspected of being a foreign body in the first image;

[0036] A positioning module, used for positioning the conductive particles in the second image to obtain a conductive particle positioning result;

[0037] The determination module is used to determine whether the suspected foreign matter is a foreign matter of the display panel according to the distribution information of the conductive particles in the area of ​​the suspected foreign matter represented by the conductive particle positioning result.

[0038] An electronic device, comprising:

[0039] Memory, used to store computer programs;

[0040] The processor is used to implement the foreign matter detection method for the display panel as described in any one of the above items by calling and executing the computer program in the memory.

[0041] A computer-readable medium stores a computer program, which, when executed by a processor, can be used to implement the foreign matter detection method for a display panel as described in any one of the above.

[0042] According to the above scheme, the foreign matter detection method and related devices for the display panel provided by the present application, after obtaining a first image obtained by image acquisition of the display panel to be detected, perform foreign matter detection on the first image based on a first detection model, and then, based on the situation in which the detection result characterizes the existence of an area suspected of foreign matter in the first image, further cropping the area suspected of foreign matter and performing conductive particle positioning on the cropped second image, the conductive particles around the suspected foreign matter can be accurately detected. On this basis, by determining whether the suspected foreign matter is a foreign matter in the display panel based on the distribution information of the conductive particles in the suspected foreign matter area characterized by the conductive particle positioning result, the distribution information of the conductive particles in the suspected foreign matter area can be used as the basis to accurately identify whether the suspected foreign matter is a foreign matter in the display panel, thereby overcoming the problem of passing the adhered conductive particles as foreign matter, improving the accuracy of foreign matter detection on the display panel, and avoiding false detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 is an example diagram of foreign matter on a display panel provided by the present application;

[0045] Figure 2 is a flow chart of a method for detecting foreign matter in a display panel provided by the present application;

[0046] Figure 3 This is an example of a non-foreign matter on the display panel provided by the present application;

[0047] Figure 4 is an example diagram of suspected foreign matter detected provided by this application;

[0048] Figure 5 This is an example of a real foreign object identified from a suspected foreign object provided by the present application;

[0049] Figure 6 is a flowchart for realizing conductive particle positioning of the second image based on the dense point positioning method provided by the present application;

[0050] Figure 7 This is the overall network architecture of HRNet provided by this application;

[0051] Figure 8 is a structural diagram of a foreign body detection device for a display panel provided by the present application;

[0052] Fig. 9 It is a structural diagram of the electronic device provided in this application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] The embodiments of the present application provide a method and a related device for detecting foreign matter in a display panel, which are used to improve the accuracy of foreign matter detection in the display panel and avoid false detection by performing foreign matter removal inspection on the display panel based on the positioning of conductive particles.

[0055] See also Figure 2 As shown in the method flow chart, the foreign body detection method for a display panel provided in the embodiment of the present application may at least include the following steps 201 to 205, which are described in detail below.

[0056] Step 201, obtaining a first image; the first image is an image obtained by capturing an image of a display panel to be inspected.

[0057] The display panel to be inspected may be, but is not limited to, a FOG panel to be inspected for foreign matter.

[0058] Optionally, this step may specifically obtain a first image obtained by photographing the display panel using a camera that meets the resolution requirement.

[0059] The resolution condition is used to indicate that the camera resolution is high resolution. Specifically, but not limited to, the resolution condition may be set to: the camera resolution is greater than a predetermined resolution threshold.

[0060] In implementation, optionally, the display panel of the FOG panel to be inspected can be photographed by a high-resolution line scan camera to acquire a high-resolution image of the display panel as the first image. Exemplarily, the width of the acquired first image resolution is 30,000 to 60,000 and the height is about 2,000.

[0061] Step 202: Perform foreign body detection on the first image based on a first detection model to obtain a detection result; the detection result is used to characterize a foreign body region and / or a suspected foreign body region in the first image.

[0062] The first detection model is a pre-trained model for detecting foreign objects on a display panel based on an image of the display panel, and may be a computer vision model in the field of artificial intelligence, and may specifically be, but not limited to, a target detection model such as yolov10.

[0063] In display panels such as FOG panels, some foreign objects have similar visual features to conductive particles. For example, some small foreign objects are close in size to conductive particles, only slightly larger than conductive particles. This can easily cause the adhesion particles to be detected as foreign objects. However, when there are conductive particles around the suspected foreign object, it is not necessary to detect it (the suspected foreign object) as a foreign object, because it does not affect the conductivity of the particles and should be identified as non-foreign objects. Figure 3 As shown in the figure, the part in the rectangular frame is not a foreign object because the conductive particles around it have obvious indentations, which do not affect the conductivity of the particles. Figure 1 The part within the rectangular frame, Figure 1 The part in the rectangular box is a foreign object because it has affected the indentation of the surrounding conductive particles, thereby affecting the conductive properties of the conductive particles. In view of the above-mentioned characteristics of foreign objects / suspected foreign objects, when constructing the first detection model, in addition to enabling the first detection model to identify foreign objects based on the distinctive features of foreign objects (such as a size that is significantly larger than the regular size of conductive particles), the first detection model also enables the first detection model to identify particles whose visual features on the display panel image are not clear enough (such as a size that is close to the regular size of conductive particles) as suspected foreign objects, that is, it does not give a conclusion on whether they are foreign objects, so as to leave it for subsequent foreign object removal inspection based on the positioning of conductive particles to accurately identify whether the suspected foreign objects are foreign objects on the display panel.

[0064] Based on this, in this step, after obtaining the first image, the first image can be input into the first detection model to obtain the detection result generated and output by the first detection model through foreign body detection on the first image; the detection result is used to characterize the foreign body area and / or the suspected foreign body area existing in the first image.

[0065] During implementation, optionally, before using the first detection model to perform foreign body detection, the first image can be preprocessed using image processing technology. The preprocessing performed includes but is not limited to denoising, image enhancement and other operations to improve the quality of the first image, thereby facilitating accurate and efficient subsequent foreign body detection processing based on the preprocessed first image.

[0066] In addition, optionally, before using the first detection model to perform foreign object detection, the first image (corresponding to the case where preprocessing is not performed on the first image) or the preprocessed first image (corresponding to the case where preprocessing is performed on the first image) can be cropped into multiple sub-images based on cropping rules.

[0067] The cropping rule may include, but is not limited to, performing traversal cropping on the first image based on a predetermined size, for example, taking the height of the first image as the side length, cropping the first image from left to right into square images in sequence until the cropping is completed, for example, cropping the first image with a width of 30000 to 60000 and a height of 2000 from left to right into a plurality of square images with a side length of 2000, etc. Optionally, each cropped sub-image may be scaled to a predetermined size, such as 1000*1000.

[0068] On this basis, each sub-image (such as each sub-image after scaling) can be input into a first detection model such as the yolov10 target detection model to perform foreign body detection on each sub-image based on the first detection model to obtain sub-detection results corresponding to each sub-image.

[0069] It is easy to understand that in this case, the detection result of the first detection model on the first image includes the sub-detection results corresponding to each of the sub-images. The sub-detection result corresponding to each sub-image is used to characterize the foreign body area and / or the suspected foreign body area in the sub-image.

[0070] Step 203: If the detection result indicates that there is a region suspected of being a foreign object in the first image, the region suspected of being a foreign object is cropped to obtain a second image of the region suspected of being a foreign object.

[0071] If the detection result indicates that there is no area suspected of being a foreign object in the first image, it is not necessary to perform the processing of steps 203 to 205.

[0072] On the contrary, if the detection result indicates that there is an area suspected of foreign matter in the first image, it is necessary to further accurately identify whether the suspected foreign matter is a foreign matter in the display panel. In this case, the area suspected of foreign matter can be cropped first to obtain a second image of the area suspected of foreign matter, for example, the area suspected of foreign matter can be cropped according to a predetermined area size such as 128*128, so as to determine whether the suspected foreign matter is a foreign matter in the display panel by subsequent processing of the second image of the area suspected of foreign matter.

[0073] For the case where the first image is cropped into sub-images, it can be specifically determined whether the sub-detection result corresponding to each sub-image represents an area in the sub-image where suspected foreign matter exists. If the sub-detection result corresponding to the corresponding sub-image represents an area in the corresponding sub-image where suspected foreign matter exists, the area in the corresponding sub-image where suspected foreign matter exists can be cropped according to a predetermined area size such as 128*128 to obtain a second image of the area in which suspected foreign matter exists.

[0074] Step 204: Conductive particle positioning is performed on the second image to obtain a conductive particle positioning result.

[0075] After obtaining the second image of the area suspected of being a foreign body, this step specifically performs conductive particle positioning on the second image based on a dense point positioning method to obtain a conductive particle positioning result.

[0076] Optionally, the conductive particle positioning result includes the particle position (such as the position coordinates of the particles in the display panel) and size of the conductive particles.

[0077] Step 205 : determining whether the suspected foreign matter is a foreign matter of the display panel according to the distribution information of the conductive particles in the region of the suspected foreign matter represented by the conductive particle positioning result.

[0078] In this step, the number of conductive particles in a predetermined peripheral area of ​​the suspected foreign matter can be determined based on the distribution information of the conductive particles in the area of ​​the suspected foreign matter on the second image characterized by the particle position and size of the conductive particles on the corresponding second image, wherein if the number of conductive particles is not higher than a threshold value, the suspected foreign matter is determined to be a foreign matter of the display panel. In this case, it means that there are no or insufficient normal particle indentations around the suspected foreign matter, which will affect the display performance of the display panel. Therefore, the suspected foreign matter is identified as a foreign matter. On the contrary, if the number of conductive particles is higher than the threshold value, the suspected foreign matter is determined to be a foreign matter of the display panel. In this case, it means that there are or sufficient normal particle indentations around the suspected foreign matter, which will not affect the display performance of the display panel. Therefore, the suspected foreign matter is identified as a non-foreign matter.

[0079] See also Figure 4-Figure 5 For example, Figure 4 Each rectangular box in the second image represents a suspected foreign body region. The embodiment of the present application locates the conductive particles in the second image by dense point positioning. On this basis, the number of conductive particles around the suspected foreign body is determined according to the conductive particle distribution information around the suspected foreign body, and then the number of conductive particles around the suspected foreign body is accurately identified as to whether the suspected foreign body is a foreign body of the display panel. See Figure 5 , provides examples of real foreign bodies screened from suspected foreign bodies, due to Figure 5There are no particle indentations in the local neighborhoods of these suspected foreign objects, so they are identified as real foreign objects in the display panel.

[0080] According to the above scheme, the foreign matter detection method for the display panel provided by the present application, after acquiring a first image obtained by image acquisition of the display panel to be inspected, performs foreign matter detection on the first image based on a first detection model, and based on the situation in which the detection result characterizes the existence of an area suspected of foreign matter in the first image, by further cropping the area suspected of foreign matter and performing conductive particle positioning on the cropped second image, the conductive particles around the suspected foreign matter can be accurately detected. On this basis, by determining whether the suspected foreign matter is a foreign matter in the display panel based on the distribution information of the conductive particles in the suspected foreign matter area characterized by the conductive particle positioning result, the distribution information of the conductive particles in the suspected foreign matter area can be used as the basis to accurately identify whether the suspected foreign matter is a foreign matter in the display panel, thereby overcoming the problem of passing the adhered conductive particles as foreign matter, improving the accuracy of foreign matter detection of the display panel, and avoiding false detection.

[0081] The following further provides a specific implementation process of positioning the conductive particles in the second image based on the dense point positioning method.

[0082] See also Figure 6 Based on the dense point positioning method, the process of positioning the conductive particles in the second image can be implemented as follows:

[0083] Step 601: Generate a FIDT graph corresponding to the second image based on the second detection model; the pixel value of each pixel on the FIDT graph represents the probability that conductive particles exist at the display panel position corresponding to the pixel on the second image.

[0084] The applicant has found that particle detection / positioning tasks and crowd positioning have similar challenges, such as dense distribution and overlap between particles similar to crowd characteristics. Therefore, this embodiment applies the FIDT (Focal Inverse Distance Transform) graph to the detection / positioning of conductive particles based on the dense point positioning method, so as to learn from the advantages of FIDT in crowd positioning and address similar challenges in particle detection / positioning tasks. The following further describes the specific implementation process of applying FIDT to particle detection / positioning based on the dense point positioning method.

[0085] When applying FIDT to particle detection / localization, optionally, this embodiment uses HRNet as the basic network architecture to construct a second detection model for generating a FIDT graph.

[0086] HRNet has multi-resolution feature representation capabilities, can process feature maps in parallel at different scales, and enhance feature expression capabilities by continuously fusing information at each resolution.

[0087] See also Figure 7 , shows the overall network architecture of HRNet, which consists of multiple branches, each of which is used to extract features of different resolutions and finally output a high-resolution feature map. The horizontal and vertical directions represent the depth of the network and the scale of the feature map, respectively. The entire network consists of four stages of self-networks. Each node has a new branch compared to the previous stage. The resolution of the new branch is halved compared to the upper layer, but the number of channels is doubled.

[0088] The second detection model of the embodiment of the present application adds a convolution layer and a transposed convolution layer on the basis of the HRNet network, and generates a FIDT graph based on the structure through a regression method. That is, the input of the second detection model is a second image, such as a 128*128 second image, and a FIDT graph corresponding to the second image is generated and output through a regression method. The pixel value P(i, j) of each pixel on the FIDT graph represents the probability that a conductive particle exists at the display panel position corresponding to the pixel on the second image. The exemplary expression is as follows:

[0089]

[0090] Among them, w k is the weight associated with the kth particle, and d(i, j, k) is the distance from pixel (i, j) to particle k.

[0091] Step 602: extract a local maximum value from the FIDT image, and determine the particle position of the conductive particles on the second image based on the extracted local maximum value.

[0092] Based on step 601, this step can further extract the local maximum from the generated FIDT graph through a local maximum detection strategy (LMDS) to determine the position of the conductive particle, wherein the position of the extracted local maximum can be specifically determined as the position of the conductive particle. The local maximum detection formula is:

[0093]

[0094] Wherein, N(i, j) represents the neighborhood of pixel (i, j). 1 represents the presence of conductive particles at pixel (i, j), and 0 represents the absence of conductive particles at pixel (i, j).

[0095] Step 603: By determining the K nearest neighbor distances of the particle position of each conductive particle, the size of the conductive particle at each detected particle position is estimated to obtain the size of each conductive particle.

[0096] In addition to detecting the position of conductive particles, the size of the detected conductive particles can also be estimated.

[0097] Optionally, this embodiment combines the K-nearest neighbor algorithm to estimate the size of the detected particle position. By calculating the K nearest neighbor distance of the particle position of each conductive particle, the actual size of the conductive particle is obtained, and the corresponding bounding box can be generated. The exemplary calculation formula is:

[0098]

[0099] Among them, N k are the K nearest neighbors of the conductive particle (x, y), and scale_factor is the scaling factor used to adjust the size of the conductive particle.

[0100] The particle positions and sizes of the conductive particles together form the positioning results of the conductive particles, that is, the conductive particle positioning results include the particle positions and sizes of the conductive particles.

[0101] This embodiment applies the FIDT map to conductive particle detection / positioning based on a dense point positioning method, which can draw on the advantages of FIDT in crowd positioning, cope with similar challenges in particle detection / positioning tasks, and combine with high-resolution feature maps to improve the detection accuracy of the conductive particle position, and can provide accurate distribution information of conductive particles for effective identification of suspected foreign matter, and support the subsequent accurate identification of whether the suspected foreign matter is a foreign matter in the display panel based on the distribution information of conductive particles in the suspected foreign matter area, thereby overcoming the problem of misdetecting adhered conductive particles as foreign matter, improving the accuracy of foreign matter detection on the display panel, and avoiding false detection.

[0102] At the same time, the method provided in the embodiment of the present application is simple to operate, easy to implement, and has high practical value.

[0103] Corresponding to the above method, the embodiment of the present application further provides a foreign body detection device for a display panel, see Figure 8 The schematic diagram of the composition structure of the device comprises:

[0104] An acquisition module 801 is used to acquire a first image; the first image is an image acquired by acquiring an image of a display panel to be detected;

[0105] A detection module 802 is used to perform foreign body detection on the first image based on a first detection model to obtain a detection result; the detection result is used to characterize a foreign body region and / or a suspected foreign body region in the first image;

[0106] A cropping module 803 is used to crop the suspected foreign body region when the detection result indicates that there is a suspected foreign body region in the first image, so as to obtain a second image of the suspected foreign body region;

[0107] A positioning module 804 is used to perform conductive particle positioning on the second image to obtain a conductive particle positioning result;

[0108] The determination module 805 is used to determine whether the suspected foreign matter is a foreign matter of the display panel according to the distribution information of the conductive particles in the region of the suspected foreign matter represented by the conductive particle positioning result.

[0109] In an optional implementation manner, the acquisition module 801 is specifically used to: acquire a first image obtained by photographing the display panel using a camera that meets a resolution requirement.

[0110] In an optional embodiment, the above device further includes:

[0111] A preprocessing module, used for preprocessing the first image before performing foreign body detection on the first image based on a first detection model, wherein the preprocessing is used for improving the quality of the first image;

[0112] The cropping module 803 is further used to crop the first image or the preprocessed first image into multiple sub-images based on a cropping rule before performing foreign object detection on the first image based on the first detection model.

[0113] In an optional implementation, the detection module 802 is specifically configured to perform foreign body detection on each of the sub-images based on the first detection model to obtain sub-detection results corresponding to each of the sub-images; the detection results include sub-detection results corresponding to each of the sub-images;

[0114] The cropping module 803 is specifically used to: if the sub-detection result corresponding to the corresponding sub-image indicates that there is an area suspected of foreign matter in the corresponding sub-image, crop the area suspected of foreign matter in the corresponding sub-image according to a predetermined area size to obtain a second image of the area suspected of foreign matter.

[0115] In an optional implementation, the positioning module 804 is specifically configured to perform conductive particle positioning on the second image based on a dense point positioning method to obtain a conductive particle positioning result.

[0116] In an optional implementation manner, the positioning module 804, when performing conductive particle positioning on the second image based on the dense point positioning method to obtain the conductive particle positioning result, is specifically configured to:

[0117] Based on the second detection model, a FIDT graph corresponding to the second image is generated according to the second image; the pixel value of each pixel on the FIDT graph represents the probability that conductive particles exist at the display panel position corresponding to the pixel on the second image;

[0118] extracting a local maximum value from the FIDT image, and determining a particle position of the conductive particle on the second image based on the extracted local maximum value;

[0119] By determining the K nearest neighbor distances of the particle position of each conductive particle, the size of the conductive particle at each detected particle position is estimated to obtain the size of each conductive particle;

[0120] The conductive particle positioning result includes the particle position and size of the conductive particles.

[0121] In an optional implementation manner, the determination module 805 is specifically configured to:

[0122] Determining the number of conductive particles in a predetermined peripheral area of ​​the suspected foreign matter based on distribution information of conductive particles in the area of ​​the suspected foreign matter characterized by particle positions and sizes of the conductive particles;

[0123] If the number of the conductive particles is not higher than a threshold, determining that the suspected foreign matter is a foreign matter of the display panel;

[0124] If the number of the conductive particles is higher than a threshold, it is determined that the suspected foreign matter is not a foreign matter of the display panel.

[0125] As for the foreign matter detection device for a display panel disclosed in the embodiment of the present application, since it corresponds to the foreign matter detection method for a display panel disclosed in the above method embodiment, the description is relatively simple. For relevant similarities, please refer to the description of the above method embodiments, which will not be described in detail here.

[0126] The present application also discloses an electronic device, the composition structure of the electronic device, such as Fig. 9 As shown, including at least:

[0127] The memory 10 is used to store computer programs.

[0128] The processor 20 is used to implement the method for detecting foreign matter on a display panel provided in any one of the above method embodiments by calling and executing the computer program in the memory.

[0129] The processor 20 can be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a neural network processor (NPU), a deep learning processor (DPU) or other programmable logic devices, etc.

[0130] In addition, the electronic device may also include components such as a communication interface and a communication bus. The memory, the processor and the communication interface communicate with each other through the communication bus.

[0131] The communication interface is used for communication between electronic devices and other devices. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0132] In addition, the present application also provides a computer-readable medium having a computer program stored thereon, wherein the computer program includes program code for executing the foreign matter detection method for a display panel as disclosed in any of the method embodiments above, and when executed by a processor, can be used to implement the foreign matter detection method for a display panel as disclosed in any of the method embodiments above.

[0133] In the context of the present application, a computer readable medium (machine readable medium) may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine readable medium may be a machine readable signal medium or a machine readable storage medium. A machine readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0134] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0135] For the convenience of description, the above system or device is described by dividing it into various modules or units according to its functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0136] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.

[0137] Finally, it should be noted that, in this article, relational terms such as first, second, third and target are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also 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 statement "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0138] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting foreign matter in a display panel, characterized in that: include: acquiring a first image; The first image is an image obtained by capturing an image of the display panel to be inspected; Performing foreign body detection on the first image based on a first detection model to obtain a detection result; the detection result is used to characterize a foreign body region and / or a suspected foreign body region in the first image; If the detection result indicates that there is a region suspected of being a foreign object in the first image, cropping the region suspected of being a foreign object to obtain a second image of the region suspected of being a foreign object; Performing conductive particle positioning on the second image to obtain a conductive particle positioning result; It is determined whether the suspected foreign matter is a foreign matter of the display panel according to the distribution information of the conductive particles in the region of the suspected foreign matter represented by the conductive particle positioning result.

2. The method for detecting foreign matter in a display panel according to claim 1, characterized in that: The acquiring of the first image comprises: A first image is acquired by photographing the display panel using a camera that meets a resolution requirement.

3. The method for detecting foreign matter in a display panel according to claim 1, wherein: Before performing foreign body detection on the first image based on the first detection model, the method further includes at least one of the following: Preprocessing the first image, where the preprocessing is used to improve the quality of the first image; Based on a cropping rule, the first image or the preprocessed first image is cropped into a plurality of sub-images.

4. The method for detecting foreign matter in a display panel according to claim 3, characterized in that: The performing foreign body detection on the first image based on the first detection model to obtain a detection result includes: Perform foreign body detection on each of the sub-images based on the first detection model to obtain sub-detection results corresponding to each of the sub-images; the detection results include sub-detection results corresponding to each of the sub-images; If the detection result indicates that there is a region suspected of being a foreign object in the first image, cropping the region suspected of being a foreign object to obtain a second image of the region suspected of being a foreign object includes: If the sub-detection result corresponding to the corresponding sub-image indicates that there is an area suspected of being a foreign object in the corresponding sub-image, the area suspected of being a foreign object in the corresponding sub-image is cropped according to a predetermined area size to obtain a second image of the area suspected of being a foreign object.

5. The method for detecting foreign matter in a display panel according to claim 1, wherein: The performing conductive particle positioning on the second image to obtain a conductive particle positioning result includes: Based on the dense point positioning method, conductive particle positioning is performed on the second image to obtain a conductive particle positioning result.

6. The method for detecting foreign matter in a display panel according to claim 5, characterized in that: The method of performing conductive particle positioning on the second image based on the dense point positioning method to obtain a conductive particle positioning result includes: Based on the second detection model, a FIDT graph corresponding to the second image is generated according to the second image; the pixel value of each pixel on the FIDT graph represents the probability that conductive particles exist at the display panel position corresponding to the pixel on the second image; extracting a local maximum value from the FIDT image, and determining a particle position of the conductive particle on the second image based on the extracted local maximum value; By determining the K nearest neighbor distances of the particle position of each conductive particle, the size of the conductive particle at each detected particle position is estimated to obtain the size of each conductive particle; The conductive particle positioning result includes the particle position and size of the conductive particles.

7. The method for detecting foreign matter in a display panel according to claim 6, wherein: The determining whether the suspected foreign matter is a foreign matter on the display panel according to the distribution information of the conductive particles in the region of the suspected foreign matter represented by the conductive particle positioning result comprises: Determining the number of conductive particles in a predetermined peripheral area of ​​the suspected foreign matter based on distribution information of conductive particles in the area of ​​the suspected foreign matter characterized by particle positions and sizes of the conductive particles; If the number of the conductive particles is not higher than a threshold, determining that the suspected foreign matter is a foreign matter of the display panel; If the number of the conductive particles is higher than a threshold, it is determined that the suspected foreign matter is not a foreign matter of the display panel.

8. A foreign body detection device for a display panel, characterized in that: include: An acquisition module, used for acquiring a first image; The first image is an image obtained by capturing an image of the display panel to be inspected; A detection module, configured to perform foreign body detection on the first image based on a first detection model to obtain a detection result; the detection result is used to characterize a foreign body region and / or a suspected foreign body region in the first image; A cropping module, configured to crop the area suspected of being a foreign body, to obtain a second image of the area suspected of being a foreign body, when the detection result indicates that there is an area suspected of being a foreign body in the first image; A positioning module, used for positioning the conductive particles in the second image to obtain a conductive particle positioning result; The determination module is used to determine whether the suspected foreign matter is a foreign matter of the display panel according to the distribution information of the conductive particles in the area of ​​the suspected foreign matter represented by the conductive particle positioning result.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to implement the method for detecting foreign matter in a display panel according to any one of claims 1 to 7 by calling and executing a computer program in the memory.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can be used to implement the foreign matter detection method for a display panel as described in any one of claims 1 to 7.

Images